[tvm-site] branch asf-site updated: deploying docs (apache/tvm@648a29a53a641f1e923220600dce9c9215104879)

[tq...@apache.org]

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

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


The following commit(s) were added to refs/heads/asf-site by this push:
     new 81d3ad911 deploying docs (apache/tvm@648a29a53a641f1e923220600dce9c9215104879)
81d3ad911 is described below

commit 81d3ad9118f14c4b152b64d1cc2d0c0c36f95c4d
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Aug 29 09:58:35 2022 +0000

    deploying docs (apache/tvm@648a29a53a641f1e923220600dce9c9215104879)
---
 .../how_to/compile_models/from_darknet.rst.txt     |    2 +-
 .../how_to/compile_models/from_mxnet.rst.txt       |    2 +-
 .../how_to/compile_models/from_oneflow.rst.txt     |    2 +-
 .../how_to/compile_models/from_pytorch.rst.txt     |    2 +-
 .../how_to/compile_models/from_tensorflow.rst.txt  |    2 +-
 .../compile_models/sg_execution_times.rst.txt      |   22 +-
 .../deploy_models/deploy_model_on_android.rst.txt  |    2 +-
 .../deploy_object_detection_pytorch.rst.txt        |    4 +-
 .../deploy_models/deploy_prequantized.rst.txt      |    6 +-
 .../deploy_prequantized_tflite.rst.txt             |    4 +-
 .../how_to/deploy_models/deploy_quantized.rst.txt  |    2 +-
 .../deploy_models/deploy_ssd_gluoncv.rst.txt       |    4 +-
 .../deploy_models/sg_execution_times.rst.txt       |   20 +-
 .../extend_tvm/bring_your_own_datatypes.rst.txt    |    2 +-
 .../how_to/extend_tvm/sg_execution_times.rst.txt   |    8 +-
 .../how_to/extend_tvm/use_pass_instrument.rst.txt  |   16 +-
 .../optimize_operators/opt_conv_cuda.rst.txt       |    2 +-
 .../optimize_operators/opt_conv_tensorcore.rst.txt |    2 +-
 .../how_to/optimize_operators/opt_gemm.rst.txt     |   16 +-
 .../optimize_operators/sg_execution_times.rst.txt  |    8 +-
 .../sg_execution_times.rst.txt                     |   14 +-
 .../tune_conv2d_layer_cuda.rst.txt                 | 1032 +++-----------------
 .../tune_network_cuda.rst.txt                      |    2 +-
 .../tune_network_x86.rst.txt                       |    4 +-
 .../tune_sparse_x86.rst.txt                        |   88 +-
 .../tune_with_autotvm/sg_execution_times.rst.txt   |    8 +-
 .../tune_with_autotvm/tune_conv2d_cuda.rst.txt     |   26 +-
 .../work_with_microtvm/micro_autotune.rst.txt      |   16 +-
 .../how_to/work_with_microtvm/micro_train.rst.txt  |   16 +-
 .../work_with_microtvm/sg_execution_times.rst.txt  |   10 +-
 .../work_with_relay/sg_execution_times.rst.txt     |    8 +-
 .../how_to/work_with_schedules/intrin_math.rst.txt |    2 +-
 .../work_with_schedules/sg_execution_times.rst.txt |   14 +-
 .../how_to/work_with_schedules/tensorize.rst.txt   |    2 +-
 .../tutorials/autotvm/sg_execution_times.rst.txt   |    6 +-
 .../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     |    9 +-
 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  |   24 +-
 .../tutorial/tensor_expr_get_started.rst.txt       |   44 +-
 docs/commit_hash                                   |    2 +-
 docs/how_to/compile_models/from_darknet.html       |    2 +-
 docs/how_to/compile_models/from_mxnet.html         |    2 +-
 docs/how_to/compile_models/from_oneflow.html       |   12 +-
 docs/how_to/compile_models/from_pytorch.html       |    6 +-
 docs/how_to/compile_models/from_tensorflow.html    |    2 +-
 docs/how_to/compile_models/sg_execution_times.html |   26 +-
 .../deploy_models/deploy_model_on_android.html     |    2 +-
 .../deploy_object_detection_pytorch.html           |   18 +-
 docs/how_to/deploy_models/deploy_prequantized.html |    6 +-
 .../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  |   38 +-
 docs/how_to/deploy_models/sg_execution_times.html  |   20 +-
 .../extend_tvm/bring_your_own_datatypes.html       |    2 +-
 docs/how_to/extend_tvm/sg_execution_times.html     |    8 +-
 docs/how_to/extend_tvm/use_pass_instrument.html    |   16 +-
 docs/how_to/optimize_operators/opt_conv_cuda.html  |    2 +-
 .../optimize_operators/opt_conv_tensorcore.html    |    2 +-
 docs/how_to/optimize_operators/opt_gemm.html       |   16 +-
 .../optimize_operators/sg_execution_times.html     |    8 +-
 .../sg_execution_times.html                        |   14 +-
 .../tune_conv2d_layer_cuda.html                    | 1032 +++-----------------
 .../tune_with_autoscheduler/tune_network_cuda.html |    2 +-
 .../tune_with_autoscheduler/tune_network_x86.html  |    4 +-
 .../tune_with_autoscheduler/tune_sparse_x86.html   |   88 +-
 .../tune_with_autotvm/sg_execution_times.html      |    8 +-
 .../how_to/tune_with_autotvm/tune_conv2d_cuda.html |   26 +-
 docs/how_to/work_with_microtvm/micro_autotune.html |   16 +-
 docs/how_to/work_with_microtvm/micro_train.html    |   16 +-
 .../work_with_microtvm/sg_execution_times.html     |   10 +-
 .../how_to/work_with_relay/sg_execution_times.html |    8 +-
 docs/how_to/work_with_schedules/intrin_math.html   |    2 +-
 .../work_with_schedules/sg_execution_times.html    |   14 +-
 docs/how_to/work_with_schedules/tensorize.html     |    2 +-
 docs/install/nnpack.html                           |   12 +-
 ...stvm_1_1meta__schedule_1_1Database-members.html |    7 +-
 .../classtvm_1_1meta__schedule_1_1Database.html    |   41 +-
 ..._1_1meta__schedule_1_1DatabaseNode-members.html |    6 +-
 ...classtvm_1_1meta__schedule_1_1DatabaseNode.html |   69 +-
 ..._1_1meta__schedule_1_1Database__coll__graph.svg |  107 +-
 ...1meta__schedule_1_1Database__inherit__graph.svg |   79 +-
 ..._1meta__schedule_1_1PyDatabaseNode-members.html |    6 +-
 ...asstvm_1_1meta__schedule_1_1PyDatabaseNode.html |   18 +-
 docs/reference/api/doxygen/database_8h_source.html |   33 +-
 docs/reference/api/doxygen/functions_func_q.html   |    6 +-
 docs/reference/api/doxygen/functions_func_r.html   |    2 +-
 docs/reference/api/doxygen/functions_func_s.html   |   17 +-
 docs/reference/api/doxygen/functions_func_t.html   |    8 +-
 docs/reference/api/doxygen/functions_func_u.html   |    2 +-
 docs/reference/api/doxygen/functions_m.html        |    2 +-
 docs/reference/api/doxygen/functions_q.html        |    6 +-
 docs/reference/api/doxygen/functions_s.html        |   13 +-
 docs/reference/api/doxygen/functions_t.html        |    6 +-
 docs/reference/api/doxygen/functions_u.html        |    2 +-
 docs/reference/api/doxygen/search/all_12.js        |    6 +-
 docs/reference/api/doxygen/search/all_13.js        |    6 +-
 docs/reference/api/doxygen/search/all_14.js        |   11 +-
 docs/reference/api/doxygen/search/all_15.js        |    8 +-
 docs/reference/api/doxygen/search/all_16.js        |    4 +-
 docs/reference/api/doxygen/search/all_17.js        |    2 +-
 docs/reference/api/doxygen/search/all_18.js        |    2 +-
 docs/reference/api/doxygen/search/all_e.js         |    4 +-
 docs/reference/api/doxygen/search/all_f.js         |    2 +-
 docs/reference/api/doxygen/search/functions_11.js  |    6 +-
 docs/reference/api/doxygen/search/functions_12.js  |    4 +-
 docs/reference/api/doxygen/search/functions_13.js  |    7 +-
 docs/reference/api/doxygen/search/functions_14.js  |    4 +-
 docs/reference/api/doxygen/search/functions_15.js  |    2 +-
 docs/reference/api/doxygen/search/functions_d.js   |    2 +-
 docs/reference/api/doxygen/search/functions_e.js   |    2 +-
 docs/reference/api/doxygen/search/typedefs_e.js    |    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  |    6 +-
 .../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       |    5 +-
 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              |   28 +-
 docs/tutorial/tensor_expr_get_started.html         |   44 +-
 158 files changed, 1453 insertions(+), 2903 deletions(-)

diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index c5c60dcf7..3a959ee1a 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  1.784 seconds)
+   **Total running time of the script:** ( 1 minutes  5.194 seconds)
 
 
 .. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 2ff8cf797..a0b79fb09 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe4bef291-8bb6-4e0d-9e47-a236ea289cb2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+    Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc6ac7d72-b8d6-43eb-9196-08a19b8683b4 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 8ec3753d9..a0e1139fd 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
  .. code-block:: none
 
     Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 50.1MB/s]
     39%|###8      | 16.0M/41.5M [00:00<00:00, 56.7MB/s]
     58%|#####7    | 24.0M/41.5M [00:00<00:00, 44.8MB/s]
     77%|#######7  | 32.1M/41.5M [00:00<00:00, 54.5MB/s]
     95%|#########4| 39.3M/41.5M [00:00<00:00, 59.9MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 54.1MB/s]
+
      0%|          | 0.00/41.5M [00:00<?, ?B/s]
     19%|#9        | 7.99M/41.5M [00:00<00:00, 65.3MB/s]
     35%|###4      | 14.3M/41.5M [00:00<00:00, 63.1MB/s]
     56%|#####5    | 23.1M/41.5M [00:00<00:00, 75.0MB/s]
     77%|#######7  | 32.0M/41.5M [00:00<00:00, 65.8MB/s]
     93%|#########2| 38.5M/41.5M [00:00<00:00, 63.1MB/s]
    100%|##########| 41.5M/41.5M [00:00<00:00, 63.5MB/s]
 
