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 2022/06/24 22:19:37 UTC

[tvm-site] branch asf-site updated: deploying docs (apache/tvm@bca278a8294fe28e3428a5cd63b9ea361e47070c)

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 b975ead60 deploying docs (apache/tvm@bca278a8294fe28e3428a5cd63b9ea361e47070c)
b975ead60 is described below

commit b975ead60155d467962b30b17d4c3d496835aceb
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 24 22:19:32 2022 +0000

    deploying docs (apache/tvm@bca278a8294fe28e3428a5cd63b9ea361e47070c)
---
 .../how_to/compile_models/from_mxnet.rst.txt       |   2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |   2 +-
 .../how_to/compile_models/from_paddle.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       |  16 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |   4 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |  10 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |  16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |   2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |   2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |  16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |   8 +-
 .../sg_execution_times.rst.txt                     |  14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 983 ++++-----------------
 .../tune_network_cuda.rst.txt                      |   2 +-
 .../tune_network_x86.rst.txt                       |   4 +-
 .../tune_sparse_x86.rst.txt                        | 134 +--
 .../tune_with_autotvm/sg_execution_times.rst.txt   |   4 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |  34 +-
 .../work_with_microtvm/micro_autotune.rst.txt      |  16 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |  16 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |   8 +-
 .../work_with_relay/sg_execution_times.rst.txt     |   6 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |   2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |  12 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |   2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |   4 +-
 .../frontend/deploy_classification.rst.txt         |   2 +-
 .../tutorials/frontend/deploy_detection.rst.txt    |   2 +-
 .../tutorials/frontend/sg_execution_times.rst.txt  |   6 +-
 .../tutorials/optimize/sg_execution_times.rst.txt  |   6 +-
 .../topic/vta/tutorials/sg_execution_times.rst.txt |   6 +-
 .../tutorial/auto_scheduler_matmul_x86.rst.txt     |  14 +-
 docs/_sources/tutorial/autotvm_matmul_x86.rst.txt  |  20 +-
 docs/_sources/tutorial/autotvm_relay_x86.rst.txt   |  54 +-
 .../tutorial/cross_compilation_and_rpc.rst.txt     |   2 +-
 docs/_sources/tutorial/intro_topi.rst.txt          |   2 +-
 docs/_sources/tutorial/sg_execution_times.rst.txt  |  16 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |  47 +-
 docs/commit_hash                                   |   2 +-
 docs/how_to/compile_models/from_mxnet.html         |   2 +-
 docs/how_to/compile_models/from_oneflow.html       |  73 +-
 docs/how_to/compile_models/from_paddle.html        |   2 +-
 docs/how_to/compile_models/from_pytorch.html       |   8 +-
 docs/how_to/compile_models/from_tensorflow.html    |   2 +-
 docs/how_to/compile_models/sg_execution_times.html |  22 +-
 .../deploy_models/deploy_model_on_android.html     |   2 +-
 .../deploy_object_detection_pytorch.html           |  27 +-
 docs/how_to/deploy_models/deploy_prequantized.html |  11 +-
 .../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  |  41 +-
 docs/how_to/deploy_models/sg_execution_times.html  |  16 +-
 .../extend_tvm/bring_your_own_datatypes.html       |   4 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |  10 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |  16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |   2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |   2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |  16 +-
 .../optimize_operators/sg_execution_times.html     |   8 +-
 .../sg_execution_times.html                        |  14 +-
 .../tune_conv2d_layer_cuda.html                    | 983 ++++-----------------
 .../tune_with_autoscheduler/tune_network_cuda.html |   2 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |   4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   | 134 +--
 .../tune_with_autotvm/sg_execution_times.html      |   4 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |  34 +-
 docs/how_to/work_with_microtvm/micro_autotune.html |  16 +-
 docs/how_to/work_with_microtvm/micro_train.html    |  16 +-
 .../work_with_microtvm/sg_execution_times.html     |   8 +-
 .../how_to/work_with_relay/sg_execution_times.html |   6 +-
 docs/how_to/work_with_schedules/intrin_math.html   |   2 +-
 .../work_with_schedules/sg_execution_times.html    |  12 +-
 docs/how_to/work_with_schedules/tensorize.html     |   2 +-
 docs/reference/api/python/auto_scheduler.html      |   4 +-
 .../api/typedoc/classes/bytestreamreader.html      |  12 +-
 .../api/typedoc/classes/cachedcallstack.html       |  34 +-
 docs/reference/api/typedoc/classes/dldatatype.html |  12 +-
 docs/reference/api/typedoc/classes/dldevice.html   |  10 +-
 .../reference/api/typedoc/classes/environment.html |  12 +-
 docs/reference/api/typedoc/classes/ffilibrary.html |  20 +-
 .../api/typedoc/classes/graphexecutor.html         |  16 +-
 docs/reference/api/typedoc/classes/instance.html   |  40 +-
 docs/reference/api/typedoc/classes/memory.html     |  34 +-
 docs/reference/api/typedoc/classes/module.html     |  10 +-
 docs/reference/api/typedoc/classes/ndarray.html    |  22 +-
 .../api/typedoc/classes/packedfunccell.html        |   6 +-
 docs/reference/api/typedoc/classes/rpcserver.html  |  14 +-
 docs/reference/api/typedoc/classes/scalar.html     |   6 +-
 .../api/typedoc/classes/webgpucontext.html         |  12 +-
 docs/reference/api/typedoc/enums/argtypecode.html  |  30 +-
 .../api/typedoc/enums/aynccallbackcode.html        |   4 +-
 .../api/typedoc/enums/dldatatypecode.html          |   8 +-
 .../api/typedoc/enums/rpcserverstate.html          |  12 +-
 docs/reference/api/typedoc/enums/sizeof.html       |  18 +-
 docs/reference/api/typedoc/index.html              | 112 +--
 .../api/typedoc/interfaces/disposable.html         |   2 +-
 .../api/typedoc/interfaces/functioninfo.html       |   6 +-
 .../api/typedoc/interfaces/libraryprovider.html    |   4 +-
 docs/searchindex.js                                |   2 +-
 .../vta/tutorials/autotvm/sg_execution_times.html  |   4 +-
 .../tutorials/frontend/deploy_classification.html  |   2 +-
 .../vta/tutorials/frontend/deploy_detection.html   |   2 +-
 .../vta/tutorials/frontend/sg_execution_times.html |   6 +-
 .../vta/tutorials/optimize/sg_execution_times.html |   6 +-
 docs/topic/vta/tutorials/sg_execution_times.html   |   6 +-
 docs/tutorial/auto_scheduler_matmul_x86.html       |   6 +-
 docs/tutorial/autotvm_matmul_x86.html              |  20 +-
 docs/tutorial/autotvm_relay_x86.html               | 258 +++---
 docs/tutorial/cross_compilation_and_rpc.html       |   2 +-
 docs/tutorial/intro_topi.html                      |   2 +-
 docs/tutorial/sg_execution_times.html              |  20 +-
 docs/tutorial/tensor_expr_get_started.html         |  43 +-
 121 files changed, 1255 insertions(+), 2639 deletions(-)

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 6c44ac499..61bc5bef6 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4f5d8f38-b824-4286-9194-cb3aaeeedca8 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip05845c7c-c55a-4877-820f-1c5ba9f41a60 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 9b32e25d9..de7da5253 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ 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]
      0%|          | 16.0k/41.5M [00:00<07:39, 94.6kB/s]
      0%|          | 40.0k/41.5M [00:00<05:56, 122kB/s] 
      0%|          | 96.0k/41.5M [00:00<03:20, 217kB/s]
      0%|          | 160k/41.5M [00:00<02:34, 280kB/s] 
      1%|          | 280k/41.5M [00:00<01:39, 433kB/s]
      1%|1         | 528k/41.5M [00:01<00:54, 782kB/s]
      2%|2         | 944k/41.5M [00:01<00:32, 1.33MB/s]
      4%|4         | 1.83M/41.5M [00:01<00:15, 2.64MB/s]
      8%|7         | 3.30M/41.5M [00:01<00:08, 4.60MB/s]
     12%|#1        | 4.77M/41.5M [00:01<00:06, 5.91MB/s]
     15%|#5        | 6.24M/41.5M [00:01<00:05, 6.81MB/s]
     19%|#8        | 7.71M/41.5M [00:02<00:04, 7.43MB/s]
     22%|##2       | 9.19M/41.5M [00:02<00:04, 7.87MB/s]
     26%|##5       | 10.6M/41.5M [00:02<00:03, 8.16MB/s]
     29%|##9       | 12.1M/41.5M [00:02<00:03, 8.38MB/s]
     33%|###2      | 13.6M/41.5M [00:02<00:03, 8.52MB/s]
     36%|###6      | 15.1M/41.5M [00:02<00:
 03, 8.62MB/s]
     40%|###9      | 16.5M/41.5M [00:03<00:03, 8.69MB/s]
     43%|####3     | 18.0M/41.5M [00:03<00:02, 8.75MB/s]
     47%|####6     | 19.5M/41.5M [00:03<00:02, 8.78MB/s]
     50%|#####     | 20.9M/41.5M [00:03<00:02, 8.80MB/s]
     54%|#####4    | 22.4M/41.5M [00:03<00:02, 8.81MB/s]
     58%|#####7    | 23.9M/41.5M [00:04<00:02, 8.81MB/s]
     61%|######1   | 25.3M/41.5M [00:04<00:01, 8.82MB/s]
     65%|######4   | 26.8M/41.5M [00:04<00:01, 8.83MB/s]
     68%|######8   | 28.3M/41.5M [00:04<00:01, 8.83MB/s]
     70%|#######   | 29.1M/41.5M [00:04<00:01, 7.46MB/s]
     74%|#######3  | 30.6M/41.5M [00:04<00:01, 7.80MB/s]
     77%|#######6  | 31.8M/41.5M [00:05<00:01, 7.57MB/s]
     79%|#######8  | 32.8M/41.5M [00:05<00:01, 7.16MB/s]
     82%|########2 | 34.2M/41.5M [00:05<00:00, 7.67MB/s]
     86%|########6 | 35.7M/41.5M [00:05<00:00, 8.02MB/s]
     90%|########9 | 37.2M/41.5M [00:05<00:00, 8.28MB/s]
     93%|#########3| 38.6M/41.5M [00:05<00:00, 8.45MB/s]
     97%|#####
 ####6| 40.1M/41.5M [00:06<00:00, 8.57MB/s]
    100%|##########| 41.5M/41.5M [00:06<00:00, 7.08MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
      0%|          | 16.0k/41.5M [00:00<07:24, 97.8kB/s]
      0%|          | 40.0k/41.5M [00:00<05:44, 126kB/s] 
      0%|          | 96.0k/41.5M [00:00<03:13, 224kB/s]
      0%|          | 160k/41.5M [00:00<02:29, 289kB/s] 
      1%|          | 328k/41.5M [00:00<01:17, 554kB/s]
      1%|1         | 544k/41.5M [00:01<00:52, 813kB/s]
      3%|2         | 1.07M/41.5M [00:01<00:25, 1.65MB/s]
      5%|5         | 2.15M/41.5M [00:01<00:12, 3.26MB/s]
      9%|8         | 3.62M/41.5M [00:01<00:07, 5.10MB/s]
     11%|#1        | 4.67M/41.5M [00:01<00:06, 5.55MB/s]
     14%|#4        | 5.81M/41.5M [00:01<00:06, 5.97MB/s]
     18%|#7        | 7.29M/41.5M [00:02<00:05, 6.94MB/s]
     20%|#9        | 8.30M/41.5M [00:02<00:05, 6.81MB/s]
     23%|##2       | 9.34M/41.5M [00:02<00:05, 6.71MB/s]
     26%|##6       | 10.8M/41.5M [00:02<00:04, 7.46MB/s]
     29%|##9       | 12.2M/41.5M [00:02<00:03, 7.73MB/s]
     33%|###2      | 13.6M/41.5M [00:02<00
 :03, 8.18MB/s]
     36%|###6      | 15.1M/41.5M [00:03<00:03, 8.47MB/s]
     40%|###9      | 16.6M/41.5M [00:03<00:03, 8.69MB/s]
     43%|####3     | 18.0M/41.5M [00:03<00:02, 8.83MB/s]
     47%|####7     | 19.5M/41.5M [00:03<00:02, 8.92MB/s]
     51%|#####     | 21.0M/41.5M [00:03<00:02, 9.01MB/s]
     54%|#####4    | 22.5M/41.5M [00:03<00:02, 9.05MB/s]
     58%|#####7    | 23.9M/41.5M [00:03<00:01, 9.80MB/s]
     61%|######1   | 25.4M/41.5M [00:04<00:01, 9.59MB/s]
     65%|######4   | 26.9M/41.5M [00:04<00:01, 9.46MB/s]
     68%|######8   | 28.3M/41.5M [00:04<00:01, 8.72MB/s]
     72%|#######1  | 29.8M/41.5M [00:04<00:01, 8.85MB/s]
     75%|#######5  | 31.3M/41.5M [00:04<00:01, 8.95MB/s]
     79%|#######8  | 32.8M/41.5M [00:05<00:01, 9.01MB/s]
     82%|########2 | 34.2M/41.5M [00:05<00:00, 10.3MB/s]
     86%|########6 | 35.7M/41.5M [00:05<00:00, 11.3MB/s]
     89%|########8 | 36.8M/41.5M [00:05<00:00, 10.4MB/s]
     91%|#########1| 37.9M/41.5M [00:05<00:00, 9.10MB/s]
     94%|####
 #####3| 38.8M/41.5M [00:05<00:00, 8.11MB/s]
     97%|#########6| 40.1M/41.5M [00:05<00:00, 8.17MB/s]
    100%|##########| 41.5M/41.5M [00:05<00:00, 7.37MB/s]
 
 
 
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 96aba6643..51f7247dd 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  11.597 seconds)
+   **Total running time of the script:** ( 1 minutes  6.624 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 8317b2c64..e0ef81a89 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ Load a pretrained PyTorch model
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
      2%|2         | 1.01M/44.7M [00:00<00:04, 10.5MB/s]
      6%|6         | 2.85M/44.7M [00:00<00:02, 15.7MB/s]
     14%|#4        | 6.44M/44.7M [00:00<00:01, 25.6MB/s]
     30%|##9       | 13.4M/44.7M [00:00<00:00, 43.9MB/s]
     61%|######    | 27.1M/44.7M [00:00<00:00, 79.9MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 79.6MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     50%|#####     | 22.4M/44.7M [00:00<00:00, 235MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 257MB/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 b9b983354..993413510 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -422,7 +422,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  2.552 seconds)
+   **Total running time of the script:** ( 1 minutes  1.361 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 8bb3490d5..9f763a044 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
 
 Computation times
 =================
-**05:25.945** total execution time for **how_to_compile_models** files:
+**05:19.526** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 01:11.597 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 01:06.624 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.552 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.361 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 00:57.354 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 00:56.265 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:31.464 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:31.384 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:23.683 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.067 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:22.535 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:22.462 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:21.733 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:21.872 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:18.871 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.171 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:13.816 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:14.063 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.340 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.258 | 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 57919afc3..c3bdb64b6 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
@@ -440,7 +440,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      15.9836      15.9385      16.3336      15.8066       0.1478   
+      16.0196      15.9892      16.3060      15.8382       0.1700   
                
 
 
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 b90b5ce2d..7e41aaf4d 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
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
      5%|5         | 9.20M/170M [00:00<00:01, 95.7MB/s]
     15%|#4        | 25.0M/170M [00:00<00:01, 137MB/s] 
     24%|##3       | 40.2M/170M [00:00<00:00, 147MB/s]
     33%|###3      | 56.1M/170M [00:00<00:00, 154MB/s]
     42%|####2     | 71.6M/170M [00:00<00:00, 157MB/s]
     51%|#####1    | 87.2M/170M [00:00<00:00, 159MB/s]
     61%|######    | 103M/170M [00:00<00:00, 161MB/s] 
     70%|######9   | 119M/170M [00:00<00:00, 162MB/s]
     79%|#######9  | 134M/170M [00:00<00:00, 162MB/s]
     88%|########8 | 150M/170M [00:01<00:00, 162MB/s]
     97%|#########7| 165M/170M [00:01<00:00, 162MB/s]
    100%|##########| 170M/170M [00:01<00:00, 157MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      1%|          | 1.27M/170M [00:00<00:13, 13.2MB/s]
      2%|2         | 3.89M/170M [00:00<00:08, 21.6MB/s]
      5%|5         | 9.31M/170M [00:00<00:04, 37.5MB/s]
     12%|#1        | 20.1M/170M [00:00<00:02, 67.1MB/s]
     25%|##4       | 41.7M/170M [00:00<00:01, 124MB/s] 
     35%|###5      | 60.1M/170M [00:00<00:00, 148MB/s]
     45%|####5     | 76.7M/170M [00:00<00:00, 156MB/s]
     55%|#####5    | 93.5M/170M [00:00<00:00, 162MB/s]
     65%|######5   | 110M/170M [00:00<00:00, 167MB/s] 
     74%|#######4  | 126M/170M [00:01<00:00, 159MB/s]
     85%|########4 | 144M/170M [00:01<00:00, 165MB/s]
     95%|#########4| 161M/170M [00:01<00:00, 171MB/s]
    100%|##########| 170M/170M [00:01<00:00, 139MB/s]
     /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  53.164 seconds)
+   **Total running time of the script:** ( 2 minutes  57.970 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 a98cedec0..17554bd9b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ training. Other models require a full post training calibration.
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     16%|#5        | 2.11M/13.6M [00:00<00:00, 22.1MB/s]
     45%|####5     | 6.11M/13.6M [00:00<00:00, 33.7MB/s]
     93%|#########2| 12.6M/13.6M [00:00<00:00, 48.4MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 44.2MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
     23%|##2       | 3.08M/13.6M [00:00<00:00, 32.3MB/s]
     76%|#######5  | 10.2M/13.6M [00:00<00:00, 57.3MB/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 61.7MB/s]
 
 
 
@@ -399,7 +399,7 @@ 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)  
-      90.3444      90.2612      95.2618      90.0319       0.5189   
+      90.2972      90.2349      94.0197      90.0798       0.3918   
                
 
 
@@ -448,7 +448,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  6.586 seconds)
+   **Total running time of the script:** ( 1 minutes  7.407 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 5ffd55d7b..dc590d3d4 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
@@ -426,7 +426,7 @@ 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)  
-      119.5962     119.6527     120.6479     118.7289      0.3636   
+      119.4027     119.3606     120.5569     118.5830      0.3793   
                
 
 
@@ -463,7 +463,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  54.499 seconds)
+   **Total running time of the script:** ( 1 minutes  57.914 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 23c87efe0..77512c9ed 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  12.805 seconds)
+   **Total running time of the script:** ( 1 minutes  12.133 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 25559ed46..ad68980b1 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
@@ -157,7 +157,7 @@ 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]
      1%|          | 1251/132723 [00:00<00:10, 12412.74KB/s]
      3%|2         | 3518/132723 [00:00<00:07, 18426.23KB/s]
      5%|5         | 7123/132723 [00:00<00:04, 26458.20KB/s]
     10%|9         | 13027/132723 [00:00<00:03, 39306.18KB/s]
     16%|#5        | 20621/132723 [00:00<00:02, 52505.71KB/s]
     21%|##1       | 28109/132723 [00:00<00:01, 60107.13KB/s]
     27%|##7       | 35946/132723 [00:00<00:01, 66072.87KB/s]
     33%|###2      | 43687/132723 [00:00<00:01, 69678.85KB/s]
     39%|###8      | 51366/132723 [00:00<00:01, 71898.57KB/s]
     44%|####4     | 58861/132723 [00:01<00:01, 72834.95KB/s]
     50%|#####     | 66741/132723 [00:01<00:00, 74657.22KB/s]
     56%|#####6    | 74654/132723 [00:01<00:00, 76016.61KB/s]
     62%|######2   | 82562/132723 [00:01<00:00, 76941.09KB/s]
     68%|######8   | 90353/132723 [00:01<00:00, 77232.01KB/s]
     74%|#######4  | 98234/132723 [00:01<00:00, 77705.25KB/s]
     80%|#######9  | 1
 06005/132723 [00:01<00:00, 77667.46KB/s]
     86%|########5 | 113772/132723 [00:01<00:00, 74644.80KB/s]
     91%|#########1| 121262/132723 [00:01<00:00, 72544.29KB/s]
     97%|#########6| 128543/132723 [00:01<00:00, 71327.24KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 66564.69KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      1%|          | 1317/132723 [00:00<00:10, 13116.26KB/s]
      3%|2         | 3557/132723 [00:00<00:06, 18515.81KB/s]
      5%|5         | 7189/132723 [00:00<00:04, 26601.54KB/s]
     10%|9         | 12964/132723 [00:00<00:03, 38872.76KB/s]
     16%|#5        | 20807/132723 [00:00<00:02, 53117.25KB/s]
     22%|##1       | 28824/132723 [00:00<00:01, 62304.76KB/s]
     28%|##7       | 36853/132723 [00:00<00:01, 68177.16KB/s]
     34%|###3      | 44861/132723 [00:00<00:01, 71961.08KB/s]
     40%|###9      | 52805/132723 [00:00<00:01, 74296.92KB/s]
     46%|####5     | 60681/132723 [00:01<00:00, 75670.98KB/s]
     52%|#####1    | 68749/132723 [00:01<00:00, 77200.72KB/s]
     58%|#####7    | 76873/132723 [00:01<00:00, 78427.27KB/s]
     64%|######3   | 84821/132723 [00:01<00:00, 78743.09KB/s]
     70%|#######   | 92952/132723 [00:01<00:00, 79515.89KB/s]
     76%|#######6  | 101064/132723 [00:01<00:00, 79996.69KB/s]
     82%|########2 | 
 109210/132723 [00:01<00:00, 80434.41KB/s]
     88%|########8 | 117294/132723 [00:01<00:00, 80553.84KB/s]
     94%|#########4| 125350/132723 [00:01<00:00, 80437.47KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 70011.97KB/s]
 
 
 
@@ -240,7 +240,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  17.729 seconds)
+   **Total running time of the script:** ( 2 minutes  19.327 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 0502de716..728518dbb 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
@@ -5,22 +5,22 @@
 
 Computation times
 =================
-**10:15.034** total execution time for **how_to_deploy_models** files:
+**10:26.155** total execution time for **how_to_deploy_models** files:
 
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:53.164 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:57.970 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:17.729 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:19.327 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:54.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:57.914 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:12.805 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:12.133 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:06.586 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:07.407 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:28.650 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:28.773 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:21.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:22.626 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.006 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index f81ee83bd..e6007e22c 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipaa8d58dc-c9be-4f91-ac44-3d1ca28e8e3b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip433d11bd-8c9e-40ed-9719-fb14562eb917 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 
 
 
@@ -577,7 +577,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-      Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+      Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
 
 
 
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index b82f74b55..c8ab07f3f 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
 =================
-**00:39.446** total execution time for **how_to_extend_tvm** files:
+**00:39.456** 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``) | 00:36.378 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.275 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.219 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.879 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.953 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.009 | 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 a83f6729e..99e0c9aa9 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
@@ -215,10 +215,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6470us [6470us] (45.84%; 45.84%)
-    FoldScaleAxis: 7645us [5us] (54.16%; 54.16%)
-            FoldConstant: 7640us [1561us] (54.13%; 99.93%)
-                    InferType: 6079us [6079us] (43.07%; 79.57%)
+    InferType: 6753us [6753us] (45.59%; 45.59%)
+    FoldScaleAxis: 8059us [6us] (54.41%; 54.41%)
+            FoldConstant: 8053us [1640us] (54.37%; 99.92%)
+                    InferType: 6414us [6414us] (43.30%; 79.64%)
 
 
 
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6126us [6126us] (44.41%; 44.41%)
-    FoldScaleAxis: 7667us [5us] (55.59%; 55.59%)
-            FoldConstant: 7662us [1569us] (55.55%; 99.94%)
-                    InferType: 6093us [6093us] (44.18%; 79.53%)
+    InferType: 6693us [6693us] (44.45%; 44.45%)
+    FoldScaleAxis: 8363us [6us] (55.55%; 55.55%)
+            FoldConstant: 8358us [1784us] (55.51%; 99.93%)
+                    InferType: 6573us [6573us] (43.66%; 78.65%)
 
 
 
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 505bf1fc1..b35ea23fb 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
@@ -327,7 +327,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 54.178198 ms
+    Convolution: 34.337717 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 e86545a95..4846a1288 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
@@ -658,7 +658,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 6.464348 ms
+    conv2d with tensor core: 7.985035 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 f0f94f29c..bec0b5e44 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.018597
-    Baseline: 3.291772
+    Numpy running time: 0.018953
+    Baseline: 3.409586
 
 
 
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.296020
+    Opt1: 0.310919
 
 
 
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.334483
+    Opt2: 0.346889
 
 
 
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.119389
+    Opt3: 0.119664
 
 
 
@@ -550,7 +550,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.111189
+    Opt4: 0.110782
 
 
 
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.111423
+    Opt5: 0.111538
 
 
 
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
 
  .. code-block:: none
 
-    Opt6: 0.145232
+    Opt6: 0.145749
 
 
 
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 badbd30f6..58c831179 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:34.032** total execution time for **how_to_optimize_operators** files:
+**00:34.876** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:31.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.593 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.223 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.254 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.003 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.029 | 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 c59c88d7a..c4a075c2e 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
 =================
-**05:20.725** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:21.998** 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``) | 02:34.273 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:42.797 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:19.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:20.758 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:42.637 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:43.450 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:26.921 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:17.861 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.458 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.669 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.448 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.463 | 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 fcfc0cac8..e49e810cb 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
@@ -239,428 +239,107 @@ cooperative fetching, unrolling and operator fusion.
                  compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
       buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
       preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 224;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
       allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
         conv2d_nchw_1[1] = 0f32
         conv2d_nchw_1[2] = 0f32
         conv2d_nchw_1[3] = 0f32
         conv2d_nchw_1[4] = 0f32
         conv2d_nchw_1[5] = 0f32
         conv2d_nchw_1[6] = 0f32
-        for (rc.outer.outer: int32, 0, 128) {
-          let cse_var_1: int32 = (rc.outer.outer*36)
+        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, 256) {
+          let cse_var_1: int32 = (rc.outer.outer*18)
            {
-            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[(threadIdx.x_1*24)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49)) + (floordiv(floormod((threadIdx.x_1*8), [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49)) + (floordiv(floormod((threadIdx.x_1*8), 9), 3)*7)) + (floormod(blockIdx.x, 7)*7))  [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49)) + (floordiv(floormod((threadIdx.x_1*8), 9), 3)*7)) + (floormod(blockIdx.x, 7)*7))  [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3)*7)) + (floo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) < 8)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx.x_1*8), 3) + [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) < 8)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx.x_1*8), 3)  [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((floordiv((threadIdx [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3)*7)) + (flo [...]
-              }
-              if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
-                pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3)*7)) + (flo [...]
+            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[(threadIdx.x_1*9)] = 0f32
+              pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
+              pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
+            }
+            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 18), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 168), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 6)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 18), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+            if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+              kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 280), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            }
+            for (rc.outer.inner: int32, 0, 2) {
+              for (rx.outer.inner: int32, 0, 3) {
+                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+                conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+                conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+                conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
               }
             }
-            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + threadIdx.x_2)]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 16), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 8), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 12), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 16), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 20), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 24), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 32), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 18432)]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 40), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 44), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 48), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 52), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 60), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 64), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 68), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 36864)]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 76), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 304), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 80), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 320), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 88), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 352), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 92), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 368), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 96), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 100), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 400), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 104), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 416), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 55296)]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 116), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 464), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 120), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 124), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 496), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 128), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 512), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 132), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 136), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 544), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
-            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
-            kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*36)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 35)]))
           }
         }
-        compute[(((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-        compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
+        for (i1.inner: int32, 0, 2) {
+          for (i3.inner: int32, 0, 7) {
+            compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+          }
+        }
       }
     }
 
@@ -714,7 +393,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.403 ms
+    Execution time of this operator: 0.268 ms
 
 
 
@@ -762,37 +441,37 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+    conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
     conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
     conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
     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_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
     conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
     conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-    conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=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=1)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-    conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-    conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+    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=3)
+    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+    conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=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=16)
     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=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_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+    compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
     s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
     s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
     kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -811,14 +490,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
     kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
+    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=112)
     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=24)
+    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=9)
     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=16)
+    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=112)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -836,9 +515,9 @@ 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__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[7];
-      __shared__ float pad_temp_shared[108];
+    extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+      float conv2d_nchw[14];
+      __shared__ float pad_temp_shared[162];
       __shared__ float kernel_shared[576];
       conv2d_nchw[0] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
@@ -847,377 +526,87 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       conv2d_nchw[4] = 0.000000e+00f;
       conv2d_nchw[5] = 0.000000e+00f;
       conv2d_nchw[6] = 0.000000e+00f;
-      for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+      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 < 256; ++rc_outer_outer) {
         __syncthreads();
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((1 <= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.0000 [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 6) + [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((1 <= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 6) + [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) < 8)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 3) * 7)) + ((((int)threadId [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 3) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 5) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 3) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
+        if (((int)threadIdx.x) < 18) {
+          pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
+          pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
         }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+        kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 4) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 8) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) / 3) + 4) % 6) * 3)) + (((int)threadIdx.x) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 16) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        if (((int)threadIdx.x) < 16) {
+          kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
         }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) < 8)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 3) * 7)) + ((((int)threadI [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 3) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 <= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 3) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
-        }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
+        __syncthreads();
+        for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+          for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+            conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+            conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+            conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+          }
         }
-        if (((int)threadIdx.x) < 4) {
-          pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) && ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((( [...]
+      }
+      for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+        for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+          compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
         }
-        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
-        kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
-        kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
-        kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
-        kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 528)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-        kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-        __syncthreads();
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 36)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
       }
-      compute[((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-      compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
     }
 
 
@@ -1278,7 +667,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  34.273 seconds)
+   **Total running time of the script:** ( 2 minutes  42.797 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 d393fe246..0c8b9a410 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
@@ -646,7 +646,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       9.9472       9.9498      10.0102       9.8816       0.0525   
+      10.0204      10.0450      10.0482       9.9681       0.0370   
                
 
 
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 06fec8a8b..b10e9c561 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
@@ -665,7 +665,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      760.8491     760.8105     761.0520     760.6849      0.1524   
+      759.7623     759.6817     760.1304     759.4748      0.2737   
                
 
 
@@ -693,7 +693,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  19.989 seconds)
+   **Total running time of the script:** ( 1 minutes  20.758 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 1f7729b50..832de88dd 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
@@ -396,121 +396,31 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-      preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
-      for (i0.outer: int32, 0, 8) "parallel" {
-        allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global;
-        for (i1.outer: int32, 0, 64) {
-          for (i.outer.inner: int32, 0, 8) {
-            let cse_var_2: int32 = floordiv(i1.outer, 2)
-            let cse_var_1: int32 = (i.outer.inner*32)
-             {
-              compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
-              compute_5[(cse_var_1 + 1)] = 0f32
-              compute_5[(cse_var_1 + 2)] = 0f32
-              compute_5[(cse_var_1 + 3)] = 0f32
-              compute_5[(cse_var_1 + 4)] = 0f32
-              compute_5[(cse_var_1 + 5)] = 0f32
-              compute_5[(cse_var_1 + 6)] = 0f32
-              compute_5[(cse_var_1 + 7)] = 0f32
-              compute_5[(cse_var_1 + 8)] = 0f32
-              compute_5[(cse_var_1 + 9)] = 0f32
-              compute_5[(cse_var_1 + 10)] = 0f32
-              compute_5[(cse_var_1 + 11)] = 0f32
-              compute_5[(cse_var_1 + 12)] = 0f32
-              compute_5[(cse_var_1 + 13)] = 0f32
-              compute_5[(cse_var_1 + 14)] = 0f32
-              compute_5[(cse_var_1 + 15)] = 0f32
-              compute_5[(cse_var_1 + 16)] = 0f32
-              compute_5[(cse_var_1 + 17)] = 0f32
-              compute_5[(cse_var_1 + 18)] = 0f32
-              compute_5[(cse_var_1 + 19)] = 0f32
-              compute_5[(cse_var_1 + 20)] = 0f32
-              compute_5[(cse_var_1 + 21)] = 0f32
-              compute_5[(cse_var_1 + 22)] = 0f32
-              compute_5[(cse_var_1 + 23)] = 0f32
-              compute_5[(cse_var_1 + 24)] = 0f32
-              compute_5[(cse_var_1 + 25)] = 0f32
-              compute_5[(cse_var_1 + 26)] = 0f32
-              compute_5[(cse_var_1 + 27)] = 0f32
-              compute_5[(cse_var_1 + 28)] = 0f32
-              compute_5[(cse_var_1 + 29)] = 0f32
-              compute_5[(cse_var_1 + 30)] = 0f32
-              compute_5[(cse_var_1 + 31)] = 0f32
-              for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-                let cse_var_35: int32 = (elem_idx*16)
-                let cse_var_34: int32 = (cse_var_1 + 9)
-                let cse_var_33: int32 = (cse_var_1 + 8)
-                let cse_var_32: int32 = (cse_var_1 + 7)
-                let cse_var_31: int32 = (cse_var_1 + 6)
-                let cse_var_30: int32 = (cse_var_1 + 5)
-                let cse_var_29: int32 = (cse_var_1 + 4)
-                let cse_var_28: int32 = (cse_var_1 + 31)
-                let cse_var_27: int32 = (cse_var_1 + 30)
-                let cse_var_26: int32 = (cse_var_1 + 3)
-                let cse_var_25: int32 = (cse_var_1 + 29)
-                let cse_var_24: int32 = (cse_var_1 + 28)
-                let cse_var_23: int32 = (cse_var_1 + 27)
-                let cse_var_22: int32 = (cse_var_1 + 26)
-                let cse_var_21: int32 = (cse_var_1 + 25)
-                let cse_var_20: int32 = (cse_var_1 + 24)
-                let cse_var_19: int32 = (cse_var_1 + 23)
-                let cse_var_18: int32 = (cse_var_1 + 22)
-                let cse_var_17: int32 = (cse_var_1 + 21)
-                let cse_var_16: int32 = (cse_var_1 + 20)
-                let cse_var_15: int32 = (cse_var_1 + 2)
-                let cse_var_14: int32 = (cse_var_1 + 19)
-                let cse_var_13: int32 = (cse_var_1 + 18)
-                let cse_var_12: int32 = (cse_var_1 + 17)
-                let cse_var_11: int32 = (cse_var_1 + 16)
-                let cse_var_10: int32 = (cse_var_1 + 15)
-                let cse_var_9: int32 = (cse_var_1 + 14)
-                let cse_var_8: int32 = (cse_var_1 + 13)
-                let cse_var_7: int32 = (cse_var_1 + 12)
-                let cse_var_6: int32 = (cse_var_1 + 11)
-                let cse_var_5: int32 = (cse_var_1 + 10)
-                let cse_var_4: int32 = (cse_var_1 + 1)
-                let cse_var_3: int32 = ((i0.outer*4096) + (i.outer.inner*512))
-                 {
-                  compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-                  compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-                  compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+      preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+      for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+        allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+          for (i.outer.inner: int32, 0, 2) {
+            for (i.inner.init: int32, 0, 64) {
+              for (j.init: int32, 0, 16) {
+                compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*1024) + (i.inner.init*16)) + j.init)] = 0f32
+              }
+            }
+            for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+              if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+                for (i.inner: int32, 0, 64) {
+                  for (j: int32, 0, 16) {
+                    let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner*16)) + j)
+                    compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+                  }
                 }
               }
             }
           }
-          for (i0.inner: int32, 0, 16) {
-            let cse_var_37: int32 = (i1.outer*8)
-            let cse_var_36: int32 = (((i0.outer*8192) + (i0.inner*512)) + cse_var_37)
-            compute[ramp(cse_var_36, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_37) - (floordiv(i1.outer, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_36, 1, 8)]), broadcast(0f32, 8))
+          for (i0.inner: int32, 0, 128) {
+            for (i1.inner: int32, 0, 16) {
+              let cse_var_2: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
+              compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
+            }
           }
         }
       }
@@ -566,7 +476,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 6.967 ms
+    Execution time of this operator: 1.780 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 dd8078e1a..25a0dcab9 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:43.275** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.226** 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``)           | 00:43.246 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:43.197 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.015 | 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 d599371a1..aef75e23d 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
@@ -879,8 +879,8 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-    No: 6   GFLOPS: 110.58/110.58   result: MeasureResult(costs=(0.0020934496458333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8007960319519043, timestamp=1656104860.0191834)      [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-    No: 7   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 6   GFLOPS: 42.41/42.41     result: MeasureResult(costs=(0.005458147105263158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6413054466247559, timestamp=1656107178.9823925)       [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+    No: 7   GFLOPS: 0.00/42.41      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
@@ -1003,7 +1003,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-    No: 8   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 8   GFLOPS: 0.00/42.41      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
@@ -1126,7 +1126,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 1, 32]), ('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,943546
-    No: 9   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 9   GFLOPS: 0.00/42.41      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
@@ -1249,7 +1249,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('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,2868708
-    No: 10  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 10  GFLOPS: 0.00/42.41      result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
         res = future.result()
       File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1267,7 +1267,7 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-    No: 11  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 11  GFLOPS: 0.00/42.41      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
@@ -1390,7 +1390,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-    No: 12  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 12  GFLOPS: 0.00/42.41      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
@@ -1513,7 +1513,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-    No: 13  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 13  GFLOPS: 0.00/42.41      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
@@ -1636,7 +1636,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-    No: 14  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 14  GFLOPS: 0.00/42.41      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
@@ -1759,7 +1759,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-    No: 15  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 15  GFLOPS: 0.00/42.41      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
@@ -1882,7 +1882,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-    No: 16  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 16  GFLOPS: 0.00/42.41      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
@@ -2005,7 +2005,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-    No: 17  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 17  GFLOPS: 0.00/42.41      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
@@ -2128,7 +2128,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-    No: 18  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 18  GFLOPS: 0.00/42.41      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
@@ -2251,7 +2251,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-    No: 19  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+    No: 19  GFLOPS: 0.00/42.41      result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
         yield remote, remote.load_module(os.path.split(build_result.filename)[1])
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
       15: _PyEval_EvalFrameDefault
       14: 0x0000000000537c30
       13: _PyObject_FastCallKeywords
-      12: 0x00007f2968c30fa2
+      12: 0x00007f0334240fa2
       11: _ctypes_callproc
       10: ffi_call
       9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ for this template
       21: _PyFunction_FastCallKeywords
       20: _PyEval_EvalFrameDefault
       19: _PyFunction_FastCall      [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-    No: 20  GFLOPS: 144.00/144.00   result: MeasureResult(costs=(0.0016076431500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.440328598022461, timestamp=1656104886.5177128)       [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+    No: 20  GFLOPS: 142.80/142.80   result: MeasureResult(costs=(0.0016211996300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.430893898010254, timestamp=1656107205.5226185)       [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
 
 
 
@@ -2461,7 +2461,7 @@ and measure running time.
     Best config:
     [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
     Finish loading 20 records
-    Time cost of this operator: 0.001975
+    Time cost of this operator: 0.001977
 
 
 
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 c7aeafd55..a1655833c 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
@@ -328,10 +328,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  
     ---------                                     ---                                           --------  -------  -----              ------  -------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  312.3     98.745   (1, 2, 10, 10, 3)  2       1        
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.033     0.959    (1, 6, 10, 10)     1       1        
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.936     0.296    (1, 1, 10, 10, 3)  1       1        
-    Total_time                                    -                                             316.269   -        -                  -       -        
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.3     98.741   (1, 2, 10, 10, 3)  2       1        
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.088     0.973    (1, 6, 10, 10)     1       1        
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.906     0.286    (1, 1, 10, 10, 3)  1       1        
+    Total_time                                    -                                             317.294   -        -                  -       -        
 
 
 
@@ -397,10 +397,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  
     ---------                                     ---                                           --------  -------  -----              ------  -------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  144.5     98.142   (1, 6, 10, 10, 1)  2       1        
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.816     1.233    (1, 6, 10, 10)     1       1        
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.92      0.625    (1, 1, 10, 10, 3)  1       1        
-    Total_time                                    -                                             147.236   -        -                  -       -        
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  125.8     97.859   (1, 6, 10, 10, 1)  2       1        
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.835     1.427    (1, 6, 10, 10)     1       1        
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.917     0.714    (1, 1, 10, 10, 3)  1       1        
+    Total_time                                    -                                             128.552   -        -                  -       -        
 
 
 
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 a3c23a07a..2e03e6930 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/tmpi3jpugbr/images/random'
+    '/tmp/tmpwu17c7va/images/random'
 
 
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpi3jpugbr/images/target contains 8144 images
-    /tmp/tmpi3jpugbr/images/random contains 5000 images
+    /tmp/tmpwu17c7va/images/target contains 8144 images
+    /tmp/tmpwu17c7va/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 55s - loss: 0.2227 - accuracy: 0.9278 - val_loss: 0.1394 - val_accuracy: 0.9600
+    328/328 - 55s - loss: 0.2224 - accuracy: 0.9256 - val_loss: 0.1308 - val_accuracy: 0.9607
     Epoch 2/3
-    328/328 - 52s - loss: 0.0950 - accuracy: 0.9635 - val_loss: 0.1180 - val_accuracy: 0.9645
+    328/328 - 52s - loss: 0.0942 - accuracy: 0.9650 - val_loss: 0.1156 - val_accuracy: 0.9675
     Epoch 3/3
-    328/328 - 52s - loss: 0.0696 - accuracy: 0.9730 - val_loss: 0.1061 - val_accuracy: 0.9683
+    328/328 - 52s - loss: 0.0661 - accuracy: 0.9760 - val_loss: 0.1062 - val_accuracy: 0.9683
 
-    <keras.callbacks.History object at 0x7f8841913810>
+    <keras.callbacks.History object at 0x7f7859f7ecd0>
 
 
 
@@ -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:** ( 8 minutes  18.148 seconds)
+   **Total running time of the script:** ( 8 minutes  22.193 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 a165dc343..6a78af010 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
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**09:04.164** total execution time for **how_to_work_with_microtvm** files:
+**09:09.121** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 08:18.148 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 08:22.193 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:42.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:43.357 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.571 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)             | 00:00.000 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index a6ddb6e84..fa114363e 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
@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**00:11.540** total execution time for **how_to_work_with_relay** files:
+**00:11.439** total execution time for **how_to_work_with_relay** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.825 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.732 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                   | 00:01.709 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                   | 00:01.702 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)       | 00:00.006 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index f37bafd15..e03531598 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
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7f87b6efc560>
+    <function my_cuda_math_rule at 0x7f77c5cfdf80>
 
 
 
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 eac80e769..eeb8788f2 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
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**00:04.018** total execution time for **how_to_work_with_schedules** files:
+**00:04.030** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.874 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.887 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.952 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:00.941 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.523 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.511 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.097 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)                     | 00:00.098 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.033 | 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 31b4fd1ec..badf10922 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C}
       preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpqfnoel_v/input0.cc'\nsource_filename = \"/tmp/tmpqfnoel_v/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/tmpmk9ddkrn/input0.cc'\nsource_filename = \"/tmp/tmpmk9ddkrn/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 477753dbe..402453174 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:20.772** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.763** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.765 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.756 | 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 8a934b1b3..2d610df2c 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
       DeprecationWarning,
     /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
       relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-    resnet18_v1 inference graph built in 22.15s!
+    resnet18_v1 inference graph built in 22.21s!
 