 
 
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 7dcddaebb..3183d6a11 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
      9%|9         | 4.23M/44.7M [00:00<00:00, 43.9MB/s]
     19%|#8        | 8.42M/44.7M [00:00<00:00, 41.8MB/s]
     71%|#######1  | 31.8M/44.7M [00:00<00:00, 132MB/s] 
    100%|##########| 44.7M/44.7M [00:00<00:00, 126MB/s]
+
      0%|          | 0.00/44.7M [00:00<?, ?B/s]
     42%|####1     | 18.6M/44.7M [00:00<00:00, 195MB/s]
    100%|##########| 44.7M/44.7M [00:00<00:00, 236MB/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 8969adff0..5ea12244d 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  5.388 seconds)
+   **Total running time of the script:** ( 1 minutes  4.001 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 cdd1d1fe4..d576396e0 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
 =================
-**05:02.291** total execution time for **how_to_compile_models** files:
+**05:11.405** total execution time for **how_to_compile_models** files:
 
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.388 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:05.194 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)       | 01:01.784 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.001 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:38.254 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)         | 00:40.080 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:28.271 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)       | 00:28.599 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:25.576 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)           | 00:26.121 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:24.228 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)         | 00:25.053 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:21.777 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)         | 00:23.551 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:18.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)       | 00:19.792 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:15.786 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)           | 00:16.508 | 0.0 MB |
 +-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)             | 00:02.504 | 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 821625874..d3f7ed47d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      15.0291      14.4506      19.6940      14.1347       1.5876   
+      16.2976      16.2951      16.4644      16.1974       0.0772   
                
 
 
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 04feb940d..23f6fb01a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
      0%|          | 0.00/170M [00:00<?, ?B/s]
     11%|#1        | 19.1M/170M [00:00<00:00, 200MB/s]
     27%|##6       | 45.3M/170M [00:00<00:00, 244MB/s]
     41%|####      | 68.9M/170M [00:00<00:00, 246MB/s]
     56%|#####5    | 94.7M/170M [00:00<00:00, 255MB/s]
     70%|#######   | 119M/170M [00:00<00:00, 251MB/s] 
     84%|########4 | 143M/170M [00:00<00:00, 249MB/s]
     98%|#########8| 167M/170M [00:00<00:00, 229MB/s]
    100%|##########| 170M/170M [00:00<00:00, 233MB/s]
+
      0%|          | 0.00/170M [00:00<?, ?B/s]
      9%|9         | 16.0M/170M [00:00<00:00, 168MB/s]
     23%|##3       | 39.1M/170M [00:00<00:00, 212MB/s]
     36%|###6      | 61.8M/170M [00:00<00:00, 224MB/s]
     51%|#####     | 86.0M/170M [00:00<00:00, 236MB/s]
     67%|######6   | 113M/170M [00:00<00:00, 253MB/s] 
     82%|########1 | 139M/170M [00:00<00:00, 260MB/s]
     97%|#########7| 166M/170M [00:00<00:00, 265MB/s]
    100%|##########| 170M/170M [00:00<00:00, 249MB/s]
     /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
       for i in range(dim)
     /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  45.466 seconds)
+   **Total running time of the script:** ( 3 minutes  5.033 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 d60a30d9e..9c7d53129 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
  .. code-block:: none
 
     Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 190MB/s]
+
      0%|          | 0.00/13.6M [00:00<?, ?B/s]
    100%|##########| 13.6M/13.6M [00:00<00:00, 170MB/s]
 
 
 
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      87.6873      87.5938      89.7886      87.3683       0.3204   
+      90.3629      90.2958      91.0122      90.0396       0.2039   
                
 
 
@@ -461,7 +461,7 @@ TODO
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  7.082 seconds)
+   **Total running time of the script:** ( 1 minutes  12.091 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 7c16c0d04..0fc0ed24e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      115.6665     115.1263     127.4992     114.3867      1.6262   
+      121.3593     121.3275     123.8800     120.6025      0.4172   
                
 
 
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  49.682 seconds)
+   **Total running time of the script:** ( 1 minutes  53.523 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 1c5131540..62e45289e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  28.696 seconds)
+   **Total running time of the script:** ( 1 minutes  22.251 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 65d721ca8..fe6293638 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
             data: None
       input_sym_arg_type = in_param.infer_type()[0]
     Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
      0%|          | 0/132723 [00:00<?, ?KB/s]
      4%|3         | 5229/132723 [00:00<00:02, 52283.69KB/s]
      9%|9         | 12562/132723 [00:00<00:01, 64659.12KB/s]
     15%|#5        | 19947/132723 [00:00<00:01, 68853.09KB/s]
     21%|##        | 27427/132723 [00:00<00:01, 71189.63KB/s]
     26%|##6       | 34856/132723 [00:00<00:01, 72305.71KB/s]
     32%|###1      | 42265/132723 [00:00<00:01, 72909.44KB/s]
     37%|###7      | 49663/132723 [00:00<00:01, 73256.62KB/s]
     43%|####3     | 57116/132723 [00:00<00:01, 73660.25KB/s]
     49%|####8     | 64483/132723 [00:00<00:00, 73539.73KB/s]
     54%|#####4    | 71838/132723 [00:01<00:00, 71950.11KB/s]
     60%|#####9    | 79293/132723 [00:01<00:00, 72725.77KB/s]
     65%|######5   | 86748/132723 [00:01<00:00, 73273.82KB/s]
     71%|#######   | 94189/132723 [00:01<00:00, 73613.48KB/s]
     77%|#######6  | 101584/132723 [00:01<00:00, 73713.21KB/s]
     82%|########2 | 109013/132723 [00:01<00:00, 73881.66KB/s]
     88%|########7
  | 116485/132723 [00:01<00:00, 74130.36KB/s]
     93%|#########3| 123997/132723 [00:01<00:00, 74426.42KB/s]
     99%|#########9| 131606/132723 [00:01<00:00, 74923.44KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 72803.15KB/s]
+
      0%|          | 0/132723 [00:00<?, ?KB/s]
      5%|4         | 6487/132723 [00:00<00:01, 64862.95KB/s]
     11%|#1        | 14941/132723 [00:00<00:01, 76422.53KB/s]
     18%|#7        | 23357/132723 [00:00<00:01, 79943.89KB/s]
     24%|##4       | 31917/132723 [00:00<00:01, 82165.54KB/s]
     30%|###       | 40134/132723 [00:00<00:01, 71533.21KB/s]
     37%|###6      | 48619/132723 [00:00<00:01, 75653.08KB/s]
     42%|####2     | 56356/132723 [00:00<00:01, 68794.80KB/s]
     49%|####8     | 64760/132723 [00:00<00:00, 73113.54KB/s]
     55%|#####5    | 73149/132723 [00:00<00:00, 76218.11KB/s]
     62%|######1   | 81651/132723 [00:01<00:00, 78783.77KB/s]
     68%|######7   | 90172/132723 [00:01<00:00, 80672.12KB/s]
     74%|#######4  | 98333/132723 [00:01<00:00, 80520.07KB/s]
     80%|########  | 106450/132723 [00:01<00:00, 77082.61KB/s]
     86%|########6 | 114695/132723 [00:01<00:00, 78624.16KB/s]
     93%|#########2| 123186/132723 [00:01<00:00, 80453.24KB/s]
     99%|########
 #9| 131750/132723 [00:01<00:00, 81974.25KB/s]
    100%|##########| 132723/132723 [00:01<00:00, 77717.08KB/s]
 
 
 
@@ -241,7 +241,7 @@ Display result
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  31.356 seconds)
+   **Total running time of the script:** ( 2 minutes  42.544 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 3080a6136..e03ff9b55 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
 
 Computation times
 =================
-**10:53.919** total execution time for **how_to_deploy_models** files:
+**11:32.847** 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``) | 02:45.466 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:05.033 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:31.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)                           | 02:42.544 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:49.682 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)           | 01:53.523 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:28.696 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)                               | 01:22.251 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:07.082 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)                         | 01:12.091 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:28.655 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)                 | 00:31.474 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:21.608 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``)                       | 00:23.329 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:21.367 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)                       | 00:22.595 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)                                     | 00:00.007 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 2efafaf4c..072bfd44c 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
 
  .. code-block:: none
 
-    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0071ef9f-14bf-49ab-a4ab-4c36f8f23624 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+    Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip72f9f933-de15-44b4-8a4a-63b292c3a6bf from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 
 
 
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index ed7d1ed6d..9d16e5631 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:40.025** total execution time for **how_to_extend_tvm** files:
+**00:43.777** 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``) | 00:36.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:40.426 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.132 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)           | 00:02.344 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.897 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)                     | 00:00.999 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)       | 00:00.008 | 0.0 MB |
 +-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index f6d8c3781..d49466ce1 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6683us [6683us] (46.14%; 46.14%)
-    FoldScaleAxis: 7800us [5us] (53.86%; 53.86%)
-            FoldConstant: 7795us [1639us] (53.82%; 99.93%)
-                    InferType: 6156us [6156us] (42.51%; 78.98%)
+    InferType: 7102us [7102us] (46.63%; 46.63%)
+    FoldScaleAxis: 8129us [7us] (53.37%; 53.37%)
+            FoldConstant: 8122us [1696us] (53.32%; 99.91%)
+                    InferType: 6426us [6426us] (42.19%; 79.11%)
 
 
 