 
 
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 a110516cc..67df85477 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
       "target_host parameter is going to be deprecated. "
     /workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 15.50s!
+    yolov3-tiny inference graph built in 15.47s!
 
 
 
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 d0be21b20..bd1ab99e2 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
 =================
-**01:29.424** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.808** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:47.334 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:46.799 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.089 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.009 | 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 23c3629be..685de254f 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
 =================
-**00:03.203** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.194** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.812 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.815 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.379 | 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 865216132..911a8c22e 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
 =================
-**00:00.715** total execution time for **topic_vta_tutorials** files:
+**00:00.695** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.387 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.375 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.328 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.320 | 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 c03f2268f..01f7af4ea 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -204,6 +204,13 @@ trials, we can load the best schedule from the log file and apply it.
 
 
 
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+    *E
+
+
 
 
 
@@ -327,7 +334,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 94.232 ms
+    Execution time of this operator: 93.679 ms
 
 
 
@@ -443,6 +450,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
 operations.
 
 
+.. rst-class:: sphx-glr-timing
+
+   **Total running time of the script:** ( 1 minutes  4.997 seconds)
+
+
 .. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
 
 .. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 8fc9fda00..3f1d6e9e1 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 10.25/10.25     result: MeasureResult(costs=(0.026179888799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560853481292725, timestamp=1656103743.932299)        [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-    No: 2   GFLOPS: 2.67/10.25      result: MeasureResult(costs=(0.1006437088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.758345603942871, timestamp=1656103746.2208872)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-    No: 3   GFLOPS: 11.73/11.73     result: MeasureResult(costs=(0.0228894768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5927228927612305, timestamp=1656103746.7917702)       [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-    No: 4   GFLOPS: 1.85/11.73      result: MeasureResult(costs=(0.1451685982,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.432061195373535, timestamp=1656103749.7913995)        [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-    No: 5   GFLOPS: 3.58/11.73      result: MeasureResult(costs=(0.0749977926,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3312056064605713, timestamp=1656103751.250486)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 6   GFLOPS: 1.70/11.73      result: MeasureResult(costs=(0.15767939839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6846201419830322, timestamp=1656103753.9809964)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-    No: 7   GFLOPS: 0.86/11.73      result: MeasureResult(costs=(0.3104200336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.081960439682007, timestamp=1656103759.621381) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 8   GFLOPS: 10.64/11.73     result: MeasureResult(costs=(0.0252224752,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.541811466217041, timestamp=1656103760.1866388)        [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-    No: 9   GFLOPS: 1.89/11.73      result: MeasureResult(costs=(0.14176163400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3615221977233887, timestamp=1656103762.666653) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-    No: 10  GFLOPS: 2.76/11.73      result: MeasureResult(costs=(0.097177004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6571660041809082, timestamp=1656103764.3823142)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+    No: 1   GFLOPS: 9.90/9.90       result: MeasureResult(costs=(0.0271204122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5677464008331299, timestamp=1656106042.2186384)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+    No: 2   GFLOPS: 2.80/9.90       result: MeasureResult(costs=(0.0957543954,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6820878982543945, timestamp=1656106044.4355528)       [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+    No: 3   GFLOPS: 11.79/11.79     result: MeasureResult(costs=(0.0227757816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5960910320281982, timestamp=1656106045.0045743)       [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+    No: 4   GFLOPS: 1.72/11.79      result: MeasureResult(costs=(0.1562885542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.620313882827759, timestamp=1656106048.1923103)        [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+    No: 5   GFLOPS: 3.59/11.79      result: MeasureResult(costs=(0.0747638204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3331496715545654, timestamp=1656106049.6533155)       [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+    No: 6   GFLOPS: 1.66/11.79      result: MeasureResult(costs=(0.1620144816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.71201753616333, timestamp=1656106052.9291515) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+    No: 7   GFLOPS: 0.82/11.79      result: MeasureResult(costs=(0.3285055248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.372325897216797, timestamp=1656106058.3483934)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+    No: 8   GFLOPS: 10.13/11.79     result: MeasureResult(costs=(0.026508293999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5659093856811523, timestamp=1656106058.9367528)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 9   GFLOPS: 1.52/11.79      result: MeasureResult(costs=(0.1767549098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9282991886138916, timestamp=1656106061.9854414)       [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 10  GFLOPS: 2.57/11.79      result: MeasureResult(costs=(0.104364645,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.77083158493042, timestamp=1656106063.8148737)  [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
 
 
 
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index a772b83c9..ac167a44f 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 494.34439387000003, 'median': 494.35892080000485, 'std': 0.746111878681599}
+    {'mean': 495.5015535999996, 'median': 495.33758939999757, 'std': 0.8942336265092279}
 
 
 