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
  .. code-block:: none
 
     Printing results of timing profile...
-    InferType: 6197us [6197us] (44.38%; 44.38%)
-    FoldScaleAxis: 7765us [4us] (55.62%; 55.62%)
-            FoldConstant: 7761us [1680us] (55.59%; 99.95%)
-                    InferType: 6081us [6081us] (43.55%; 78.35%)
+    InferType: 6542us [6542us] (43.06%; 43.06%)
+    FoldScaleAxis: 8651us [5us] (56.94%; 56.94%)
+            FoldConstant: 8645us [1683us] (56.91%; 99.94%)
+                    InferType: 6963us [6963us] (45.83%; 80.54%)
 
 
 
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 093c64ac3..79c31fc62 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
 
  .. code-block:: none
 
-    Convolution: 54.309120 ms
+    Convolution: 38.524817 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 6b3390ba5..3aeb995ab 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
 
  .. code-block:: none
 
-    conv2d with tensor core: 7.021444 ms
+    conv2d with tensor core: 11.179388 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 8dbcd1f2e..719609dcb 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 
  .. code-block:: none
 
-    Numpy running time: 0.015417
-    Baseline: 3.434214
+    Numpy running time: 0.019202
+    Baseline: 3.320618
 
 
 
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 
  .. code-block:: none
 
-    Opt1: 0.296426
+    Opt1: 0.324964
 
 
 
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
 
  .. code-block:: none
 
-    Opt2: 0.326353
+    Opt2: 0.352623
 
 
 
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
 
  .. code-block:: none
 
-    Opt3: 0.111500
+    Opt3: 0.125868
 
 
 
@@ -563,7 +563,7 @@ flattening.
 
  .. code-block:: none
 
-    Opt4: 0.106720
+    Opt4: 0.109626
 
 
 
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
 
  .. code-block:: none
 
-    Opt5: 0.099107
+    Opt5: 0.112154
 
 
 
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
 
  .. code-block:: none
 
-    Opt6: 0.130604
+    Opt6: 0.147503
 
 
 
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 b12853b22..f6c3e0ca6 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
 =================
-**00:32.968** total execution time for **how_to_optimize_operators** files:
+**00:34.964** total execution time for **how_to_optimize_operators** files:
 
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:30.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)                       | 00:32.727 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.197 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.263 | 0.0 MB |
 +-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:01.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)             | 00:00.974 | 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 d4a759fdb..95d0903df 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
 
 Computation times
 =================
-**06:08.259** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:11.346** total execution time for **how_to_tune_with_autoscheduler** files:
 
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:16.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:20.911 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:20.012 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)             | 01:24.704 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:45.813 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)           | 00:48.404 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:29.355 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)               | 00:19.047 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:08.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)           | 00:09.216 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:08.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)             | 00:09.063 | 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 4bcafee3f..217232fae 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,484 +240,65 @@ 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" = 28;
-      allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-      allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-      allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+      attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+      allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+      allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+      allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+      attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
+        conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
         conv2d_nchw_1[1] = 0f32
-        conv2d_nchw_1[2] = 0f32
-        conv2d_nchw_1[3] = 0f32
-        conv2d_nchw_1[4] = 0f32
-        conv2d_nchw_1[5] = 0f32
-        conv2d_nchw_1[6] = 0f32
-        conv2d_nchw_1[7] = 0f32
-        conv2d_nchw_1[8] = 0f32
-        conv2d_nchw_1[9] = 0f32
-        conv2d_nchw_1[10] = 0f32
-        conv2d_nchw_1[11] = 0f32
-        conv2d_nchw_1[12] = 0f32
-        conv2d_nchw_1[13] = 0f32
-        for (rc.outer.outer: int32, 0, 64) {
-          for (ry.outer.outer: int32, 0, 3) {
-            let cse_var_2: int32 = (rc.outer.outer*72)
-            let cse_var_1: int32 = (ry.outer.outer*3)
-             {
-              attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
-                }
-                if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
-                  pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
-                }
-              }
-              attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-              attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
-              kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-              conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-              conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+        for (rc.outer.outer: int32, 0, 32) {
+          let cse_var_2: int32 = (rc.outer.outer*784)
+          let cse_var_1: int32 = (rc.outer.outer*144)
+           {
+            attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+            attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
+              pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+            }
+            attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+            attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+            if @tir.likely((threadIdx.x_2 < 344), dtype=bool) {
+              kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+            }
+            for (rc.outer.inner: int32, 0, 16) {
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9))]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1152)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1153)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 2)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1154)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 3)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1155)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 4)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1156)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 5)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1157)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 6)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1158)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 7)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1159)]))
+              conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 8)]))
+              conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1160)]))
             }
           }
         }
-        for (i1.inner: int32, 0, 2) {
-          for (i3.inner: int32, 0, 7) {
-            compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-          }
-        }
+        compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
+        compute[(((blockIdx.x*784) + threadIdx.x) + 392)] = max((conv2d_nchw_1[1] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 8)]), 0f32)
       }
     }
 
@@ -771,7 +352,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 0.359 ms
+    Execution time of this operator: 0.276 ms
 
 
 
@@ -820,35 +401,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
     conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
     conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
     conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
-    conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+    conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+    conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+    conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
     conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
     conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+    conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
     conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
     conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-    conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+    conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+    conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
     conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-    conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-    conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+    conv2d_nchw_rc_o_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=16)
     conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+    conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
     conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
     conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
     s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
     compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
     compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
     compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
-    compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+    compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+    compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+    compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
     compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+    compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
     compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-    compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+    compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+    compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
     compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
     s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
     s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -868,14 +449,14 @@ 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=64)
+    kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
     s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
     pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
     s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+    pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
     s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+    s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
     s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
 
     CUDA source code:
@@ -893,431 +474,52 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
       #define int64_t long long
       #define uint64_t unsigned long long
     #endif
-    extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-      float conv2d_nchw[14];
-      __shared__ float pad_temp_shared[72];
-      __shared__ float kernel_shared[3072];
+    extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+      float conv2d_nchw[2];
+      __shared__ float pad_temp_shared[1296];
+      __shared__ float kernel_shared[2304];
       conv2d_nchw[0] = 0.000000e+00f;
       conv2d_nchw[1] = 0.000000e+00f;
-      conv2d_nchw[2] = 0.000000e+00f;
-      conv2d_nchw[3] = 0.000000e+00f;
-      conv2d_nchw[4] = 0.000000e+00f;
-      conv2d_nchw[5] = 0.000000e+00f;
-      conv2d_nchw[6] = 0.000000e+00f;
-      conv2d_nchw[7] = 0.000000e+00f;
-      conv2d_nchw[8] = 0.000000e+00f;
-      conv2d_nchw[9] = 0.000000e+00f;
-      conv2d_nchw[10] = 0.000000e+00f;
-      conv2d_nchw[11] = 0.000000e+00f;
-      conv2d_nchw[12] = 0.000000e+00f;
-      conv2d_nchw[13] = 0.000000e+00f;
-      for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
-        for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
-          __syncthreads();
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-          }
-          if (((int)threadIdx.x) < 18) {
-            pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-          }
-          kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-          kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-          kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-          kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-          kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-          kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-          kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-          kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-          kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-          kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-          kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-          kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-          kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-          kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-          kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-          kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-          kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-          __syncthreads();
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-          conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-          conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+      for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+        __syncthreads();
+        pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+        pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+        if (((int)threadIdx.x) < 120) {
+          pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
         }
-      }
-      for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
-        for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
-          compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+        kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+        kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+        kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 24) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+        kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+        if (((int)threadIdx.x) < 344) {
+          kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+        }
+        __syncthreads();
+        for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9))]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1152)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1153)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 2)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1154)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 3)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1155)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 4)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1156)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 5)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1157)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 6)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1158)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 7)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1159)]));
+          conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 8)]));
+          conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1160)]));
         }
       }
+      compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
+      compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 8)]), 0.000000e+00f);
     }
 
 
@@ -1378,7 +580,7 @@ In the example below we resume the status and do more 5 trials.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  16.114 seconds)
+   **Total running time of the script:** ( 3 minutes  20.911 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 e8cb29bf3..31a63f01d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-       9.8441       9.8558       9.8899       9.7867       0.0429   
+       9.7366       9.7491       9.7752       9.6855       0.0377   
                
 
 
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 ba796dc5f..577471a4c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
     Evaluate inference time cost...
     Execution time summary:
      mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)  
-      724.5897     725.6453     725.9321     722.1918      1.6997   
+      754.9634     753.7135     758.5801     752.5968      2.5976   
                
 
 