@@ -550,31 +550,31 @@ the tuning data to.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.51/  17.51 GFLOPS | Progress: (4/20) | 5.69 s
    [Task  1/25]  Current/Best:    6.17/  17.51 GFLOPS | Progress: (8/20) | 9.15 s
    [Task  1/25]  Current/Best:   11.55/  22.81 GFLOPS | Progress: (12/20) | 11.59 s
    [Task  1/25]  Current/Best:   16.80/  22.81 GFLOPS | Progress: (16/20) | 13.25 s
    [Task  1/25]  Current/Best:   11.62/  23.88 GFLOPS | Progress: (20/20) | 14.99 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.26/  13.15 GFLOPS | Progress: (4/20) | 3.60 s
    [Task  2/25]  Current/Best:   14.15/  18.45 GFLOPS | Progress: (8/20) | 4.92 s
    [Task  2/25]  Current/Best:   21.07/  21.07 GFLOPS | Progress: (12/20) | 6.23 s
    [Task  2/25]  Current/Best:   12.00/  21.07 GFLOPS | Progress: (16/20) | 7.49 s
    [Task  2/25]  Current/Best:   20.16/  21.07 GFLOPS | Progress: (20/20) | 9.04 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.57 GFLOPS | Progress: (4/20) | 5.85 s
    [Task  3/25]  Current/Best:   15.61/  16.92 GFLOPS | Progress: (8/20) | 7.75 s
    [Task  3/25]  Current/Best:   14.89/  16.92 GFLOPS | Progress: (12/20) | 9.47 s
    [Task  3/25]  Current/Best:    7.19/  23.74 GFLOPS | Progress: (16/20) | 11.35 s
    [Task  3/25]  Current/Best:   12.67/  23.74 GFLOPS | Progress: (20/20) | 15.88 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.54/  20.34 GFLOPS | Progress: (4/20) | 2.36 s
    [Task  4/25]  Current/Best:    6.55/  20.34 GFLOPS | Progress: (8/20) | 6.66 s
    [Task  4/25]  Current/Best:   21.86/  21.86 GFLOPS | Progress: (12/20) | 11.22 s
    [Task  4/25]  Current/Best:   15.95/  21.86 GFLOPS | Progress: (16/20) | 13.41 s
    [Task  4/25]  Current/Best:   13.40/  21.86 GFLOPS | Progress: (20/20) | 15.29 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.53/  10.32 GFLOPS | Progress: (4/20) | 2.57 s
    [Task  5/25]  Current/Best:   11.85/  11.85 GFLOPS | Progress: (8/20) | 4.63 s
    [Task  5/25]  Current/Best:   11.61/  18.03 GFLOPS | Progress: (12/20) | 7.72 s
    [Task  5/25]  Current/Best:   11.71/  22.34 GFLOPS | Progress: (16/20) | 9.13 s
    [Task  5/25]  Current/Best:   12.07/  22.34 GFLOPS | Progress: (20/20) | 10.94 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.30/  20.74 GFLOPS | Progress: (4/20) | 3.95 s
    [Task  6/25]  Current/Best:   19.01/  20.74 GFLOPS | Progress: (8/20) | 5.68 s
    [Task  6/25]  Current/Best:   13.31/  20.74 GFLOPS | Progress: (12/20) | 7.60 s
    [Task  6/25]  Current/Best:   19.96/  20.74 GFLOPS | Progress: (16/20) | 9.84 s
    [Task  6/25]  Current/Best:    3.71/  20.74 GFLOPS | Progress: (20/20) | 12.35 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   10.21/  12.91 GFLOPS | Progress: (4/20) | 3.60 s
    [Task  7/25]  Current/Best:   20.29/  21.03 GFLOPS | Progress: (8/20) | 5.09 s
    [Task  7/25]  Current/Best:   15.88/  21.03 GFLOPS | Progress: (12/20) | 7.03 s
    [Task  7/25]  Current/Best:   12.25/  21.03 GFLOPS | Progress: (16/20) | 9.07 s
    [Task  7/25]  Current/Best:    6.44/  21.78 GFLOPS | Progress: (20/20) | 11.50 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.93/  14.01 GFLOPS | Progress: (4/20) | 2.93 s
    [Task  8/25]  Current/Best:    9.56/  14.01 GFLOPS | Progress: (8/20) | 7.59 s
    [Task  8/25]  Current/Best:   12.76/  14.01 GFLOPS | Progress: (12/20) | 13.65 s
    [Task  8/25]  Current/Best:   18.81/  18.81 GFLOPS | Progress: (16/20) | 15.74 s
    [Task  8/25]  Current/Best:   19.64/  19.64 GFLOPS | Progress: (20/20) | 22.22 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.40/  15.41 GFLOPS | Progress: (4/20) | 11.93 s
    [Task  9/25]  Current/Best:   23.47/  23.47 GFLOPS | Progress: (8/20) | 13.73 s
    [Task  9/25]  Current/Best:    8.26/  23.47 GFLOPS | Progress: (12/20) | 16.08 s
    [Task  9/25]  Current/Best:   17.95/  23.47 GFLOPS | Progress: (16/20) | 18.72 s
    [Task  9/25]  Current/Best:    9.10/  23.47 GFLOPS | Progress: (20/20) | 26.22 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.18/  18.18 GFLOPS | Progress: (4/20) | 2.55 s
    [Task 10/25]  Current/Best:   15.22/  18.18 GFLOPS | Progress: (8/20) | 4.12 s
    [Task 10/25]  Current/Best:   12.89/  18.84 GFLOPS | Progress: (12/20) | 5.64 s
    [Task 10/25]  Current/Best:   18.96/  20.47 GFLOPS | Progress: (16/20) | 6.75 s
    [Task 10/25]  Current/Best:    9.08/  20.47 GFLOPS | Progress: (20/20
 ) | 8.26 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.27/  18.08 GFLOPS | Progress: (4/20) | 3.25 s
    [Task 11/25]  Current/Best:   16.95/  18.08 GFLOPS | Progress: (8/20) | 5.96 s
    [Task 11/25]  Current/Best:   18.05/  18.08 GFLOPS | Progress: (12/20) | 8.01 s
    [Task 11/25]  Current/Best:   13.24/  21.20 GFLOPS | Progress: (16/20) | 10.78 s
    [Task 11/25]  Current/Best:   19.42/  21.61 GFLOPS | Progress: (20/20) | 12.80 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.84/  18.03 GFLOPS | Progress: (4/20) | 5.21 s
    [Task 12/25]  Current/Best:    5.17/  18.03 GFLOPS | Progress: (8/20) | 8.87 s
    [Task 12/25]  Current/Best:   18.94/  18.94 GFLOPS | Progress: (12/20) | 10.84 s
    [Task 12/25]  Current/Best:   15.52/  18.94 GFLOPS | Progress: (16/20) | 13.59 s
    [Task 12/25]  Current/Best:   15.10/  18.94 GFLOPS | Progress: (20/20) | 15.55 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.68/  17.25 GFLOPS | Progress: (4/20) | 3.67 s
    [Task 13/25]  Current/Best:   15.82/  20.89 GFLOPS | Progress: (8/20) | 6.11 s
    [Task 13/25]  Current/Best:   19.40/  21.41 GFLOPS | Progress: (12/20) | 8.97 s
    [Task 13/25]  Current/Best:   12.17/  21.41 GFLOPS | Progress: (16/20) | 12.37 s
    [Task 13/25]  Current/Best:   18.47/  21.41 GFLOPS | Progress: (20/20) | 14.60 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.33/  13.33 GFLOPS | Progress: (4/20) | 3.24 s
    [Task 14/25]  Current/Best:    6.08/  13.33 GFLOPS | Progress: (8/20) | 5.40 s
    [Task 14/25]  Current/Best:   21.05/  21.05 GFLOPS | Progress: (12/20) | 7.89 s
    [Task 14/25]  Current/Best:   15.17/  21.05 GFLOPS | Progress: (16/20) | 9.58 s Done.
-
    [Task 14/25]  Current/Best:   17.19/  21.05 GFLOPS | Progress: (20/20) | 11.32 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.21/  17.65 GFLOPS | Progress: (4/20) | 2.68 s
    [Task 15/25]  Current/Best:   14.16/  18.14 GFLOPS | Progress: (8/20) | 3.97 s
    [Task 15/25]  Current/Best:   10.35/  22.10 GFLOPS | Progress: (12/20) | 6.02 s
    [Task 15/25]  Current/Best:   20.39/  22.10 GFLOPS | Progress: (16/20) | 9.13 s
    [Task 15/25]  Current/Best:    9.71/  22.10 GFLOPS | Progress: (20/20) | 10.15 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   19.48/  19.48 GFLOPS | Progress: (4/20) | 2.99 s
    [Task 16/25]  Current/Best:    3.02/  19.48 GFLOPS | Progress: (8/20) | 4.62 s
    [Task 16/25]  Current/Best:   19.11/  19.48 GFLOPS | Progress: (12/20) | 5.84 s
    [Task 16/25]  Current/Best:   17.36/  19.48 GFLOPS | Progress: (16/20) |
  7.21 s
    [Task 16/25]  Current/Best:   10.06/  22.58 GFLOPS | Progress: (20/20) | 9.23 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.08/  18.89 GFLOPS | Progress: (4/20) | 4.66 s
    [Task 17/25]  Current/Best:   14.45/  23.32 GFLOPS | Progress: (8/20) | 7.51 s
    [Task 17/25]  Current/Best:   16.97/  23.32 GFLOPS | Progress: (12/20) | 9.56 s
    [Task 17/25]  Current/Best:   16.54/  23.32 GFLOPS | Progress: (16/20) | 11.69 s
    [Task 17/25]  Current/Best:   10.06/  23.32 GFLOPS | Progress: (20/20) | 13.78 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.36/  17.90 GFLOPS | Progress: (4/20) | 3.64 s
    [Task 18/25]  Current/Best:   10.43/  17.90 GFLOPS | Progress: (8/20) | 7.12 s
    [Task 18/25]  Current/Best:   19.07/  19.07 GFLOPS | Progress: (12/20) | 9.06 s
    [Task 18/25]  Current/Best:   10.08/  19.07 GFLOPS | Progress: (16/20) | 12.59 s
    [Task 18/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (20/20) | 14.10 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.18/  20.46 GFLOPS | Progress: (4/20) | 5.97 s
    [Task 19/25]  Current/Best:    2.61/  20.46 GFLOPS | Progress: (8/20) | 9.18 s
    [Task 19/25]  Current/Best:   19.29/  21.88 GFLOPS | Progress: (12/20) | 11.96 s
    [Task 19/25]  Current/Best:   13.10/  21.88 GFLOPS | Progress: (16/20) | 14.82 s
    [Task 19/25]  Current/Best:    2.70/  23.56 GFLOPS | Progress: (20/20) | 17.63 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.27/  15.33 GFLOPS | Progress: (4/20) | 3.30 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.47/  17.47 GFLOPS | Progress: (4/20) | 6.22 s
    [Task  1/25]  Current/Best:    6.15/  17.47 GFLOPS | Progress: (8/20) | 9.11 s
    [Task  1/25]  Current/Best:   11.53/  22.77 GFLOPS | Progress: (12/20) | 11.57 s
    [Task  1/25]  Current/Best:   16.80/  22.77 GFLOPS | Progress: (16/20) | 13.25 s
    [Task  1/25]  Current/Best:   11.63/  23.87 GFLOPS | Progress: (20/20) | 14.97 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.24/  12.94 GFLOPS | Progress: (4/20) | 3.89 s
    [Task  2/25]  Current/Best:   13.64/  18.57 GFLOPS | Progress: (8/20) | 5.21 s
    [Task  2/25]  Current/Best:   21.34/  21.34 GFLOPS | Progress: (12/20) | 6.52 s
    [Task  2/25]  Current/Best:   12.70/  21.34 GFLOPS | Progress: (16/20) | 7.78 s
    [Task  2/25]  Current/Best:   19.49/  21.34 GFLOPS | Progress: (20/20) | 9.40 s Done.
+
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.63/  10.50 GFLOPS | Progress: (4/20) | 5.84 s
    [Task  3/25]  Current/Best:   15.61/  16.86 GFLOPS | Progress: (8/20) | 7.75 s
    [Task  3/25]  Current/Best:   14.88/  16.86 GFLOPS | Progress: (12/20) | 9.49 s
    [Task  3/25]  Current/Best:    7.22/  23.79 GFLOPS | Progress: (16/20) | 11.40 s
    [Task  3/25]  Current/Best:   12.63/  23.79 GFLOPS | Progress: (20/20) | 15.97 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.56/  20.46 GFLOPS | Progress: (4/20) | 2.38 s
    [Task  4/25]  Current/Best:    6.65/  20.46 GFLOPS | Progress: (8/20) | 7.09 s
    [Task  4/25]  Current/Best:   22.08/  22.08 GFLOPS | Progress: (12/20) | 12.11 s
    [Task  4/25]  Current/Best:   16.04/  22.08 GFLOPS | Progress: (16/20) | 14.49 s
    [Task  4/25]  Current/Best:   12.68/  22.08 GFLOPS | Progress: (20/20) | 16.47 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.73/  10.20 GFLOPS | Progress: (4/20) | 2.59 s
    [Task  5/25]  Current/Best:   11.73/  12.53 GFLOPS | Progress: (8/20) | 4.66 s
    [Task  5/25]  Current/Best:   11.56/  18.02 GFLOPS | Progress: (12/20) | 7.85 s
    [Task  5/25]  Current/Best:   11.79/  22.51 GFLOPS | Progress: (16/20) | 9.27 s
    [Task  5/25]  Current/Best:   12.08/  22.51 GFLOPS | Progress: (20/20) | 11.18 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.21/  20.79 GFLOPS | Progress: (4/20) | 4.25 s
    [Task  6/25]  Current/Best:   18.98/  20.79 GFLOPS | Progress: (8/20) | 6.00 s
    [Task  6/25]  Current/Best:   13.32/  20.79 GFLOPS | Progress: (12/20) | 7.93 s
    [Task  6/25]  Current/Best:   19.97/  20.79 GFLOPS | Progress: (16/20) | 10.16 s
    [Task  6/25]  Current/Best:    3.71/  20.79 GFLOPS | Progress: (20/20) | 12.69 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   10.29/  12.90 GFLOPS | Progress: (4/20) | 3.53 s
    [Task  7/25]  Current/Best:   20.17/  21.20 GFLOPS | Progress: (8/20) | 5.05 s
    [Task  7/25]  Current/Best:   15.80/  21.20 GFLOPS | Progress: (12/20) | 6.97 s
    [Task  7/25]  Current/Best:   12.23/  21.20 GFLOPS | Progress: (16/20) | 9.00 s
    [Task  7/25]  Current/Best:    6.44/  21.64 GFLOPS | Progress: (20/20) | 11.45 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.95/  13.91 GFLOPS | Progress: (4/20) | 2.91 s
    [Task  8/25]  Current/Best:    9.67/  13.91 GFLOPS | Progress: (8/20) | 8.02 s
    [Task  8/25]  Current/Best:   12.53/  13.91 GFLOPS | Progress: (12/20) | 14.52 s
    [Task  8/25]  Current/Best:   18.63/  18.63 GFLOPS | Progress: (16/20) | 16.63 s
    [Task  8/25]  Current/Best:   20.35/  20.35 GFLOPS | Progress: (20/20) | 23.78 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.26/  15.73 GFLOPS | Progress: (4/20) | 11.96 s
    [Task  9/25]  Current/Best:   23.43/  23.43 GFLOPS | Progress: (8/20) | 13.71 s
    [Task  9/25]  Current/Best:    8.32/  23.43 GFLOPS | Progress: (12/20) | 16.25 s
    [Task  9/25]  Current/Best:   17.89/  23.43 GFLOPS | Progress: (16/20) | 19.14 s
    [Task  9/25]  Current/Best:    9.06/  23.43 GFLOPS | Progress: (20/20) | 27.77 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.06/  18.06 GFLOPS | Progress: (4/20) | 2.56 s
    [Task 10/25]  Current/Best:   15.48/  18.06 GFLOPS | Progress: (8/20) | 4.19 s
    [Task 10/25]  Current/Best:   12.82/  19.17 GFLOPS | Progress: (12/20) | 5.73 s
    [Task 10/25]  Current/Best:   19.00/  20.14 GFLOPS | Progress: (16/20) | 6.83 s
    [Task 10/25]  Current/Best:    9.00/  20.14 GFLOPS | Progress: (20/20
 ) | 8.35 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.24/  18.12 GFLOPS | Progress: (4/20) | 3.36 s
    [Task 11/25]  Current/Best:   16.80/  18.12 GFLOPS | Progress: (8/20) | 6.15 s
    [Task 11/25]  Current/Best:   18.03/  18.12 GFLOPS | Progress: (12/20) | 8.24 s
    [Task 11/25]  Current/Best:   13.40/  21.18 GFLOPS | Progress: (16/20) | 11.19 s
    [Task 11/25]  Current/Best:   19.41/  21.58 GFLOPS | Progress: (20/20) | 13.30 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.81/  18.10 GFLOPS | Progress: (4/20) | 5.71 s
    [Task 12/25]  Current/Best:    5.15/  18.10 GFLOPS | Progress: (8/20) | 9.63 s
    [Task 12/25]  Current/Best:   18.87/  18.97 GFLOPS | Progress: (12/20) | 11.63 s
    [Task 12/25]  Current/Best:   14.46/  18.97 GFLOPS | Progress: (16/20) | 14.57 s
    [Task 12/25]  Current/Best:   15.24/  19.01 GFLOPS | Progress: (20/20) | 16.48 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.66/  17.27 GFLOPS | Progress: (4/20) | 3.76 s
    [Task 13/25]  Current/Best:   16.09/  20.89 GFLOPS | Progress: (8/20) | 6.39 s
    [Task 13/25]  Current/Best:   19.43/  20.99 GFLOPS | Progress: (12/20) | 9.49 s
    [Task 13/25]  Current/Best:   12.27/  20.99 GFLOPS | Progress: (16/20) | 12.89 s
    [Task 13/25]  Current/Best:   18.62/  20.99 GFLOPS | Progress: (20/20) | 15.19 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.49/  13.49 GFLOPS | Progress: (4/20) | 3.32 s
    [Task 14/25]  Current/Best:    6.08/  13.49 GFLOPS | Progress: (8/20) | 5.48 s
    [Task 14/25]  Current/Best:   20.52/  20.52 GFLOPS | Progress: (12/20) | 8.15 s
    [Task 14/25]  Current/Best:   16.72/  20.52 GFLOPS | Progress: (16/20) | 9.80 s Done.
+
    [Task 14/25]  Current/Best:   17.23/  20.52 GFLOPS | Progress: (20/20) | 11.54 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.13/  17.65 GFLOPS | Progress: (4/20) | 2.70 s
    [Task 15/25]  Current/Best:   14.23/  18.07 GFLOPS | Progress: (8/20) | 4.05 s
    [Task 15/25]  Current/Best:   10.39/  22.33 GFLOPS | Progress: (12/20) | 6.31 s
    [Task 15/25]  Current/Best:   20.42/  22.33 GFLOPS | Progress: (16/20) | 9.40 s
    [Task 15/25]  Current/Best:    9.69/  22.33 GFLOPS | Progress: (20/20) | 10.42 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.33/  20.33 GFLOPS | Progress: (4/20) | 3.09 s
    [Task 16/25]  Current/Best:    2.99/  20.33 GFLOPS | Progress: (8/20) | 4.72 s
    [Task 16/25]  Current/Best:   19.50/  20.33 GFLOPS | Progress: (12/20) | 5.95 s
    [Task 16/25]  Current/Best:   18.18/  20.33 GFLOPS | Progress: (16/20) |
  7.34 s
    [Task 16/25]  Current/Best:   10.04/  22.34 GFLOPS | Progress: (20/20) | 9.49 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   12.88/  16.64 GFLOPS | Progress: (4/20) | 4.82 s
    [Task 17/25]  Current/Best:   14.38/  23.19 GFLOPS | Progress: (8/20) | 7.72 s
    [Task 17/25]  Current/Best:   17.29/  23.19 GFLOPS | Progress: (12/20) | 9.79 s
    [Task 17/25]  Current/Best:   16.44/  23.19 GFLOPS | Progress: (16/20) | 12.00 s
    [Task 17/25]  Current/Best:   10.05/  23.19 GFLOPS | Progress: (20/20) | 14.17 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.71/  18.04 GFLOPS | Progress: (4/20) | 3.78 s
    [Task 18/25]  Current/Best:   10.56/  20.03 GFLOPS | Progress: (8/20) | 7.51 s
    [Task 18/25]  Current/Best:   19.13/  20.03 GFLOPS | Progress: (12/20) | 9.44 s
    [Task 18/25]  Current/Best:   10.00/  20.03 GFLOPS | Progress: (16/20) | 13.27 s
    [Task 18/25]  Current/Best:   20.59/  20.59 GFLOPS | Progress: (20/20) | 14.79 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    6.89/  20.20 GFLOPS | Progress: (4/20) | 6.24 s
    [Task 19/25]  Current/Best:    2.61/  20.20 GFLOPS | Progress: (8/20) | 9.59 s
    [Task 19/25]  Current/Best:   19.42/  20.89 GFLOPS | Progress: (12/20) | 12.50 s
    [Task 19/25]  Current/Best:   15.22/  21.44 GFLOPS | Progress: (16/20) | 15.45 s
    [Task 19/25]  Current/Best:    2.70/  22.64 GFLOPS | Progress: (20/20) | 18.24 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.01/  14.88 GFLOPS | Progress: (4/20) | 3.37 s Done.
      Done.
-
    [Task 20/25]  Current/Best:    9.64/  15.33 GFLOPS | Progress: (8/20) | 6.57 s
    [Task 20/25]  Current/Best:    2.32/  16.53 GFLOPS | Progress: (12/20) | 10.40 s
    [Task 20/25]  Current/Best:   12.35/  16.53 GFLOPS | Progress: (16/20) | 13.90 s
    [Task 20/25]  Current/Best:   12.25/  22.08 GFLOPS | Progress: (20/20) | 15.98 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.38/  17.67 GFLOPS | Progress: (4/20) | 3.21 s
    [Task 21/25]  Current/Best:   14.63/  17.67 GFLOPS | Progress: (8/20) | 4.79 s
    [Task 21/25]  Current/Best:    1.61/  17.67 GFLOPS | Progress: (12/20) | 6.92 s
    [Task 21/25]  Current/Best:   18.05/  18.05 GFLOPS | Progress: (16/20) | 10.32 s
    [Task 21/25]  Current/Best:    4.46/  18.05 GFLOPS | Progress: (20/20) | 17.31 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  16.93 GFLOPS | Progress: (4/20
 ) | 2.65 s
    [Task 22/25]  Current/Best:    8.66/  21.85 GFLOPS | Progress: (8/20) | 4.62 s
    [Task 22/25]  Current/Best:   20.02/  21.85 GFLOPS | Progress: (12/20) | 6.90 s
    [Task 22/25]  Current/Best:   14.79/  21.85 GFLOPS | Progress: (16/20) | 8.98 s
    [Task 22/25]  Current/Best:   14.97/  21.85 GFLOPS | Progress: (20/20) | 10.69 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.62/  20.08 GFLOPS | Progress: (4/20) | 3.23 s
    [Task 23/25]  Current/Best:   14.39/  20.08 GFLOPS | Progress: (8/20) | 6.49 s
    [Task 23/25]  Current/Best:   20.81/  21.42 GFLOPS | Progress: (12/20) | 8.28 s
    [Task 23/25]  Current/Best:    6.45/  21.42 GFLOPS | Progress: (16/20) | 15.11 s
    [Task 23/25]  Current/Best:    7.78/  21.42 GFLOPS | Progress: (20/20) | 19.31 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.39/   8.39 GFLOPS | Progress: (4/20) | 11.77 s
    [Task 24/25]  Current/Best:    3.56/   8.39 GFLOPS | Progress: (8/20) | 23.00 s
    [Task 24/25]  Current/Best:    4.45/   8.39 GFLOPS | Progress: (12/20) | 33.71 s Done.
+
    [Task 20/25]  Current/Best:    9.95/  14.88 GFLOPS | Progress: (8/20) | 6.79 s
    [Task 20/25]  Current/Best:    2.32/  16.68 GFLOPS | Progress: (12/20) | 10.78 s
    [Task 20/25]  Current/Best:   12.41/  16.68 GFLOPS | Progress: (16/20) | 14.72 s
    [Task 20/25]  Current/Best:   13.53/  21.64 GFLOPS | Progress: (20/20) | 16.82 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.40/  17.65 GFLOPS | Progress: (4/20) | 3.31 s
    [Task 21/25]  Current/Best:   14.32/  17.65 GFLOPS | Progress: (8/20) | 4.90 s
    [Task 21/25]  Current/Best:    1.61/  17.65 GFLOPS | Progress: (12/20) | 7.03 s
    [Task 21/25]  Current/Best:   18.17/  18.17 GFLOPS | Progress: (16/20) | 10.57 s
    [Task 21/25]  Current/Best:    4.47/  18.17 GFLOPS | Progress: (20/20) | 18.01 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  17.01 GFLOPS | Progress: (4/20
 ) | 2.69 s
    [Task 22/25]  Current/Best:    8.75/  21.82 GFLOPS | Progress: (8/20) | 4.75 s
    [Task 22/25]  Current/Best:   19.58/  21.82 GFLOPS | Progress: (12/20) | 7.16 s
    [Task 22/25]  Current/Best:   15.59/  21.82 GFLOPS | Progress: (16/20) | 9.28 s
    [Task 22/25]  Current/Best:   14.64/  21.82 GFLOPS | Progress: (20/20) | 11.03 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.44/  20.18 GFLOPS | Progress: (4/20) | 3.25 s
    [Task 23/25]  Current/Best:   15.75/  20.18 GFLOPS | Progress: (8/20) | 6.74 s
    [Task 23/25]  Current/Best:   20.81/  21.39 GFLOPS | Progress: (12/20) | 8.59 s
    [Task 23/25]  Current/Best:    6.17/  21.39 GFLOPS | Progress: (16/20) | 15.64 s
    [Task 23/25]  Current/Best:    7.65/  21.39 GFLOPS | Progress: (20/20) | 19.93 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.54/   8.54 GFLOPS | Progress: (4/20) | 11.81 s
    [Task 24/25]  Current/Best:    3.44/   8.54 GFLOPS | Progress: (8/20) | 23.07 s
    [Task 24/25]  Current/Best:    4.58/   8.54 GFLOPS | Progress: (12/20) | 33.81 s Done.
      Done.
-
    [Task 24/25]  Current/Best:    5.93/   8.85 GFLOPS | Progress: (16/20) | 39.12 s
    [Task 24/25]  Current/Best:    3.30/   8.85 GFLOPS | Progress: (20/20) | 44.91 s Done.
-
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.55/   2.75 GFLOPS | Progress: (4/20) | 11.57 s
    [Task 25/25]  Current/Best:    5.69/   8.12 GFLOPS | Progress: (8/20) | 22.82 s
    [Task 25/25]  Current/Best:    5.95/   8.12 GFLOPS | Progress: (12/20) | 34.29 s
    [Task 25/25]  Current/Best:    5.78/   8.88 GFLOPS | Progress: (16/20) | 35.98 s
    [Task 25/25]  Current/Best:    2.88/   8.88 GFLOPS | Progress: (20/20) | 46.64 s
+
    [Task 24/25]  Current/Best:    7.13/   8.70 GFLOPS | Progress: (16/20) | 39.61 s
    [Task 24/25]  Current/Best:    3.31/   8.76 GFLOPS | Progress: (20/20) | 45.66 s Done.
+
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.55/   2.92 GFLOPS | Progress: (4/20) | 11.61 s
    [Task 25/25]  Current/Best:    5.65/   7.90 GFLOPS | Progress: (8/20) | 22.86 s
    [Task 25/25]  Current/Best:    5.96/   7.90 GFLOPS | Progress: (12/20) | 34.33 s
    [Task 25/25]  Current/Best:    5.78/   9.25 GFLOPS | Progress: (16/20) | 36.10 s
    [Task 25/25]  Current/Best:    2.88/   9.25 GFLOPS | Progress: (20/20) | 46.78 s
 
 
 
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 410.96431230999997, 'median': 410.907805450006, 'std': 0.8809606599589154}
-    unoptimized: {'mean': 494.34439387000003, 'median': 494.35892080000485, 'std': 0.746111878681599}
+    optimized: {'mean': 411.66733768000313, 'median': 411.5519871500055, 'std': 0.38716530809748584}
+    unoptimized: {'mean': 495.5015535999996, 'median': 495.33758939999757, 'std': 0.8942336265092279}
 
 
 
@@ -759,7 +759,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 10 minutes  10.730 seconds)
+   **Total running time of the script:** ( 10 minutes  22.108 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 824c67763..01be61367 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.319e-07 secs/op
+    1.314e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 61f4e0f4d..b0d7066e1 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0x208f8870)), stage(b, placeholder(b, 0x22007500)), 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, 0x21838230)), stage(b, placeholder(b, 0x44ae300)), 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 aa1968744..275b85ad1 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
 =================
-**12:55.129** total execution time for **tutorial** files:
+**13:23.311** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:10.730 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:22.108 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 00:59.151 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:04.997 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:51.477 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:01.105 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:27.953 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:28.173 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:23.865 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:25.073 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.143 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.037 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.670 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.139 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.148 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.000 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 54fdcf2e1..f82c2de6c 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -289,7 +289,7 @@ helper function to run a profile of the TVM generated code.
  .. code-block:: none
 
     Numpy running time: 0.000008
-    naive: 0.000006
+    naive: 0.000007
 
 
 
@@ -447,7 +447,7 @@ factor to be the number of threads on your CPU.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vector: 0.000026
+    vector: 0.000025
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.727449999492819e-06                    1.0
-                   naive    5.8567999999999996e-06    0.7579214359697446
-                parallel              6.1058e-06      0.7901442261549083
-                  vector             2.63021e-05      3.4037230912818983
+                   numpy    8.136739998008125e-06                    1.0
+                   naive               6.816e-06      0.8376819219575109
+                parallel              6.0722e-06      0.7462693906265255
+                  vector    2.4624800000000002e-05     3.026371741757529
 
 
 
@@ -923,7 +923,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.017895
+    Numpy running time: 0.019072
 
 
 
@@ -983,7 +983,7 @@ optimizations.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    none: 3.283269
+    none: 3.410031
 
 
 
@@ -1088,7 +1088,7 @@ schedule.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    blocking: 0.301291
+    blocking: 0.311227
 
 
 
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vectorization: 0.343489
+    vectorization: 0.343408
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    loop permutation: 0.113401
+    loop permutation: 0.118194
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    array packing: 0.108325
+    array packing: 0.108928
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    block caching: 0.110696
+    block caching: 0.110495
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
 
     /workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallelization: 0.144732
+    parallelization: 0.144055
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none      3.2832685142000004                     1.0
-                blocking            0.3012914517     0.09176570554522938
-           vectorization     0.34348864960000003     0.10461789771821155
-        loop permutation     0.11340090430000001    0.034539028352248924
-           array packing            0.1083249895    0.032993033932953976
-           block caching            0.1106958311    0.033715131924557835
-         parallelization            0.1447315333    0.044081540292559715
+                    none      3.4100311574999997                     1.0
+                blocking     0.31122655289999995     0.09126794991755144
+           vectorization            0.3434083098      0.1007053290538739
+        loop permutation             0.118194036     0.03466069092654618
+           array packing     0.10892798249999999    0.031943398012779005
+           block caching     0.11049544009999998     0.03240305879815117
+         parallelization            0.1440551873     0.04224453696945436
 
 
 
@@ -1673,6 +1673,11 @@ operations with tunable parameters that allows you to automatically optimize
 the computation for specific platforms.
 
 
+.. rst-class:: sphx-glr-timing
+
+   **Total running time of the script:** ( 1 minutes  1.105 seconds)
+
+
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
 
 .. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 7851bad4f..ef11d5e19 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-503f1a65d48acdd15278b6c804ef3b83d70f54ac
+bca278a8294fe28e3428a5cd63b9ea361e47070c
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 796824776..118618fed 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ 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.zip4f5d8f38-b824-4286-9194-cb3aaeeedca8 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.zip05845c7c-c55a-4877-820f-1c5ba9f41a60 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 50640ac29..42f3e3ff0 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,42 +427,43 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
-  0%|          | 16.0k/41.5M [00:00&lt;07:39, 94.6kB/s]
-  0%|          | 40.0k/41.5M [00:00&lt;05:56, 122kB/s]
-  0%|          | 96.0k/41.5M [00:00&lt;03:20, 217kB/s]
-  0%|          | 160k/41.5M [00:00&lt;02:34, 280kB/s]
-  1%|          | 280k/41.5M [00:00&lt;01:39, 433kB/s]
-  1%|1         | 528k/41.5M [00:01&lt;00:54, 782kB/s]
-  2%|2         | 944k/41.5M [00:01&lt;00:32, 1.33MB/s]
-  4%|4         | 1.83M/41.5M [00:01&lt;00:15, 2.64MB/s]
-  8%|7         | 3.30M/41.5M [00:01&lt;00:08, 4.60MB/s]
- 12%|#1        | 4.77M/41.5M [00:01&lt;00:06, 5.91MB/s]
- 15%|#5        | 6.24M/41.5M [00:01&lt;00:05, 6.81MB/s]
- 19%|#8        | 7.71M/41.5M [00:02&lt;00:04, 7.43MB/s]
- 22%|##2       | 9.19M/41.5M [00:02&lt;00:04, 7.87MB/s]
- 26%|##5       | 10.6M/41.5M [00:02&lt;00:03, 8.16MB/s]
- 29%|##9       | 12.1M/41.5M [00:02&lt;00:03, 8.38MB/s]
- 33%|###2      | 13.6M/41.5M [00:02&lt;00:03, 8.52MB/s]
- 36%|###6      | 15.1M/41.5M [00:02&lt;00:03, 8.62MB/s]
- 40%|###9      | 16.5M/41.5M [00:03&lt;00:03, 8.69MB/s]
- 43%|####3     | 18.0M/41.5M [00:03&lt;00:02, 8.75MB/s]
- 47%|####6     | 19.5M/41.5M [00:03&lt;00:02, 8.78MB/s]
- 50%|#####     | 20.9M/41.5M [00:03&lt;00:02, 8.80MB/s]
- 54%|#####4    | 22.4M/41.5M [00:03&lt;00:02, 8.81MB/s]
- 58%|#####7    | 23.9M/41.5M [00:04&lt;00:02, 8.81MB/s]
- 61%|######1   | 25.3M/41.5M [00:04&lt;00:01, 8.82MB/s]
- 65%|######4   | 26.8M/41.5M [00:04&lt;00:01, 8.83MB/s]
- 68%|######8   | 28.3M/41.5M [00:04&lt;00:01, 8.83MB/s]
- 70%|#######   | 29.1M/41.5M [00:04&lt;00:01, 7.46MB/s]
- 74%|#######3  | 30.6M/41.5M [00:04&lt;00:01, 7.80MB/s]
- 77%|#######6  | 31.8M/41.5M [00:05&lt;00:01, 7.57MB/s]
- 79%|#######8  | 32.8M/41.5M [00:05&lt;00:01, 7.16MB/s]
- 82%|########2 | 34.2M/41.5M [00:05&lt;00:00, 7.67MB/s]
- 86%|########6 | 35.7M/41.5M [00:05&lt;00:00, 8.02MB/s]
- 90%|########9 | 37.2M/41.5M [00:05&lt;00:00, 8.28MB/s]
- 93%|#########3| 38.6M/41.5M [00:05&lt;00:00, 8.45MB/s]
- 97%|#########6| 40.1M/41.5M [00:06&lt;00:00, 8.57MB/s]
-100%|##########| 41.5M/41.5M [00:06&lt;00:00, 7.08MB/s]
+  0%|          | 16.0k/41.5M [00:00&lt;07:24, 97.8kB/s]
+  0%|          | 40.0k/41.5M [00:00&lt;05:44, 126kB/s]
+  0%|          | 96.0k/41.5M [00:00&lt;03:13, 224kB/s]
+  0%|          | 160k/41.5M [00:00&lt;02:29, 289kB/s]
+  1%|          | 328k/41.5M [00:00&lt;01:17, 554kB/s]
+  1%|1         | 544k/41.5M [00:01&lt;00:52, 813kB/s]
+  3%|2         | 1.07M/41.5M [00:01&lt;00:25, 1.65MB/s]
+  5%|5         | 2.15M/41.5M [00:01&lt;00:12, 3.26MB/s]
+  9%|8         | 3.62M/41.5M [00:01&lt;00:07, 5.10MB/s]
+ 11%|#1        | 4.67M/41.5M [00:01&lt;00:06, 5.55MB/s]
+ 14%|#4        | 5.81M/41.5M [00:01&lt;00:06, 5.97MB/s]
+ 18%|#7        | 7.29M/41.5M [00:02&lt;00:05, 6.94MB/s]
+ 20%|#9        | 8.30M/41.5M [00:02&lt;00:05, 6.81MB/s]
+ 23%|##2       | 9.34M/41.5M [00:02&lt;00:05, 6.71MB/s]
+ 26%|##6       | 10.8M/41.5M [00:02&lt;00:04, 7.46MB/s]
+ 29%|##9       | 12.2M/41.5M [00:02&lt;00:03, 7.73MB/s]
+ 33%|###2      | 13.6M/41.5M [00:02&lt;00:03, 8.18MB/s]
+ 36%|###6      | 15.1M/41.5M [00:03&lt;00:03, 8.47MB/s]
+ 40%|###9      | 16.6M/41.5M [00:03&lt;00:03, 8.69MB/s]
+ 43%|####3     | 18.0M/41.5M [00:03&lt;00:02, 8.83MB/s]
+ 47%|####7     | 19.5M/41.5M [00:03&lt;00:02, 8.92MB/s]
+ 51%|#####     | 21.0M/41.5M [00:03&lt;00:02, 9.01MB/s]
+ 54%|#####4    | 22.5M/41.5M [00:03&lt;00:02, 9.05MB/s]
+ 58%|#####7    | 23.9M/41.5M [00:03&lt;00:01, 9.80MB/s]
+ 61%|######1   | 25.4M/41.5M [00:04&lt;00:01, 9.59MB/s]
+ 65%|######4   | 26.9M/41.5M [00:04&lt;00:01, 9.46MB/s]
+ 68%|######8   | 28.3M/41.5M [00:04&lt;00:01, 8.72MB/s]
+ 72%|#######1  | 29.8M/41.5M [00:04&lt;00:01, 8.85MB/s]
+ 75%|#######5  | 31.3M/41.5M [00:04&lt;00:01, 8.95MB/s]
+ 79%|#######8  | 32.8M/41.5M [00:05&lt;00:01, 9.01MB/s]
+ 82%|########2 | 34.2M/41.5M [00:05&lt;00:00, 10.3MB/s]
+ 86%|########6 | 35.7M/41.5M [00:05&lt;00:00, 11.3MB/s]
+ 89%|########8 | 36.8M/41.5M [00:05&lt;00:00, 10.4MB/s]
+ 91%|#########1| 37.9M/41.5M [00:05&lt;00:00, 9.10MB/s]
+ 94%|#########3| 38.8M/41.5M [00:05&lt;00:00, 8.11MB/s]
+ 97%|#########6| 40.1M/41.5M [00:05&lt;00:00, 8.17MB/s]
+100%|##########| 41.5M/41.5M [00:05&lt;00:00, 7.37MB/s]
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 01dfc9673..6a6c22da7 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -488,7 +488,7 @@ A quick solution is</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name:  282: &#39;tiger cat&#39;,
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  11.597 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  6.624 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 36174050d..758b2ca76 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,12 +409,8 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/resnet18-f37072fd.pth&quot; to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
 
   0%|          | 0.00/44.7M [00:00&lt;?, ?B/s]
-  2%|2         | 1.01M/44.7M [00:00&lt;00:04, 10.5MB/s]
-  6%|6         | 2.85M/44.7M [00:00&lt;00:02, 15.7MB/s]
- 14%|#4        | 6.44M/44.7M [00:00&lt;00:01, 25.6MB/s]
- 30%|##9       | 13.4M/44.7M [00:00&lt;00:00, 43.9MB/s]
- 61%|######    | 27.1M/44.7M [00:00&lt;00:00, 79.9MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 79.6MB/s]
+ 50%|#####     | 22.4M/44.7M [00:00&lt;00:00, 235MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 257MB/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 bf7ec0e2f..b541d9fe8 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  2.552 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.361 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 0165c0fe0..e0fdf4f45 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:25.945</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:19.526</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -331,43 +331,43 @@
 </colgroup>
 <tbody>
 <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>01:11.597</p></td>
+<td><p>01:06.624</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:02.552</p></td>
+<td><p>01:01.361</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <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>00:57.354</p></td>
+<td><p>00:56.265</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>00:31.464</p></td>
+<td><p>00:31.384</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>00:23.683</p></td>
+<td><p>00:24.067</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:22.535</p></td>
+<td><p>00:22.462</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.733</p></td>
+<td><p>00:21.872</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>00:18.871</p></td>
+<td><p>00:19.171</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>00:13.816</p></td>
+<td><p>00:14.063</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>00:02.340</p></td>
+<td><p>00:02.258</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 11d87aa83..a74c64215 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  15.9836      15.9385      16.3336      15.8066       0.1478
+  16.0196      15.9892      16.3060      15.8382       0.1700
 </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 aa70f7db7..5b8348511 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,18 +431,19 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
-  5%|5         | 9.20M/170M [00:00&lt;00:01, 95.7MB/s]
- 15%|#4        | 25.0M/170M [00:00&lt;00:01, 137MB/s]
- 24%|##3       | 40.2M/170M [00:00&lt;00:00, 147MB/s]
- 33%|###3      | 56.1M/170M [00:00&lt;00:00, 154MB/s]
- 42%|####2     | 71.6M/170M [00:00&lt;00:00, 157MB/s]
- 51%|#####1    | 87.2M/170M [00:00&lt;00:00, 159MB/s]
- 61%|######    | 103M/170M [00:00&lt;00:00, 161MB/s]
- 70%|######9   | 119M/170M [00:00&lt;00:00, 162MB/s]
- 79%|#######9  | 134M/170M [00:00&lt;00:00, 162MB/s]
- 88%|########8 | 150M/170M [00:01&lt;00:00, 162MB/s]
- 97%|#########7| 165M/170M [00:01&lt;00:00, 162MB/s]
-100%|##########| 170M/170M [00:01&lt;00:00, 157MB/s]
+  1%|          | 1.27M/170M [00:00&lt;00:13, 13.2MB/s]
+  2%|2         | 3.89M/170M [00:00&lt;00:08, 21.6MB/s]
+  5%|5         | 9.31M/170M [00:00&lt;00:04, 37.5MB/s]
+ 12%|#1        | 20.1M/170M [00:00&lt;00:02, 67.1MB/s]
+ 25%|##4       | 41.7M/170M [00:00&lt;00:01, 124MB/s]
+ 35%|###5      | 60.1M/170M [00:00&lt;00:00, 148MB/s]
+ 45%|####5     | 76.7M/170M [00:00&lt;00:00, 156MB/s]
+ 55%|#####5    | 93.5M/170M [00:00&lt;00:00, 162MB/s]
+ 65%|######5   | 110M/170M [00:00&lt;00:00, 167MB/s]
+ 74%|#######4  | 126M/170M [00:01&lt;00:00, 159MB/s]
+ 85%|########4 | 144M/170M [00:01&lt;00:00, 165MB/s]
+ 95%|#########4| 161M/170M [00:01&lt;00:00, 171MB/s]
+100%|##########| 170M/170M [00:01&lt;00:00, 139MB/s]
 /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=&#39;floor&#39;).
@@ -537,7 +538,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  53.164 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  57.970 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 e78486125..89b6ec778 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -472,10 +472,9 @@ training. Other models require a full post training calibration.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/mobilenet_v2-b0353104.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
 
   0%|          | 0.00/13.6M [00:00&lt;?, ?B/s]
- 16%|#5        | 2.11M/13.6M [00:00&lt;00:00, 22.1MB/s]
- 45%|####5     | 6.11M/13.6M [00:00&lt;00:00, 33.7MB/s]
- 93%|#########2| 12.6M/13.6M [00:00&lt;00:00, 48.4MB/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 44.2MB/s]
+ 23%|##2       | 3.08M/13.6M [00:00&lt;00:00, 32.3MB/s]
+ 76%|#######5  | 10.2M/13.6M [00:00&lt;00:00, 57.3MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 61.7MB/s]
 </pre></div>
 </div>
 </div>
@@ -564,7 +563,7 @@ 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)
-  90.3444      90.2612      95.2618      90.0319       0.5189
+  90.2972      90.2349      94.0197      90.0798       0.3918
 </pre></div>
 </div>
 <div class="admonition note">
@@ -603,7 +602,7 @@ 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  6.586 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  7.407 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 0ad0f9164..2d1bdeb06 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -565,7 +565,7 @@ 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)
-  119.5962     119.6527     120.6479     118.7289      0.3636
+  119.4027     119.3606     120.5569     118.5830      0.3793
 </pre></div>
 </div>
 <div class="admonition note">
@@ -593,7 +593,7 @@ network for ARM CPU</span></a>.</p></li>
 </ul>
 </div></blockquote>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  54.499 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  57.914 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 01111a4db..470a6d3ee 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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  12.805 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  12.133 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 2c755df61..116da7680 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,26 +436,25 @@ 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]
-  1%|          | 1251/132723 [00:00&lt;00:10, 12412.74KB/s]
-  3%|2         | 3518/132723 [00:00&lt;00:07, 18426.23KB/s]
-  5%|5         | 7123/132723 [00:00&lt;00:04, 26458.20KB/s]
- 10%|9         | 13027/132723 [00:00&lt;00:03, 39306.18KB/s]
- 16%|#5        | 20621/132723 [00:00&lt;00:02, 52505.71KB/s]
- 21%|##1       | 28109/132723 [00:00&lt;00:01, 60107.13KB/s]
- 27%|##7       | 35946/132723 [00:00&lt;00:01, 66072.87KB/s]
- 33%|###2      | 43687/132723 [00:00&lt;00:01, 69678.85KB/s]
- 39%|###8      | 51366/132723 [00:00&lt;00:01, 71898.57KB/s]
- 44%|####4     | 58861/132723 [00:01&lt;00:01, 72834.95KB/s]
- 50%|#####     | 66741/132723 [00:01&lt;00:00, 74657.22KB/s]
- 56%|#####6    | 74654/132723 [00:01&lt;00:00, 76016.61KB/s]
- 62%|######2   | 82562/132723 [00:01&lt;00:00, 76941.09KB/s]
- 68%|######8   | 90353/132723 [00:01&lt;00:00, 77232.01KB/s]
- 74%|#######4  | 98234/132723 [00:01&lt;00:00, 77705.25KB/s]
- 80%|#######9  | 106005/132723 [00:01&lt;00:00, 77667.46KB/s]
- 86%|########5 | 113772/132723 [00:01&lt;00:00, 74644.80KB/s]
- 91%|#########1| 121262/132723 [00:01&lt;00:00, 72544.29KB/s]
- 97%|#########6| 128543/132723 [00:01&lt;00:00, 71327.24KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 66564.69KB/s]
+  1%|          | 1317/132723 [00:00&lt;00:10, 13116.26KB/s]
+  3%|2         | 3557/132723 [00:00&lt;00:06, 18515.81KB/s]
+  5%|5         | 7189/132723 [00:00&lt;00:04, 26601.54KB/s]
+ 10%|9         | 12964/132723 [00:00&lt;00:03, 38872.76KB/s]
+ 16%|#5        | 20807/132723 [00:00&lt;00:02, 53117.25KB/s]
+ 22%|##1       | 28824/132723 [00:00&lt;00:01, 62304.76KB/s]
+ 28%|##7       | 36853/132723 [00:00&lt;00:01, 68177.16KB/s]
+ 34%|###3      | 44861/132723 [00:00&lt;00:01, 71961.08KB/s]
+ 40%|###9      | 52805/132723 [00:00&lt;00:01, 74296.92KB/s]
+ 46%|####5     | 60681/132723 [00:01&lt;00:00, 75670.98KB/s]
+ 52%|#####1    | 68749/132723 [00:01&lt;00:00, 77200.72KB/s]
+ 58%|#####7    | 76873/132723 [00:01&lt;00:00, 78427.27KB/s]
+ 64%|######3   | 84821/132723 [00:01&lt;00:00, 78743.09KB/s]
+ 70%|#######   | 92952/132723 [00:01&lt;00:00, 79515.89KB/s]
+ 76%|#######6  | 101064/132723 [00:01&lt;00:00, 79996.69KB/s]
+ 82%|########2 | 109210/132723 [00:01&lt;00:00, 80434.41KB/s]
+ 88%|########8 | 117294/132723 [00:01&lt;00:00, 80553.84KB/s]
+ 94%|#########4| 125350/132723 [00:01&lt;00:00, 80437.47KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 70011.97KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -498,7 +497,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  17.729 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  19.327 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 847ecf5ac..fd866acf3 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>10:15.034</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:26.155</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -331,31 +331,31 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:53.164</p></td>
+<td><p>02:57.970</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:17.729</p></td>
+<td><p>02:19.327</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:54.499</p></td>
+<td><p>01:57.914</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>01:12.805</p></td>
+<td><p>01:12.133</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>01:06.586</p></td>
+<td><p>01:07.407</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>00:28.650</p></td>
+<td><p>00:28.773</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.596</p></td>
+<td><p>00:22.626</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index f1828d07b..5f4fb1bd0 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -604,7 +604,7 @@ 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.zipaa8d58dc-c9be-4f91-ac44-3d1ca28e8e3b 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.zip433d11bd-8c9e-40ed-9719-fb14562eb917 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>
@@ -668,7 +668,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-  Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+  Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
 </pre></div>
 </div>
 <p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 27ec2c8d9..d11339bab 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>00:39.446</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.456</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -331,19 +331,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:36.378</p></td>
+<td><p>00:36.275</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>00:02.183</p></td>
+<td><p>00:02.219</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.879</p></td>
+<td><p>00:00.953</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.009</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 6a9f040fc..4b00544f0 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ 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: 6470us [6470us] (45.84%; 45.84%)
-FoldScaleAxis: 7645us [5us] (54.16%; 54.16%)
-        FoldConstant: 7640us [1561us] (54.13%; 99.93%)
-                InferType: 6079us [6079us] (43.07%; 79.57%)
+InferType: 6753us [6753us] (45.59%; 45.59%)
+FoldScaleAxis: 8059us [6us] (54.41%; 54.41%)
+        FoldConstant: 8053us [1640us] (54.37%; 99.92%)
+                InferType: 6414us [6414us] (43.30%; 79.64%)
 </pre></div>
 </div>
 </div>
@@ -532,10 +532,10 @@ 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: 6126us [6126us] (44.41%; 44.41%)
-FoldScaleAxis: 7667us [5us] (55.59%; 55.59%)
-        FoldConstant: 7662us [1569us] (55.55%; 99.94%)
-                InferType: 6093us [6093us] (44.18%; 79.53%)
+InferType: 6693us [6693us] (44.45%; 44.45%)
+FoldScaleAxis: 8363us [6us] (55.55%; 55.55%)
+        FoldConstant: 8358us [1784us] (55.51%; 99.93%)
+                InferType: 6573us [6573us] (43.66%; 78.65%)
 </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 49a5e3a82..26ac99447 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -556,7 +556,7 @@ latency of convolution.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Convolution: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.178198 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.337717 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 123607d6d..1b63cff34 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -898,7 +898,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.464348 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.985035 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 1b898993e..3a32f522c 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -453,8 +453,8 @@ 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: 0.018597
-Baseline: 3.291772
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018953
+Baseline: 3.409586
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -514,7 +514,7 @@ 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: 0.296020
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.310919
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -581,7 +581,7 @@ 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: 0.334483
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.346889
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -642,7 +642,7 @@ 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: 0.119389
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.119664
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -725,7 +725,7 @@ 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: 0.111189
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110782
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -811,7 +811,7 @@ 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: 0.111423
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111538
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -901,7 +901,7 @@ 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: 0.145232
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145749
 </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 8276ad481..a5cdb654a 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.032</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.876</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -331,15 +331,15 @@
 </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>00:31.806</p></td>
+<td><p>00:32.593</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>00:01.223</p></td>
+<td><p>00:01.254</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>00:01.003</p></td>
+<td><p>00:01.029</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 6074290d5..4a435105e 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>05:20.725</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:21.998</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -331,27 +331,27 @@
 </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>02:34.273</p></td>
+<td><p>02:42.797</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>01:19.989</p></td>
+<td><p>01:20.758</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:42.637</p></td>
+<td><p>00:43.450</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>00:26.921</p></td>
+<td><p>00:17.861</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.458</p></td>
+<td><p>00:08.669</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.448</p></td>
+<td><p>00:08.463</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 58b2b8ee7..3f9c08700 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
@@ -486,428 +486,107 @@ cooperative fetching, unrolling and operator fusion.</p>
              compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
   buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
   preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
-  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 224;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 16;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
   allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope=&quot;local&quot;, align=4)[0] = 0f32
+  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112 {
+    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
     conv2d_nchw_1[1] = 0f32
     conv2d_nchw_1[2] = 0f32
     conv2d_nchw_1[3] = 0f32
     conv2d_nchw_1[4] = 0f32
     conv2d_nchw_1[5] = 0f32
     conv2d_nchw_1[6] = 0f32
-    for (rc.outer.outer: int32, 0, 128) {
-      let cse_var_1: int32 = (rc.outer.outer*36)
+    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, 256) {
+      let cse_var_1: int32 = (rc.outer.outer*18)
        {
-        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16 {
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope=&quot;shared&quot;)[(threadIdx.x_1*24)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*6), 9))) &amp;&amp; (floormod((threadIdx.x_1*6), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49 [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 1), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49)) + (floordiv(floormod((threadIdx.x_1*8), 9), 3)*7)) [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod((threadIdx.x_1*8), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 2), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*8), 9)*49)) + (floordiv(floormod((threadIdx.x_1*8), 9), 3)*7)) [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 3), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 4), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 4), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 1), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 5), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 5), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 1), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 6), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 6), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 7), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 7), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 2), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 8), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 8), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 2), 9)*49)) + (floordiv(floormod(((threadIdx [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*6), 9))) &amp;&amp; (floormod((threadIdx.x_1*6), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(( [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 1), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7))  [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 5), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 2), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 3), 9)*49)) + (floormod(blockIdx.x, 7)*7))  [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 3), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 4), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 4), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 4), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 5), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 5), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 4), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 6), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 6), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 7), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 7), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 5), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 8), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 8), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 5), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*6), 9))) &amp;&amp; (floormod((threadIdx.x_1*6), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod( [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 1), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7))  [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 &lt;= (floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3))) &amp;&amp; ((floormod(blockIdx.x, 7) + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 3)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 2), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 6), 9)*49)) + (floormod(blockIdx.x, 7)*7))  [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 3), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 4), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 4), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadId [...]
-          }
-          if @tir.likely((threadIdx.x_1 &lt; 4), dtype=bool) {
-            pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((1 &lt;= (floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7))) &amp;&amp; ((floordiv(floormod(((threadIdx.x_1*8) + 7), 9), 3) + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*6) + 5), 9))) &amp;&amp; (floormod(((threadIdx.x_1*6) + 5), 9) &lt; 8)), data[((((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*8) + 7), 9)*49)) + (floordiv(floormod(((threadId [...]
+        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+        if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
+          pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope=&quot;shared&quot;)[(threadIdx.x_1*9)] = 0f32
+          pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 &lt;= floormod(threadIdx.x_1, 9)) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
+          pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
+        }
+        attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+        kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+        kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 18), 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; = 112;
+        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+        kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 168), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 6)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 112;
+        kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 18), 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; = 112;
+        if @tir.likely((threadIdx.x_2 &lt; 16), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 280), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+        }
+        for (rc.outer.inner: int32, 0, 2) {
+          for (rx.outer.inner: int32, 0, 3) {
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 18)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 21)]))
+            conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
+            conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
+            conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*36) + (rc.outer.inner*9)) + rx.outer.inner) + 24)]))
           }
         }
-        attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + threadIdx.x_2)]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 16), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 8), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 12), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 16), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 20), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 24), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 32), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 18432)]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 40), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 44), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 48), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 52), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 60), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 64), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 68), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 36864)]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 76), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 304), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 80), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 320), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 88), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 352), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 92), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 368), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 96), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 100), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 400), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 104), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 416), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 55296)]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 116), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 464), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 120), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 124), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 496), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 128), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 512), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 132), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
-        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 136), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 544), 36), 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; = 16;
-        kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*36)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 1)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 2)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 3)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 4)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 5)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 6)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 7)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 8)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 9)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 10)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 11)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 12)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 13)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 14)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 15)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 16)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 17)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 18)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 19)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 20)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 21)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 22)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 23)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 24)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 25)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 26)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 27)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 28)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 29)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 30)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 31)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 32)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 33)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 34)]))
-        conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 35)]))
-        conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 35)]))
       }
     }
-    compute[(((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
-    compute[((((floordiv(blockIdx.x, 7)*784) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*16) + threadIdx.x)]), 0f32)
+    for (i1.inner: int32, 0, 2) {
+      for (i3.inner: int32, 0, 7) {
+        compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+      }
+    }
   }
 }
 </pre></div>
@@ -943,7 +622,7 @@ 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: 0.403 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.268 ms
 </pre></div>
 </div>
 </div>
@@ -972,37 +651,37 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
 conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
 conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
 conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
 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_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
 conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
 conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=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=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+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=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=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=16)
 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=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_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
 s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
 s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
 kernel_shared = s.cache_read(kernel, &quot;shared&quot;, [conv2d_nchw])
@@ -1021,14 +700,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
 kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
+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=112)
 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=24)
+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=9)
 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=16)
+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=112)
 s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 64)
 s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;unroll_explicit&quot;, True)
 