@@ -694,7 +694,7 @@ Other Tips
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  20.012 seconds)
+   **Total running time of the script:** ( 1 minutes  24.704 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 201f6dc5c..3cb8296e9 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,30 +397,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
                  placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
                  compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
       buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-      preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
-      for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
-        allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
-          for (nb_j.inner: int32, 0, 2) {
-            for (i.inner.init: int32, 0, 16) {
-              for (j.init: int32, 0, 16) {
-                compute_5: Buffer(compute_4, float32, [512], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+      preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+      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 (nb_j.inner: int32, 0, 2) {
+              for (i.inner.init: int32, 0, 32) {
+                let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+                 {
+                  compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+                  compute_5[(cse_var_1 + 1)] = 0f32
+                  compute_5[(cse_var_1 + 2)] = 0f32
+                  compute_5[(cse_var_1 + 3)] = 0f32
+                  compute_5[(cse_var_1 + 4)] = 0f32
+                  compute_5[(cse_var_1 + 5)] = 0f32
+                  compute_5[(cse_var_1 + 6)] = 0f32
+                  compute_5[(cse_var_1 + 7)] = 0f32
+                  compute_5[(cse_var_1 + 8)] = 0f32
+                  compute_5[(cse_var_1 + 9)] = 0f32
+                  compute_5[(cse_var_1 + 10)] = 0f32
+                  compute_5[(cse_var_1 + 11)] = 0f32
+                  compute_5[(cse_var_1 + 12)] = 0f32
+                  compute_5[(cse_var_1 + 13)] = 0f32
+                  compute_5[(cse_var_1 + 14)] = 0f32
+                  compute_5[(cse_var_1 + 15)] = 0f32
+                }
               }
-            }
-            for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
-              for (i.inner: int32, 0, 16) {
-                for (j: int32, 0, 16) {
-                  let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-                  let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
-                  compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+              for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+                for (i.inner: int32, 0, 32) {
+                  let cse_var_21: int32 = (elem_idx*16)
+                  let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+                  let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+                  let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
+                  let cse_var_17: int32 = (cse_var_19 + 9)
+                  let cse_var_16: int32 = (cse_var_19 + 8)
+                  let cse_var_15: int32 = (cse_var_19 + 7)
+                  let cse_var_14: int32 = (cse_var_19 + 6)
+                  let cse_var_13: int32 = (cse_var_19 + 5)
+                  let cse_var_12: int32 = (cse_var_19 + 4)
+                  let cse_var_11: int32 = (cse_var_19 + 3)
+                  let cse_var_10: int32 = (cse_var_19 + 2)
+                  let cse_var_9: int32 = (cse_var_19 + 15)
+                  let cse_var_8: int32 = (cse_var_19 + 14)
+                  let cse_var_7: int32 = (cse_var_19 + 13)
+                  let cse_var_6: int32 = (cse_var_19 + 12)
+                  let cse_var_5: int32 = (cse_var_19 + 11)
+                  let cse_var_4: int32 = (cse_var_19 + 10)
+                  let cse_var_3: int32 = (cse_var_19 + 1)
+                   {
+                    compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                    compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                  }
                 }
               }
             }
           }
-          for (i0.inner: int32, 0, 16) {
-            for (i1.inner: int32, 0, 32) {
-              let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
-              compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
-            }
+          for (i0.inner: int32, 0, 64) {
+            let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+            compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
           }
         }
       }
@@ -476,7 +524,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 1.344 ms
+    Execution time of this operator: 1.706 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 7f3559212..59f6b1fd9 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
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:45.955** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.012** total execution time for **how_to_tune_with_autotvm** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:45.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)           | 00:45.975 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)               | 00:00.021 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)             | 00:00.006 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)               | 00:00.005 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
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 1a992be8f..91e56736e 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-    No: 9   GFLOPS: 124.23/124.23   result: MeasureResult(costs=(0.0018635354464285713,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0049548149108887, timestamp=1661726143.1269948)      [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-    No: 10  GFLOPS: 0.00/124.23     result: Traceback (most recent call last):
+    No: 9   GFLOPS: 80.76/80.76     result: MeasureResult(costs=(0.002866645114285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6300137042999268, timestamp=1661762819.134481)        [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+    No: 10  GFLOPS: 0.00/80.76      result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-    No: 11  GFLOPS: 261.55/261.55   result: MeasureResult(costs=(0.0008851109226519337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7494337558746338, timestamp=1661726144.0495627)      [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-    No: 12  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 11  GFLOPS: 260.38/260.38   result: MeasureResult(costs=(0.0008890813314917127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8063113689422607, timestamp=1661762820.0628433)      [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+    No: 12  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-    No: 13  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 13  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-    No: 14  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 14  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-    No: 15  GFLOPS: 5.31/261.55     result: MeasureResult(costs=(0.0436028125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7915902137756348, timestamp=1661726148.5534027)       [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-    No: 16  GFLOPS: 3.36/261.55     result: MeasureResult(costs=(0.0689840615,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.487291097640991, timestamp=1661726149.780498) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-    No: 17  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 15  GFLOPS: 5.32/260.38     result: MeasureResult(costs=(0.04353801625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8395516872406006, timestamp=1661762824.6931133)      [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+    No: 16  GFLOPS: 3.34/260.38     result: MeasureResult(costs=(0.06939788649999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6329381465911865, timestamp=1661762825.9308784)        [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+    No: 17  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
         res = future.result()
       File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
     TimeoutError
 
             [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-    No: 18  GFLOPS: 28.15/261.55    result: MeasureResult(costs=(0.008223709142857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2816195487976074, timestamp=1661726160.8156836)       [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-    No: 19  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 18  GFLOPS: 27.06/260.38    result: MeasureResult(costs=(0.0085550076875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3366832733154297, timestamp=1661762837.0193772)    [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+    No: 19  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
         raise InstantiationError("Skipped because of invalid gpu kernel")
     tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-    No: 20  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+    No: 20  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
         func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
       File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
     Best config:
     [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
     Finish loading 20 records
-    Time cost of this operator: 0.001235
+    Time cost of this operator: 0.001281
 
 
 
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 8d06da4f9..b9e45eff1 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
     ########## Build without Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  305.6     98.732   (1, 2, 10, 10, 3)  2       1        [305.6]           
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       2.958     0.956    (1, 6, 10, 10)     1       1        [2.958]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.967     0.312    (1, 1, 10, 10, 3)  1       1        [0.967]           
-    Total_time                                    -                                             309.525   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.7     98.75    (1, 2, 10, 10, 3)  2       1        [313.7]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.018     0.95     (1, 6, 10, 10)     1       1        [3.018]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.952     0.3      (1, 1, 10, 10, 3)  1       1        [0.952]           
+    Total_time                                    -                                             317.67    -        -                  -       -        -                 
 