 CUDA source code:
@@ -1046,9 +725,9 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[7];
-  __shared__ float pad_temp_shared[108];
+extern &quot;C&quot; __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+  float conv2d_nchw[14];
+  __shared__ float pad_temp_shared[162];
   __shared__ float kernel_shared[576];
   conv2d_nchw[0] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
@@ -1057,377 +736,87 @@ extern &quot;C&quot; __global__ void __launch_bounds__(16) default_function_kern
   conv2d_nchw[4] = 0.000000e+00f;
   conv2d_nchw[5] = 0.000000e+00f;
   conv2d_nchw[6] = 0.000000e+00f;
-  for (int rc_outer_outer = 0; rc_outer_outer &lt; 128; ++rc_outer_outer) {
+  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; 256; ++rc_outer_outer) {
     __syncthreads();
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((1 &lt;= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &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) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)thread [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((1 &lt;= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7) [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((1 &lt;= ((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; (((((((int)threadIdx.x) * 8) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 8) / 9) * 49)) + ((((((int)threadIdx.x) * 8) % 9) / 3) * 7)) + ((((int)blockIdx.x) % 7) * 7) [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 4) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 1) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 5) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 5) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 1) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 6) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 6) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 7) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 7) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 2) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 8) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 8) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 2) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 9) / 3) * 7)) + ((((i [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) &lt; 8)) &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) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) +  [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) [...]
-    }
-    if (((int)threadIdx.x) &lt; 5) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 1) % 3)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 3) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + (((( [...]
+    if (((int)threadIdx.x) &lt; 18) {
+      pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 &lt;= (((int)threadIdx.x) % 9)) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
+      pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
     }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 4) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + (((( [...]
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+    kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 4) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 8) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) / 3) + 4) % 6) * 3)) + (((int)threadIdx.x) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 16) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    if (((int)threadIdx.x) &lt; 16) {
+      kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
     }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 4) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 5) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 5) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 4) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 9) / 3) * 7)) + (((( [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 6) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 6) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + (((( [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 7) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 7) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + (((( [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 5) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 8) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 8) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 5) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 9) / 3) * 7)) + (((( [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) &lt; 8)) &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) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) * 8) / 3) + [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 &lt;= ((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3))) &amp;&amp; (((((int)blockIdx.x) % 7) + ((((((int)threadIdx.x) * 8) / 3) + 2) % 3)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 6) / 9) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((((int)threadIdx.x) [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + (((( [...]
-    }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 4) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + (((( [...]
+    __syncthreads();
+    for (int rc_outer_inner = 0; rc_outer_inner &lt; 2; ++rc_outer_inner) {
+      for (int rx_outer_inner = 0; rx_outer_inner &lt; 3; ++rx_outer_inner) {
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 18)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 21)]));
+        conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
+        conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+        conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 36) + (rc_outer_inner * 9)) + rx_outer_inner) + 24)]));
+      }
     }
-    if (((int)threadIdx.x) &lt; 4) {
-      pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((1 &lt;= (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7))) &amp;&amp; ((((((((int)threadIdx.x) * 8) + 7) % 9) / 3) + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 6) + 5) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 6) + 5) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 8) + 7) / 9) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 9) / 3) * 7)) + (((( [...]
+  }
+  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) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
     }
-    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
-    kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
-    kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
-    kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
-    kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 528)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-    kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-    __syncthreads();
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 36)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
-    conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
-    conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
   }
-  compute[((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
-  compute[(((((((int)blockIdx.x) / 7) * 784) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 16) + ((int)threadIdx.x))]), 0.000000e+00f);
 }
 </pre></div>
 </div>
@@ -1463,7 +852,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  34.273 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  42.797 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 ff1601bb0..d4b29b574 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   9.9472       9.9498      10.0102       9.8816       0.0525
+  10.0204      10.0450      10.0482       9.9681       0.0370
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 84e461c30..186da46a6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  760.8491     760.8105     761.0520     760.6849      0.1524
+  759.7623     759.6817     760.1304     759.4748      0.2737
 </pre></div>
 </div>
 </div>
@@ -942,7 +942,7 @@ 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  19.989 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  20.758 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 e7545f9a7..6d9e82a1d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,121 +620,31 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-  preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
-  for (i0.outer: int32, 0, 8) &quot;parallel&quot; {
-    allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global;
-    for (i1.outer: int32, 0, 64) {
-      for (i.outer.inner: int32, 0, 8) {
-        let cse_var_2: int32 = floordiv(i1.outer, 2)
-        let cse_var_1: int32 = (i.outer.inner*32)
-         {
-          compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
-          compute_5[(cse_var_1 + 1)] = 0f32
-          compute_5[(cse_var_1 + 2)] = 0f32
-          compute_5[(cse_var_1 + 3)] = 0f32
-          compute_5[(cse_var_1 + 4)] = 0f32
-          compute_5[(cse_var_1 + 5)] = 0f32
-          compute_5[(cse_var_1 + 6)] = 0f32
-          compute_5[(cse_var_1 + 7)] = 0f32
-          compute_5[(cse_var_1 + 8)] = 0f32
-          compute_5[(cse_var_1 + 9)] = 0f32
-          compute_5[(cse_var_1 + 10)] = 0f32
-          compute_5[(cse_var_1 + 11)] = 0f32
-          compute_5[(cse_var_1 + 12)] = 0f32
-          compute_5[(cse_var_1 + 13)] = 0f32
-          compute_5[(cse_var_1 + 14)] = 0f32
-          compute_5[(cse_var_1 + 15)] = 0f32
-          compute_5[(cse_var_1 + 16)] = 0f32
-          compute_5[(cse_var_1 + 17)] = 0f32
-          compute_5[(cse_var_1 + 18)] = 0f32
-          compute_5[(cse_var_1 + 19)] = 0f32
-          compute_5[(cse_var_1 + 20)] = 0f32
-          compute_5[(cse_var_1 + 21)] = 0f32
-          compute_5[(cse_var_1 + 22)] = 0f32
-          compute_5[(cse_var_1 + 23)] = 0f32
-          compute_5[(cse_var_1 + 24)] = 0f32
-          compute_5[(cse_var_1 + 25)] = 0f32
-          compute_5[(cse_var_1 + 26)] = 0f32
-          compute_5[(cse_var_1 + 27)] = 0f32
-          compute_5[(cse_var_1 + 28)] = 0f32
-          compute_5[(cse_var_1 + 29)] = 0f32
-          compute_5[(cse_var_1 + 30)] = 0f32
-          compute_5[(cse_var_1 + 31)] = 0f32
-          for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
-            let cse_var_35: int32 = (elem_idx*16)
-            let cse_var_34: int32 = (cse_var_1 + 9)
-            let cse_var_33: int32 = (cse_var_1 + 8)
-            let cse_var_32: int32 = (cse_var_1 + 7)
-            let cse_var_31: int32 = (cse_var_1 + 6)
-            let cse_var_30: int32 = (cse_var_1 + 5)
-            let cse_var_29: int32 = (cse_var_1 + 4)
-            let cse_var_28: int32 = (cse_var_1 + 31)
-            let cse_var_27: int32 = (cse_var_1 + 30)
-            let cse_var_26: int32 = (cse_var_1 + 3)
-            let cse_var_25: int32 = (cse_var_1 + 29)
-            let cse_var_24: int32 = (cse_var_1 + 28)
-            let cse_var_23: int32 = (cse_var_1 + 27)
-            let cse_var_22: int32 = (cse_var_1 + 26)
-            let cse_var_21: int32 = (cse_var_1 + 25)
-            let cse_var_20: int32 = (cse_var_1 + 24)
-            let cse_var_19: int32 = (cse_var_1 + 23)
-            let cse_var_18: int32 = (cse_var_1 + 22)
-            let cse_var_17: int32 = (cse_var_1 + 21)
-            let cse_var_16: int32 = (cse_var_1 + 20)
-            let cse_var_15: int32 = (cse_var_1 + 2)
-            let cse_var_14: int32 = (cse_var_1 + 19)
-            let cse_var_13: int32 = (cse_var_1 + 18)
-            let cse_var_12: int32 = (cse_var_1 + 17)
-            let cse_var_11: int32 = (cse_var_1 + 16)
-            let cse_var_10: int32 = (cse_var_1 + 15)
-            let cse_var_9: int32 = (cse_var_1 + 14)
-            let cse_var_8: int32 = (cse_var_1 + 13)
-            let cse_var_7: int32 = (cse_var_1 + 12)
-            let cse_var_6: int32 = (cse_var_1 + 11)
-            let cse_var_5: int32 = (cse_var_1 + 10)
-            let cse_var_4: int32 = (cse_var_1 + 1)
-            let cse_var_3: int32 = ((i0.outer*4096) + (i.outer.inner*512))
-             {
-              compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
-              compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
-              compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+  preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+  for (i0.outer.i1.outer.fused: int32, 0, 32) &quot;parallel&quot; {
+    allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+      for (i.outer.inner: int32, 0, 2) {
+        for (i.inner.init: int32, 0, 64) {
+          for (j.init: int32, 0, 16) {
+            compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*1024) + (i.inner.init*16)) + j.init)] = 0f32
+          }
+        }
+        for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+          if @tir.likely((elem_idx &lt; (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+            for (i.inner: int32, 0, 64) {
+              for (j: int32, 0, 16) {
+                let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner*16)) + j)
+                compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+              }
             }
           }
         }
       }
-      for (i0.inner: int32, 0, 16) {
-        let cse_var_37: int32 = (i1.outer*8)
-        let cse_var_36: int32 = (((i0.outer*8192) + (i0.inner*512)) + cse_var_37)
-        compute[ramp(cse_var_36, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_37) - (floordiv(i1.outer, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_36, 1, 8)]), broadcast(0f32, 8))
+      for (i0.inner: int32, 0, 128) {
+        for (i1.inner: int32, 0, 16) {
+          let cse_var_2: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
+          compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
+        }
       }
     }
   }
@@ -772,7 +682,7 @@ 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: 6.967 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.780 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 79084da23..402ed66e4 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>00:43.275</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.226</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -331,7 +331,7 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.246</p></td>
+<td><p>00:43.197</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index e330fdcae..fd4f5723b 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1164,8 +1164,8 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 32]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2885496
-No: 6   GFLOPS: 110.58/110.58   result: MeasureResult(costs=(0.0020934496458333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8007960319519043, timestamp=1656104860.0191834)      [(&#39;tile_f&#39;, [-1, 1, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 4]), (&#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,3754080
-No: 7   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 6   GFLOPS: 42.41/42.41     result: MeasureResult(costs=(0.005458147105263158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6413054466247559, timestamp=1656107178.9823925)       [(&#39;tile_f&#39;, [-1, 1, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 4, 4]), (&#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,3754080
+No: 7   GFLOPS: 0.00/42.41      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
@@ -1288,7 +1288,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 16, 32]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 256, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6225319
-No: 8   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 8   GFLOPS: 0.00/42.41      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
@@ -1411,7 +1411,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 1, 32]), (&#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,943546
-No: 9   GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 9   GFLOPS: 0.00/42.41      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
@@ -1534,7 +1534,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 16, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#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,2868708
-No: 10  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 10  GFLOPS: 0.00/42.41      result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 142, in build
     res = future.result()
   File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 435, in result
@@ -1552,7 +1552,7 @@ No: 10  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 32, 2, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4691833
-No: 11  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 11  GFLOPS: 0.00/42.41      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
@@ -1675,7 +1675,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 2, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,1042124
-No: 12  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 12  GFLOPS: 0.00/42.41      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
@@ -1798,7 +1798,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 32, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 32, 16]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10013405
-No: 13  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 13  GFLOPS: 0.00/42.41      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
@@ -1921,7 +1921,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 8, 8, 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, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6732082
-No: 14  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 14  GFLOPS: 0.00/42.41      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
@@ -2044,7 +2044,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 4, 32]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 1)],None,7536735
-No: 15  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 15  GFLOPS: 0.00/42.41      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
@@ -2167,7 +2167,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 128, 4]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,482121
-No: 16  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 16  GFLOPS: 0.00/42.41      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
@@ -2290,7 +2290,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 2, 1, 16]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 32, 8]), (&#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,2824525
-No: 17  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 17  GFLOPS: 0.00/42.41      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
@@ -2413,7 +2413,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 8, 8]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4559286
-No: 18  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 18  GFLOPS: 0.00/42.41      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
@@ -2536,7 +2536,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 1, 32, 16]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 512]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9677544
-No: 19  GFLOPS: 0.00/110.58     result: Traceback (most recent call last):
+No: 19  GFLOPS: 0.00/42.41      result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 738, in __call__
     yield remote, remote.load_module(os.path.split(build_result.filename)[1])
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 702, in run_through_rpc
@@ -2624,7 +2624,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
   15: _PyEval_EvalFrameDefault
   14: 0x0000000000537c30
   13: _PyObject_FastCallKeywords
-  12: 0x00007f2968c30fa2
+  12: 0x00007f0334240fa2
   11: _ctypes_callproc
   10: ffi_call
   9: ffi_call_unix64
@@ -2689,7 +2689,7 @@ Traceback (most recent call last):
   21: _PyFunction_FastCallKeywords
   20: _PyEval_EvalFrameDefault
   19: _PyFunction_FastCall      [(&#39;tile_f&#39;, [-1, 8, 2, 16]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6390073
-No: 20  GFLOPS: 144.00/144.00   result: MeasureResult(costs=(0.0016076431500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.440328598022461, timestamp=1656104886.5177128)       [(&#39;tile_f&#39;, [-1, 1, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9881539
+No: 20  GFLOPS: 142.80/142.80   result: MeasureResult(costs=(0.0016211996300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.430893898010254, timestamp=1656107205.5226185)       [(&#39;tile_f&#39;, [-1, 1, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9881539
 </pre></div>
 </div>
 <p>Finally we can inspect the best config from log file, check correctness,
@@ -2730,7 +2730,7 @@ and measure running time.</p>
 Best config:
 [(&#39;tile_f&#39;, [-1, 1, 4, 1]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,9881539
 Finish loading 20 records
-Time cost of this operator: 0.001975
+Time cost of this operator: 0.001977
 </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 07e973ad0..8d524f5ae 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
 ########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs
 ---------                                     ---                                           --------  -------  -----              ------  -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  312.3     98.745   (1, 2, 10, 10, 3)  2       1
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.033     0.959    (1, 6, 10, 10)     1       1
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.936     0.296    (1, 1, 10, 10, 3)  1       1
-Total_time                                    -                                             316.269   -        -                  -       -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.3     98.741   (1, 2, 10, 10, 3)  2       1
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.088     0.973    (1, 6, 10, 10)     1       1
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.906     0.286    (1, 1, 10, 10, 3)  1       1
+Total_time                                    -                                             317.294   -        -                  -       -
 </pre></div>
 </div>
 </div>
@@ -634,10 +634,10 @@ Total_time                                    -
 ########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs
 ---------                                     ---                                           --------  -------  -----              ------  -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  144.5     98.142   (1, 6, 10, 10, 1)  2       1
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.816     1.233    (1, 6, 10, 10)     1       1
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.92      0.625    (1, 1, 10, 10, 3)  1       1
-Total_time                                    -                                             147.236   -        -                  -       -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  125.8     97.859   (1, 6, 10, 10, 1)  2       1
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.835     1.427    (1, 6, 10, 10)     1       1
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.917     0.714    (1, 1, 10, 10, 3)  1       1
+Total_time                                    -                                             128.552   -        -                  -       -
 </pre></div>
 </div>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 755510fb4..f865a965a 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ 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/tmpi3jpugbr/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpwu17c7va/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
     <span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">&quot;off&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpi3jpugbr/images/target contains 8144 images
-/tmp/tmpi3jpugbr/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpwu17c7va/images/target contains 8144 images
+/tmp/tmpwu17c7va/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2227 - accuracy: 0.9278 - val_loss: 0.1394 - val_accuracy: 0.9600
+328/328 - 55s - loss: 0.2224 - accuracy: 0.9256 - val_loss: 0.1308 - val_accuracy: 0.9607
 Epoch 2/3
-328/328 - 52s - loss: 0.0950 - accuracy: 0.9635 - val_loss: 0.1180 - val_accuracy: 0.9645
+328/328 - 52s - loss: 0.0942 - accuracy: 0.9650 - val_loss: 0.1156 - val_accuracy: 0.9675
 Epoch 3/3
-328/328 - 52s - loss: 0.0696 - accuracy: 0.9730 - val_loss: 0.1061 - val_accuracy: 0.9683
+328/328 - 52s - loss: 0.0661 - accuracy: 0.9760 - val_loss: 0.1062 - val_accuracy: 0.9683
 
-&lt;keras.callbacks.History object at 0x7f8841913810&gt;
+&lt;keras.callbacks.History object at 0x7f7859f7ecd0&gt;
 </pre></div>
 </div>
 </div>
@@ -951,7 +951,7 @@ 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> ( 8 minutes  18.148 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 8 minutes  22.193 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 502f1627f..8158cbaa2 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>09:04.164</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>09:09.121</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -331,15 +331,15 @@
 </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>08:18.148</p></td>
+<td><p>08:22.193</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.531</p></td>
+<td><p>00:43.357</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.485</p></td>
+<td><p>00:03.571</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index e918dcd31..b76f7260a 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>00:11.540</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.439</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -331,11 +331,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.825</p></td>
+<td><p>00:09.732</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><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>00:01.709</p></td>
+<td><p>00:01.702</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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 fb1c8acc4..f48e36970 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -515,7 +515,7 @@ 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 0x7f87b6efc560&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7f77c5cfdf80&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 3c710a828..0b8d9d824 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.018</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.030</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -331,23 +331,23 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.874</p></td>
+<td><p>00:01.887</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>00:00.952</p></td>
+<td><p>00:00.941</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.521</p></td>
+<td><p>00:00.523</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.503</p></td>
+<td><p>00:00.511</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>00:00.097</p></td>
+<td><p>00:00.098</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 7349d3b60..3fca54227 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -571,7 +571,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C}
   preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmpqfnoel_v/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpqfnoel_v/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/tmpmk9ddkrn/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpmk9ddkrn/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 ff763f14c..3a40468ed 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1737,7 +1737,7 @@ Can be the a function or the function name.</p></li>
 
 <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">
@@ -1774,7 +1774,7 @@ the initial naive schedule (state).</p>
 
 <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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 848223085..8539856b3 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/503f1a65d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 7b903c34f..150838f2d 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/503f1a65d/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 c43bff7bb..58ba9bd2a 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/503f1a65d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 91c72e38a..e90f06696 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/503f1a65d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 267f0316b..5232daf51 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/503f1a65d/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 02c90c18a..e2468c058 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/503f1a65d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 f94094e61..6cc2ca4af 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/503f1a65d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 34f1e235e..23ad26c23 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/503f1a65d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/web/src/runtime.ts#L1134">runtime.ts:1134</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/503f1a65d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 cd14ed0e6..77608c205 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/503f1a65d/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 b420d4840..f68f5df37 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/503f1a65d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 881f4b4bb..4ff884888 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/503f1a65d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 329b50a8e..205469660 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/503f1a65d/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 f49145079..784ca2c45 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/503f1a65d/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 34d38b7aa..e390ee61c 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/503f1a65d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 9aa7bf4a3..955469d92 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/503f1a65d/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 002044dd2..b80ee19a0 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/503f1a65d/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 af0ba9d45..a24c4f66a 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/503f1a65d/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 0e69d575f..ef7dbf1f6 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/503f1a65d/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 61249423e..06245f673 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/503f1a65d/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 435ab89a7..0becbbcc8 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/503f1a65d/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 c7bc6e622..8e73c37a3 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/503f1a65d/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/web/src/runtime.ts#L1356">runtime.ts:1356</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/503f1a65d/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 3412eb7b0..c729dfbe2 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/503f1a65d/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 7a17edc50..819bf3376 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/503f1a65d/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 71ab0e4a0..8c80e21b4 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/503f1a65d/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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/503f1a65d/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/bca278a82/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 b39501595..7ec39a672 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 b8bbf6b94..19da2a96e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.772</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.763</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -331,7 +331,7 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.765</p></td>
+<td><p>00:20.756</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 f7d347ce3..6c7c7941e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   DeprecationWarning,
 /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
   relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.15s!
+resnet18_v1 inference graph built in 22.21s!
 </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 435b7829a..3e0a7ec0d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   &quot;target_host parameter is going to be deprecated. &quot;
 /workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
   DeprecationWarning,
-yolov3-tiny inference graph built in 15.50s!
+yolov3-tiny inference graph built in 15.47s!
 </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 0fd90e169..973590dcc 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>01:29.424</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:28.808</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -331,11 +331,11 @@
 </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>00:47.334</p></td>
+<td><p>00:46.799</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:42.089</p></td>
+<td><p>00:42.009</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 e8b0cf37f..c269beadb 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>00:03.203</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.194</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -331,11 +331,11 @@
 </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>00:02.812</p></td>
+<td><p>00:02.815</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>00:00.391</p></td>
+<td><p>00:00.379</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 e5f540d5a..a45ddd9cc 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>00:00.715</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.695</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -331,11 +331,11 @@
 </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>00:00.387</p></td>
+<td><p>00:00.375</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>00:00.328</p></td>
+<td><p>00:00.320</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 1cd99b55e..0d0c288d2 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -474,6 +474,9 @@ 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>
@@ -561,7 +564,7 @@ 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: 94.232 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.679 ms
 </pre></div>
 </div>
 </div>
@@ -635,6 +638,7 @@ 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  4.997 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 de4802938..6691c075a 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -660,16 +660,16 @@ reduce variance, we take 5 measurements and average them.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
 device available
 Get devices for measurement successfully!
-No: 1   GFLOPS: 10.25/10.25     result: MeasureResult(costs=(0.026179888799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560853481292725, timestamp=1656103743.932299)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
-No: 2   GFLOPS: 2.67/10.25      result: MeasureResult(costs=(0.1006437088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.758345603942871, timestamp=1656103746.2208872)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
-No: 3   GFLOPS: 11.73/11.73     result: MeasureResult(costs=(0.0228894768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5927228927612305, timestamp=1656103746.7917702)       [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
-No: 4   GFLOPS: 1.85/11.73      result: MeasureResult(costs=(0.1451685982,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.432061195373535, timestamp=1656103749.7913995)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
-No: 5   GFLOPS: 3.58/11.73      result: MeasureResult(costs=(0.0749977926,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3312056064605713, timestamp=1656103751.250486)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
-No: 6   GFLOPS: 1.70/11.73      result: MeasureResult(costs=(0.15767939839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6846201419830322, timestamp=1656103753.9809964)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
-No: 7   GFLOPS: 0.86/11.73      result: MeasureResult(costs=(0.3104200336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.081960439682007, timestamp=1656103759.621381) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
-No: 8   GFLOPS: 10.64/11.73     result: MeasureResult(costs=(0.0252224752,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.541811466217041, timestamp=1656103760.1866388)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
-No: 9   GFLOPS: 1.89/11.73      result: MeasureResult(costs=(0.14176163400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3615221977233887, timestamp=1656103762.666653) [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
-No: 10  GFLOPS: 2.76/11.73      result: MeasureResult(costs=(0.097177004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6571660041809082, timestamp=1656103764.3823142)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
+No: 1   GFLOPS: 9.90/9.90       result: MeasureResult(costs=(0.0271204122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5677464008331299, timestamp=1656106042.2186384)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
+No: 2   GFLOPS: 2.80/9.90       result: MeasureResult(costs=(0.0957543954,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6820878982543945, timestamp=1656106044.4355528)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
+No: 3   GFLOPS: 11.79/11.79     result: MeasureResult(costs=(0.0227757816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5960910320281982, timestamp=1656106045.0045743)       [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
+No: 4   GFLOPS: 1.72/11.79      result: MeasureResult(costs=(0.1562885542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.620313882827759, timestamp=1656106048.1923103)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
+No: 5   GFLOPS: 3.59/11.79      result: MeasureResult(costs=(0.0747638204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3331496715545654, timestamp=1656106049.6533155)       [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
+No: 6   GFLOPS: 1.66/11.79      result: MeasureResult(costs=(0.1620144816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.71201753616333, timestamp=1656106052.9291515) [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
+No: 7   GFLOPS: 0.82/11.79      result: MeasureResult(costs=(0.3285055248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.372325897216797, timestamp=1656106058.3483934)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
+No: 8   GFLOPS: 10.13/11.79     result: MeasureResult(costs=(0.026508293999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5659093856811523, timestamp=1656106058.9367528)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
+No: 9   GFLOPS: 1.52/11.79      result: MeasureResult(costs=(0.1767549098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9282991886138916, timestamp=1656106061.9854414)       [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
+No: 10  GFLOPS: 2.57/11.79      result: MeasureResult(costs=(0.104364645,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.77083158493042, timestamp=1656106063.8148737)  [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
 </pre></div>
 </div>
 <p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 87301bb89..0543b623e 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -542,7 +542,7 @@ 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;: 494.34439387000003, &#39;median&#39;: 494.35892080000485, &#39;std&#39;: 0.746111878681599}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 495.5015535999996, &#39;median&#39;: 495.33758939999757, &#39;std&#39;: 0.8942336265092279}
 </pre></div>
 </div>
 </div>
@@ -697,179 +697,179 @@ depending on the specifics of the model and the target platform.</p>
   &quot;target_host parameter is going to be deprecated. &quot;
 
 [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  1/25]  Current/Best:   17.51/  17.51 GFLOPS | Progress: (4/20) | 5.69 s
-[Task  1/25]  Current/Best:    6.17/  17.51 GFLOPS | Progress: (8/20) | 9.15 s
-[Task  1/25]  Current/Best:   11.55/  22.81 GFLOPS | Progress: (12/20) | 11.59 s
-[Task  1/25]  Current/Best:   16.80/  22.81 GFLOPS | Progress: (16/20) | 13.25 s
-[Task  1/25]  Current/Best:   11.62/  23.88 GFLOPS | Progress: (20/20) | 14.99 s Done.
+[Task  1/25]  Current/Best:   17.47/  17.47 GFLOPS | Progress: (4/20) | 6.22 s
+[Task  1/25]  Current/Best:    6.15/  17.47 GFLOPS | Progress: (8/20) | 9.11 s
+[Task  1/25]  Current/Best:   11.53/  22.77 GFLOPS | Progress: (12/20) | 11.57 s
+[Task  1/25]  Current/Best:   16.80/  22.77 GFLOPS | Progress: (16/20) | 13.25 s
+[Task  1/25]  Current/Best:   11.63/  23.87 GFLOPS | Progress: (20/20) | 14.97 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:   12.26/  13.15 GFLOPS | Progress: (4/20) | 3.60 s
-[Task  2/25]  Current/Best:   14.15/  18.45 GFLOPS | Progress: (8/20) | 4.92 s
-[Task  2/25]  Current/Best:   21.07/  21.07 GFLOPS | Progress: (12/20) | 6.23 s
-[Task  2/25]  Current/Best:   12.00/  21.07 GFLOPS | Progress: (16/20) | 7.49 s
-[Task  2/25]  Current/Best:   20.16/  21.07 GFLOPS | Progress: (20/20) | 9.04 s Done.
+[Task  2/25]  Current/Best:   12.24/  12.94 GFLOPS | Progress: (4/20) | 3.89 s
+[Task  2/25]  Current/Best:   13.64/  18.57 GFLOPS | Progress: (8/20) | 5.21 s
+[Task  2/25]  Current/Best:   21.34/  21.34 GFLOPS | Progress: (12/20) | 6.52 s
+[Task  2/25]  Current/Best:   12.70/  21.34 GFLOPS | Progress: (16/20) | 7.78 s
+[Task  2/25]  Current/Best:   19.49/  21.34 GFLOPS | Progress: (20/20) | 9.40 s Done.
 
 [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  3/25]  Current/Best:    1.63/  10.57 GFLOPS | Progress: (4/20) | 5.85 s
-[Task  3/25]  Current/Best:   15.61/  16.92 GFLOPS | Progress: (8/20) | 7.75 s
-[Task  3/25]  Current/Best:   14.89/  16.92 GFLOPS | Progress: (12/20) | 9.47 s
-[Task  3/25]  Current/Best:    7.19/  23.74 GFLOPS | Progress: (16/20) | 11.35 s
-[Task  3/25]  Current/Best:   12.67/  23.74 GFLOPS | Progress: (20/20) | 15.88 s Done.
+[Task  3/25]  Current/Best:    1.63/  10.50 GFLOPS | Progress: (4/20) | 5.84 s
+[Task  3/25]  Current/Best:   15.61/  16.86 GFLOPS | Progress: (8/20) | 7.75 s
+[Task  3/25]  Current/Best:   14.88/  16.86 GFLOPS | Progress: (12/20) | 9.49 s
+[Task  3/25]  Current/Best:    7.22/  23.79 GFLOPS | Progress: (16/20) | 11.40 s
+[Task  3/25]  Current/Best:   12.63/  23.79 GFLOPS | Progress: (20/20) | 15.97 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:    9.54/  20.34 GFLOPS | Progress: (4/20) | 2.36 s
-[Task  4/25]  Current/Best:    6.55/  20.34 GFLOPS | Progress: (8/20) | 6.66 s
-[Task  4/25]  Current/Best:   21.86/  21.86 GFLOPS | Progress: (12/20) | 11.22 s
-[Task  4/25]  Current/Best:   15.95/  21.86 GFLOPS | Progress: (16/20) | 13.41 s
-[Task  4/25]  Current/Best:   13.40/  21.86 GFLOPS | Progress: (20/20) | 15.29 s Done.
+[Task  4/25]  Current/Best:    9.56/  20.46 GFLOPS | Progress: (4/20) | 2.38 s
+[Task  4/25]  Current/Best:    6.65/  20.46 GFLOPS | Progress: (8/20) | 7.09 s
+[Task  4/25]  Current/Best:   22.08/  22.08 GFLOPS | Progress: (12/20) | 12.11 s
+[Task  4/25]  Current/Best:   16.04/  22.08 GFLOPS | Progress: (16/20) | 14.49 s
+[Task  4/25]  Current/Best:   12.68/  22.08 GFLOPS | Progress: (20/20) | 16.47 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:    9.53/  10.32 GFLOPS | Progress: (4/20) | 2.57 s
-[Task  5/25]  Current/Best:   11.85/  11.85 GFLOPS | Progress: (8/20) | 4.63 s
-[Task  5/25]  Current/Best:   11.61/  18.03 GFLOPS | Progress: (12/20) | 7.72 s
-[Task  5/25]  Current/Best:   11.71/  22.34 GFLOPS | Progress: (16/20) | 9.13 s
-[Task  5/25]  Current/Best:   12.07/  22.34 GFLOPS | Progress: (20/20) | 10.94 s Done.
+[Task  5/25]  Current/Best:    9.73/  10.20 GFLOPS | Progress: (4/20) | 2.59 s
+[Task  5/25]  Current/Best:   11.73/  12.53 GFLOPS | Progress: (8/20) | 4.66 s
+[Task  5/25]  Current/Best:   11.56/  18.02 GFLOPS | Progress: (12/20) | 7.85 s
+[Task  5/25]  Current/Best:   11.79/  22.51 GFLOPS | Progress: (16/20) | 9.27 s
+[Task  5/25]  Current/Best:   12.08/  22.51 GFLOPS | Progress: (20/20) | 11.18 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   12.30/  20.74 GFLOPS | Progress: (4/20) | 3.95 s
-[Task  6/25]  Current/Best:   19.01/  20.74 GFLOPS | Progress: (8/20) | 5.68 s
-[Task  6/25]  Current/Best:   13.31/  20.74 GFLOPS | Progress: (12/20) | 7.60 s
-[Task  6/25]  Current/Best:   19.96/  20.74 GFLOPS | Progress: (16/20) | 9.84 s
-[Task  6/25]  Current/Best:    3.71/  20.74 GFLOPS | Progress: (20/20) | 12.35 s Done.
+[Task  6/25]  Current/Best:   12.21/  20.79 GFLOPS | Progress: (4/20) | 4.25 s
+[Task  6/25]  Current/Best:   18.98/  20.79 GFLOPS | Progress: (8/20) | 6.00 s
+[Task  6/25]  Current/Best:   13.32/  20.79 GFLOPS | Progress: (12/20) | 7.93 s
+[Task  6/25]  Current/Best:   19.97/  20.79 GFLOPS | Progress: (16/20) | 10.16 s
+[Task  6/25]  Current/Best:    3.71/  20.79 GFLOPS | Progress: (20/20) | 12.69 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   10.21/  12.91 GFLOPS | Progress: (4/20) | 3.60 s
-[Task  7/25]  Current/Best:   20.29/  21.03 GFLOPS | Progress: (8/20) | 5.09 s
-[Task  7/25]  Current/Best:   15.88/  21.03 GFLOPS | Progress: (12/20) | 7.03 s
-[Task  7/25]  Current/Best:   12.25/  21.03 GFLOPS | Progress: (16/20) | 9.07 s
-[Task  7/25]  Current/Best:    6.44/  21.78 GFLOPS | Progress: (20/20) | 11.50 s Done.
+[Task  7/25]  Current/Best:   10.29/  12.90 GFLOPS | Progress: (4/20) | 3.53 s
+[Task  7/25]  Current/Best:   20.17/  21.20 GFLOPS | Progress: (8/20) | 5.05 s
+[Task  7/25]  Current/Best:   15.80/  21.20 GFLOPS | Progress: (12/20) | 6.97 s
+[Task  7/25]  Current/Best:   12.23/  21.20 GFLOPS | Progress: (16/20) | 9.00 s
+[Task  7/25]  Current/Best:    6.44/  21.64 GFLOPS | Progress: (20/20) | 11.45 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    9.93/  14.01 GFLOPS | Progress: (4/20) | 2.93 s
-[Task  8/25]  Current/Best:    9.56/  14.01 GFLOPS | Progress: (8/20) | 7.59 s
-[Task  8/25]  Current/Best:   12.76/  14.01 GFLOPS | Progress: (12/20) | 13.65 s
-[Task  8/25]  Current/Best:   18.81/  18.81 GFLOPS | Progress: (16/20) | 15.74 s
-[Task  8/25]  Current/Best:   19.64/  19.64 GFLOPS | Progress: (20/20) | 22.22 s Done.
+[Task  8/25]  Current/Best:    9.95/  13.91 GFLOPS | Progress: (4/20) | 2.91 s
+[Task  8/25]  Current/Best:    9.67/  13.91 GFLOPS | Progress: (8/20) | 8.02 s
+[Task  8/25]  Current/Best:   12.53/  13.91 GFLOPS | Progress: (12/20) | 14.52 s
+[Task  8/25]  Current/Best:   18.63/  18.63 GFLOPS | Progress: (16/20) | 16.63 s
+[Task  8/25]  Current/Best:   20.35/  20.35 GFLOPS | Progress: (20/20) | 23.78 s Done.
 
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:   14.40/  15.41 GFLOPS | Progress: (4/20) | 11.93 s
-[Task  9/25]  Current/Best:   23.47/  23.47 GFLOPS | Progress: (8/20) | 13.73 s
-[Task  9/25]  Current/Best:    8.26/  23.47 GFLOPS | Progress: (12/20) | 16.08 s
-[Task  9/25]  Current/Best:   17.95/  23.47 GFLOPS | Progress: (16/20) | 18.72 s
-[Task  9/25]  Current/Best:    9.10/  23.47 GFLOPS | Progress: (20/20) | 26.22 s
+[Task  9/25]  Current/Best:   14.26/  15.73 GFLOPS | Progress: (4/20) | 11.96 s
+[Task  9/25]  Current/Best:   23.43/  23.43 GFLOPS | Progress: (8/20) | 13.71 s
+[Task  9/25]  Current/Best:    8.32/  23.43 GFLOPS | Progress: (12/20) | 16.25 s
+[Task  9/25]  Current/Best:   17.89/  23.43 GFLOPS | Progress: (16/20) | 19.14 s
+[Task  9/25]  Current/Best:    9.06/  23.43 GFLOPS | Progress: (20/20) | 27.77 s
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.18/  18.18 GFLOPS | Progress: (4/20) | 2.55 s
-[Task 10/25]  Current/Best:   15.22/  18.18 GFLOPS | Progress: (8/20) | 4.12 s
-[Task 10/25]  Current/Best:   12.89/  18.84 GFLOPS | Progress: (12/20) | 5.64 s
-[Task 10/25]  Current/Best:   18.96/  20.47 GFLOPS | Progress: (16/20) | 6.75 s
-[Task 10/25]  Current/Best:    9.08/  20.47 GFLOPS | Progress: (20/20) | 8.26 s Done.
+[Task 10/25]  Current/Best:   18.06/  18.06 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 10/25]  Current/Best:   15.48/  18.06 GFLOPS | Progress: (8/20) | 4.19 s
+[Task 10/25]  Current/Best:   12.82/  19.17 GFLOPS | Progress: (12/20) | 5.73 s
+[Task 10/25]  Current/Best:   19.00/  20.14 GFLOPS | Progress: (16/20) | 6.83 s
+[Task 10/25]  Current/Best:    9.00/  20.14 GFLOPS | Progress: (20/20) | 8.35 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   12.27/  18.08 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 11/25]  Current/Best:   16.95/  18.08 GFLOPS | Progress: (8/20) | 5.96 s
-[Task 11/25]  Current/Best:   18.05/  18.08 GFLOPS | Progress: (12/20) | 8.01 s
-[Task 11/25]  Current/Best:   13.24/  21.20 GFLOPS | Progress: (16/20) | 10.78 s
-[Task 11/25]  Current/Best:   19.42/  21.61 GFLOPS | Progress: (20/20) | 12.80 s Done.
+[Task 11/25]  Current/Best:   12.24/  18.12 GFLOPS | Progress: (4/20) | 3.36 s
+[Task 11/25]  Current/Best:   16.80/  18.12 GFLOPS | Progress: (8/20) | 6.15 s
+[Task 11/25]  Current/Best:   18.03/  18.12 GFLOPS | Progress: (12/20) | 8.24 s
+[Task 11/25]  Current/Best:   13.40/  21.18 GFLOPS | Progress: (16/20) | 11.19 s
+[Task 11/25]  Current/Best:   19.41/  21.58 GFLOPS | Progress: (20/20) | 13.30 s Done.
 
 [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25]  Current/Best:    7.84/  18.03 GFLOPS | Progress: (4/20) | 5.21 s
-[Task 12/25]  Current/Best:    5.17/  18.03 GFLOPS | Progress: (8/20) | 8.87 s
-[Task 12/25]  Current/Best:   18.94/  18.94 GFLOPS | Progress: (12/20) | 10.84 s
-[Task 12/25]  Current/Best:   15.52/  18.94 GFLOPS | Progress: (16/20) | 13.59 s
-[Task 12/25]  Current/Best:   15.10/  18.94 GFLOPS | Progress: (20/20) | 15.55 s Done.
+[Task 12/25]  Current/Best:    7.81/  18.10 GFLOPS | Progress: (4/20) | 5.71 s
+[Task 12/25]  Current/Best:    5.15/  18.10 GFLOPS | Progress: (8/20) | 9.63 s
+[Task 12/25]  Current/Best:   18.87/  18.97 GFLOPS | Progress: (12/20) | 11.63 s
+[Task 12/25]  Current/Best:   14.46/  18.97 GFLOPS | Progress: (16/20) | 14.57 s
+[Task 12/25]  Current/Best:   15.24/  19.01 GFLOPS | Progress: (20/20) | 16.48 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:    8.68/  17.25 GFLOPS | Progress: (4/20) | 3.67 s
-[Task 13/25]  Current/Best:   15.82/  20.89 GFLOPS | Progress: (8/20) | 6.11 s
-[Task 13/25]  Current/Best:   19.40/  21.41 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 13/25]  Current/Best:   12.17/  21.41 GFLOPS | Progress: (16/20) | 12.37 s
-[Task 13/25]  Current/Best:   18.47/  21.41 GFLOPS | Progress: (20/20) | 14.60 s Done.
+[Task 13/25]  Current/Best:    8.66/  17.27 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 13/25]  Current/Best:   16.09/  20.89 GFLOPS | Progress: (8/20) | 6.39 s
+[Task 13/25]  Current/Best:   19.43/  20.99 GFLOPS | Progress: (12/20) | 9.49 s
+[Task 13/25]  Current/Best:   12.27/  20.99 GFLOPS | Progress: (16/20) | 12.89 s
+[Task 13/25]  Current/Best:   18.62/  20.99 GFLOPS | Progress: (20/20) | 15.19 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   13.33/  13.33 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 14/25]  Current/Best:    6.08/  13.33 GFLOPS | Progress: (8/20) | 5.40 s
-[Task 14/25]  Current/Best:   21.05/  21.05 GFLOPS | Progress: (12/20) | 7.89 s
-[Task 14/25]  Current/Best:   15.17/  21.05 GFLOPS | Progress: (16/20) | 9.58 s Done.
+[Task 14/25]  Current/Best:   13.49/  13.49 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 14/25]  Current/Best:    6.08/  13.49 GFLOPS | Progress: (8/20) | 5.48 s
+[Task 14/25]  Current/Best:   20.52/  20.52 GFLOPS | Progress: (12/20) | 8.15 s
+[Task 14/25]  Current/Best:   16.72/  20.52 GFLOPS | Progress: (16/20) | 9.80 s Done.
 
-[Task 14/25]  Current/Best:   17.19/  21.05 GFLOPS | Progress: (20/20) | 11.32 s
+[Task 14/25]  Current/Best:   17.23/  20.52 GFLOPS | Progress: (20/20) | 11.54 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:   16.21/  17.65 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 15/25]  Current/Best:   14.16/  18.14 GFLOPS | Progress: (8/20) | 3.97 s
-[Task 15/25]  Current/Best:   10.35/  22.10 GFLOPS | Progress: (12/20) | 6.02 s
-[Task 15/25]  Current/Best:   20.39/  22.10 GFLOPS | Progress: (16/20) | 9.13 s
-[Task 15/25]  Current/Best:    9.71/  22.10 GFLOPS | Progress: (20/20) | 10.15 s
+[Task 15/25]  Current/Best:   16.13/  17.65 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 15/25]  Current/Best:   14.23/  18.07 GFLOPS | Progress: (8/20) | 4.05 s
+[Task 15/25]  Current/Best:   10.39/  22.33 GFLOPS | Progress: (12/20) | 6.31 s
+[Task 15/25]  Current/Best:   20.42/  22.33 GFLOPS | Progress: (16/20) | 9.40 s
+[Task 15/25]  Current/Best:    9.69/  22.33 GFLOPS | Progress: (20/20) | 10.42 s
 [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25]  Current/Best:   19.48/  19.48 GFLOPS | Progress: (4/20) | 2.99 s
-[Task 16/25]  Current/Best:    3.02/  19.48 GFLOPS | Progress: (8/20) | 4.62 s
-[Task 16/25]  Current/Best:   19.11/  19.48 GFLOPS | Progress: (12/20) | 5.84 s
-[Task 16/25]  Current/Best:   17.36/  19.48 GFLOPS | Progress: (16/20) | 7.21 s
-[Task 16/25]  Current/Best:   10.06/  22.58 GFLOPS | Progress: (20/20) | 9.23 s Done.
+[Task 16/25]  Current/Best:   20.33/  20.33 GFLOPS | Progress: (4/20) | 3.09 s
+[Task 16/25]  Current/Best:    2.99/  20.33 GFLOPS | Progress: (8/20) | 4.72 s
+[Task 16/25]  Current/Best:   19.50/  20.33 GFLOPS | Progress: (12/20) | 5.95 s
+[Task 16/25]  Current/Best:   18.18/  20.33 GFLOPS | Progress: (16/20) | 7.34 s
+[Task 16/25]  Current/Best:   10.04/  22.34 GFLOPS | Progress: (20/20) | 9.49 s Done.
 
 [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   13.08/  18.89 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 17/25]  Current/Best:   14.45/  23.32 GFLOPS | Progress: (8/20) | 7.51 s
-[Task 17/25]  Current/Best:   16.97/  23.32 GFLOPS | Progress: (12/20) | 9.56 s
-[Task 17/25]  Current/Best:   16.54/  23.32 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 17/25]  Current/Best:   10.06/  23.32 GFLOPS | Progress: (20/20) | 13.78 s Done.
+[Task 17/25]  Current/Best:   12.88/  16.64 GFLOPS | Progress: (4/20) | 4.82 s
+[Task 17/25]  Current/Best:   14.38/  23.19 GFLOPS | Progress: (8/20) | 7.72 s
+[Task 17/25]  Current/Best:   17.29/  23.19 GFLOPS | Progress: (12/20) | 9.79 s
+[Task 17/25]  Current/Best:   16.44/  23.19 GFLOPS | Progress: (16/20) | 12.00 s
+[Task 17/25]  Current/Best:   10.05/  23.19 GFLOPS | Progress: (20/20) | 14.17 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   11.36/  17.90 GFLOPS | Progress: (4/20) | 3.64 s
-[Task 18/25]  Current/Best:   10.43/  17.90 GFLOPS | Progress: (8/20) | 7.12 s
-[Task 18/25]  Current/Best:   19.07/  19.07 GFLOPS | Progress: (12/20) | 9.06 s
-[Task 18/25]  Current/Best:   10.08/  19.07 GFLOPS | Progress: (16/20) | 12.59 s
-[Task 18/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (20/20) | 14.10 s Done.
+[Task 18/25]  Current/Best:   11.71/  18.04 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 18/25]  Current/Best:   10.56/  20.03 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 18/25]  Current/Best:   19.13/  20.03 GFLOPS | Progress: (12/20) | 9.44 s
+[Task 18/25]  Current/Best:   10.00/  20.03 GFLOPS | Progress: (16/20) | 13.27 s
+[Task 18/25]  Current/Best:   20.59/  20.59 GFLOPS | Progress: (20/20) | 14.79 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:    7.18/  20.46 GFLOPS | Progress: (4/20) | 5.97 s
-[Task 19/25]  Current/Best:    2.61/  20.46 GFLOPS | Progress: (8/20) | 9.18 s
-[Task 19/25]  Current/Best:   19.29/  21.88 GFLOPS | Progress: (12/20) | 11.96 s
-[Task 19/25]  Current/Best:   13.10/  21.88 GFLOPS | Progress: (16/20) | 14.82 s
-[Task 19/25]  Current/Best:    2.70/  23.56 GFLOPS | Progress: (20/20) | 17.63 s Done.
+[Task 19/25]  Current/Best:    6.89/  20.20 GFLOPS | Progress: (4/20) | 6.24 s
+[Task 19/25]  Current/Best:    2.61/  20.20 GFLOPS | Progress: (8/20) | 9.59 s
+[Task 19/25]  Current/Best:   19.42/  20.89 GFLOPS | Progress: (12/20) | 12.50 s
+[Task 19/25]  Current/Best:   15.22/  21.44 GFLOPS | Progress: (16/20) | 15.45 s
+[Task 19/25]  Current/Best:    2.70/  22.64 GFLOPS | Progress: (20/20) | 18.24 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:    9.27/  15.33 GFLOPS | Progress: (4/20) | 3.30 s Done.
+[Task 20/25]  Current/Best:    9.01/  14.88 GFLOPS | Progress: (4/20) | 3.37 s Done.
  Done.
 
-[Task 20/25]  Current/Best:    9.64/  15.33 GFLOPS | Progress: (8/20) | 6.57 s
-[Task 20/25]  Current/Best:    2.32/  16.53 GFLOPS | Progress: (12/20) | 10.40 s
-[Task 20/25]  Current/Best:   12.35/  16.53 GFLOPS | Progress: (16/20) | 13.90 s
-[Task 20/25]  Current/Best:   12.25/  22.08 GFLOPS | Progress: (20/20) | 15.98 s
+[Task 20/25]  Current/Best:    9.95/  14.88 GFLOPS | Progress: (8/20) | 6.79 s
+[Task 20/25]  Current/Best:    2.32/  16.68 GFLOPS | Progress: (12/20) | 10.78 s
+[Task 20/25]  Current/Best:   12.41/  16.68 GFLOPS | Progress: (16/20) | 14.72 s
+[Task 20/25]  Current/Best:   13.53/  21.64 GFLOPS | Progress: (20/20) | 16.82 s
 [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:    6.38/  17.67 GFLOPS | Progress: (4/20) | 3.21 s
-[Task 21/25]  Current/Best:   14.63/  17.67 GFLOPS | Progress: (8/20) | 4.79 s
-[Task 21/25]  Current/Best:    1.61/  17.67 GFLOPS | Progress: (12/20) | 6.92 s
-[Task 21/25]  Current/Best:   18.05/  18.05 GFLOPS | Progress: (16/20) | 10.32 s
-[Task 21/25]  Current/Best:    4.46/  18.05 GFLOPS | Progress: (20/20) | 17.31 s
+[Task 21/25]  Current/Best:    6.40/  17.65 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 21/25]  Current/Best:   14.32/  17.65 GFLOPS | Progress: (8/20) | 4.90 s
+[Task 21/25]  Current/Best:    1.61/  17.65 GFLOPS | Progress: (12/20) | 7.03 s
+[Task 21/25]  Current/Best:   18.17/  18.17 GFLOPS | Progress: (16/20) | 10.57 s
+[Task 21/25]  Current/Best:    4.47/  18.17 GFLOPS | Progress: (20/20) | 18.01 s
 [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25]  Current/Best:    2.70/  16.93 GFLOPS | Progress: (4/20) | 2.65 s
-[Task 22/25]  Current/Best:    8.66/  21.85 GFLOPS | Progress: (8/20) | 4.62 s
-[Task 22/25]  Current/Best:   20.02/  21.85 GFLOPS | Progress: (12/20) | 6.90 s
-[Task 22/25]  Current/Best:   14.79/  21.85 GFLOPS | Progress: (16/20) | 8.98 s
-[Task 22/25]  Current/Best:   14.97/  21.85 GFLOPS | Progress: (20/20) | 10.69 s Done.
+[Task 22/25]  Current/Best:    2.70/  17.01 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 22/25]  Current/Best:    8.75/  21.82 GFLOPS | Progress: (8/20) | 4.75 s
+[Task 22/25]  Current/Best:   19.58/  21.82 GFLOPS | Progress: (12/20) | 7.16 s
+[Task 22/25]  Current/Best:   15.59/  21.82 GFLOPS | Progress: (16/20) | 9.28 s
+[Task 22/25]  Current/Best:   14.64/  21.82 GFLOPS | Progress: (20/20) | 11.03 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:   17.62/  20.08 GFLOPS | Progress: (4/20) | 3.23 s
-[Task 23/25]  Current/Best:   14.39/  20.08 GFLOPS | Progress: (8/20) | 6.49 s
-[Task 23/25]  Current/Best:   20.81/  21.42 GFLOPS | Progress: (12/20) | 8.28 s
-[Task 23/25]  Current/Best:    6.45/  21.42 GFLOPS | Progress: (16/20) | 15.11 s
-[Task 23/25]  Current/Best:    7.78/  21.42 GFLOPS | Progress: (20/20) | 19.31 s Done.
+[Task 23/25]  Current/Best:   17.44/  20.18 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 23/25]  Current/Best:   15.75/  20.18 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 23/25]  Current/Best:   20.81/  21.39 GFLOPS | Progress: (12/20) | 8.59 s
+[Task 23/25]  Current/Best:    6.17/  21.39 GFLOPS | Progress: (16/20) | 15.64 s
+[Task 23/25]  Current/Best:    7.65/  21.39 GFLOPS | Progress: (20/20) | 19.93 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    8.39/   8.39 GFLOPS | Progress: (4/20) | 11.77 s
-[Task 24/25]  Current/Best:    3.56/   8.39 GFLOPS | Progress: (8/20) | 23.00 s
-[Task 24/25]  Current/Best:    4.45/   8.39 GFLOPS | Progress: (12/20) | 33.71 s Done.
+[Task 24/25]  Current/Best:    8.54/   8.54 GFLOPS | Progress: (4/20) | 11.81 s
+[Task 24/25]  Current/Best:    3.44/   8.54 GFLOPS | Progress: (8/20) | 23.07 s
+[Task 24/25]  Current/Best:    4.58/   8.54 GFLOPS | Progress: (12/20) | 33.81 s Done.
  Done.
 
-[Task 24/25]  Current/Best:    5.93/   8.85 GFLOPS | Progress: (16/20) | 39.12 s
-[Task 24/25]  Current/Best:    3.30/   8.85 GFLOPS | Progress: (20/20) | 44.91 s Done.
+[Task 24/25]  Current/Best:    7.13/   8.70 GFLOPS | Progress: (16/20) | 39.61 s
+[Task 24/25]  Current/Best:    3.31/   8.76 GFLOPS | Progress: (20/20) | 45.66 s Done.
 
 [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25]  Current/Best:    1.55/   2.75 GFLOPS | Progress: (4/20) | 11.57 s
-[Task 25/25]  Current/Best:    5.69/   8.12 GFLOPS | Progress: (8/20) | 22.82 s
-[Task 25/25]  Current/Best:    5.95/   8.12 GFLOPS | Progress: (12/20) | 34.29 s
-[Task 25/25]  Current/Best:    5.78/   8.88 GFLOPS | Progress: (16/20) | 35.98 s
-[Task 25/25]  Current/Best:    2.88/   8.88 GFLOPS | Progress: (20/20) | 46.64 s
+[Task 25/25]  Current/Best:    1.55/   2.92 GFLOPS | Progress: (4/20) | 11.61 s
+[Task 25/25]  Current/Best:    5.65/   7.90 GFLOPS | Progress: (8/20) | 22.86 s
+[Task 25/25]  Current/Best:    5.96/   7.90 GFLOPS | Progress: (12/20) | 34.33 s
+[Task 25/25]  Current/Best:    5.78/   9.25 GFLOPS | Progress: (16/20) | 36.10 s
+[Task 25/25]  Current/Best:    2.88/   9.25 GFLOPS | Progress: (20/20) | 46.78 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -972,8 +972,8 @@ 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;: 410.96431230999997, &#39;median&#39;: 410.907805450006, &#39;std&#39;: 0.8809606599589154}
-unoptimized: {&#39;mean&#39;: 494.34439387000003, &#39;median&#39;: 494.35892080000485, &#39;std&#39;: 0.746111878681599}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 411.66733768000313, &#39;median&#39;: 411.5519871500055, &#39;std&#39;: 0.38716530809748584}
+unoptimized: {&#39;mean&#39;: 495.5015535999996, &#39;median&#39;: 495.33758939999757, &#39;std&#39;: 0.8942336265092279}
 </pre></div>
 </div>
 </div>
@@ -987,7 +987,7 @@ models.</p>
 <p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
 supports many more features including cross-compilation, remote execution and
 profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  10.730 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  22.108 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 a7b7da679..9c81e984e 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -518,7 +518,7 @@ 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>1.319e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.314e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index cf432b29b..bf733017c 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ 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, 0x208f8870)), stage(b, placeholder(b, 0x22007500)), 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, 0x21838230)), stage(b, placeholder(b, 0x44ae300)), 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 ad5c84076..b93a89537 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
             
   <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>12:55.129</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:23.311</strong> total execution time for <strong>tutorial</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -331,27 +331,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:10.730</p></td>
+<td><p>10:22.108</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:59.151</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>01:04.997</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:51.477</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>01:01.105</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>00:27.953</p></td>
+<td><p>00:28.173</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>00:23.865</p></td>
+<td><p>00:25.073</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.143</p></td>
+<td><p>00:01.037</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
@@ -359,7 +359,7 @@
 <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>00:00.139</p></td>
+<td><p>00:00.148</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 4ed956226..245ec7e96 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -534,7 +534,7 @@ helper function to run a profile of the TVM generated code.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000006
+naive: 0.000007
 </pre></div>
 </div>
 </div>
@@ -626,7 +626,7 @@ factor to be the number of threads on your CPU.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vector: 0.000026
+vector: 0.000025
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type=&quot;auto&quot;),
@@ -659,10 +659,10 @@ vector: 0.000026
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    7.727449999492819e-06                    1.0
-   naive    5.8567999999999996e-06    0.7579214359697446
-parallel              6.1058e-06      0.7901442261549083
-  vector             2.63021e-05      3.4037230912818983
+   numpy    8.136739998008125e-06                    1.0
+   naive               6.816e-06      0.8376819219575109
+parallel              6.0722e-06      0.7462693906265255
+  vector    2.4624800000000002e-05     3.026371741757529
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -978,7 +978,7 @@ 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: 0.017895
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019072
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1021,7 +1021,7 @@ optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-none: 3.283269
+none: 3.410031
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1088,7 +1088,7 @@ schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-blocking: 0.301291
+blocking: 0.311227
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1149,7 +1149,7 @@ already cache friendly from our previous optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vectorization: 0.343489
+vectorization: 0.343408
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1206,7 +1206,7 @@ more cache friendly.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-loop permutation: 0.113401
+loop permutation: 0.118194
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1284,7 +1284,7 @@ optimized schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-array packing: 0.108325
+array packing: 0.108928
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1360,7 +1360,7 @@ to `C</cite> when all the block results are ready.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-block caching: 0.110696
+block caching: 0.110495
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1429,7 +1429,7 @@ of thread-level parallelization.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-parallelization: 0.144732
+parallelization: 0.144055
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ 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      3.2832685142000004                     1.0
-        blocking            0.3012914517     0.09176570554522938
-   vectorization     0.34348864960000003     0.10461789771821155
-loop permutation     0.11340090430000001    0.034539028352248924
-   array packing            0.1083249895    0.032993033932953976
-   block caching            0.1106958311    0.033715131924557835
- parallelization            0.1447315333    0.044081540292559715
+            none      3.4100311574999997                     1.0
+        blocking     0.31122655289999995     0.09126794991755144
+   vectorization            0.3434083098      0.1007053290538739
+loop permutation             0.118194036     0.03466069092654618
+   array packing     0.10892798249999999    0.031943398012779005
+   block caching     0.11049544009999998     0.03240305879815117
+ parallelization            0.1440551873     0.04224453696945436
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1529,6 +1529,7 @@ 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  1.105 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>