 
 
@@ -398,10 +398,10 @@ Timing the tuned program
     ########## Build with Autotuning ##########
     Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)  
     ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------  
-    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  120.875   97.825   (1, 6, 10, 10, 1)  2       1        [120.875]         
-    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.751     1.417    (1, 6, 10, 10)     1       1        [1.751]           
-    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.937     0.758    (1, 1, 10, 10, 3)  1       1        [0.937]           
-    Total_time                                    -                                             123.563   -        -                  -       -        -                 
+    tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  118.1     97.732   (1, 6, 10, 10, 1)  2       1        [118.1]           
+    tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.788     1.48     (1, 6, 10, 10)     1       1        [1.788]           
+    tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.952     0.788    (1, 1, 10, 10, 3)  1       1        [0.952]           
+    Total_time                                    -                                             120.84    -        -                  -       -        -                 
 
 
 
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 73836edf5..60b782e4d 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/tmpwu2s8058/images/random'
+    '/tmp/tmpgbf7djs4/images/random'
 
 
 
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
 
  .. code-block:: none
 
-    /tmp/tmpwu2s8058/images/target contains 8144 images
-    /tmp/tmpwu2s8058/images/random contains 5000 images
+    /tmp/tmpgbf7djs4/images/target contains 8144 images
+    /tmp/tmpgbf7djs4/images/random contains 5000 images
 
 
 
@@ -501,13 +501,13 @@ the time on our validation set).
  .. code-block:: none
 
     Epoch 1/3
-    328/328 - 52s - loss: 0.2231 - accuracy: 0.9247 - val_loss: 0.1298 - val_accuracy: 0.9588
+    328/328 - 56s - loss: 0.2194 - accuracy: 0.9227 - val_loss: 0.1336 - val_accuracy: 0.9547
     Epoch 2/3
-    328/328 - 49s - loss: 0.0932 - accuracy: 0.9647 - val_loss: 0.1130 - val_accuracy: 0.9694
+    328/328 - 53s - loss: 0.0964 - accuracy: 0.9636 - val_loss: 0.1116 - val_accuracy: 0.9660
     Epoch 3/3
-    328/328 - 49s - loss: 0.0641 - accuracy: 0.9765 - val_loss: 0.2279 - val_accuracy: 0.9324
+    328/328 - 53s - loss: 0.0647 - accuracy: 0.9748 - val_loss: 0.1574 - val_accuracy: 0.9494
 
-    <keras.callbacks.History object at 0x7ff92532b950>
+    <keras.callbacks.History object at 0x7f23697c1790>
 
 
 
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 4 minutes  45.363 seconds)
+   **Total running time of the script:** ( 4 minutes  45.830 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 176dc86a3..7362d3334 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**05:37.381** total execution time for **how_to_work_with_microtvm** files:
+**05:41.380** total execution time for **how_to_work_with_microtvm** files:
 
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:45.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)               | 04:45.830 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:41.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)         | 00:43.729 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:07.786 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``)                   | 00:08.426 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.214 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)             | 00:03.393 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)             | 00:00.001 | 0.0 MB |
 +---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index df3f78ed7..d4729ba4d 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
 
 Computation times
 =================
-**00:42.236** total execution time for **how_to_work_with_relay** files:
+**00:44.090** total execution time for **how_to_work_with_relay** files:
 
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.713 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.186 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)           | 00:10.316 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)                             | 00:01.581 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)                 | 00:00.007 | 0.0 MB |
 +----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index cc2296dd3..a58e92352 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
  .. code-block:: none
 
 
-    <function my_cuda_math_rule at 0x7ff91d7dc050>
+    <function my_cuda_math_rule at 0x7f22dd418170>
 
 
 
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 cfede9a5a..a1ea4ab54 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
 
 Computation times
 =================
-**00:04.152** total execution time for **how_to_work_with_schedules** files:
+**00:04.159** total execution time for **how_to_work_with_schedules** files:
 
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)                 | 00:01.897 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)                     | 00:01.013 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)                     | 00:00.538 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)                               | 00:00.519 | 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``)                     | 00:00.106 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)                               | 00:00.028 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)               | 00:00.015 | 0.0 MB |
 +------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index c002d2037..31e0b70ec 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
                  C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
       buffer_map = {A_1: A, B_1: B, C_1: C}
       preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-      attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpkfa4_a16/input0.cc'\nsource_filename = \"/tmp/tmpkfa4_a16/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/tmpyj99edgt/input0.cc'\nsource_filename = \"/tmp/tmpyj99edgt/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 2a3d80936..5fe1a7467 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
 =================
-**00:20.566** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.348** total execution time for **topic_vta_tutorials_autotvm** files:
 
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.560 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.342 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)     | 00:00.007 | 0.0 MB |
 +---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index de1d6c856..3f9c8f2d9 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 22.04s!
+    resnet18_v1 inference graph built in 24.50s!
 
 
 
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 de302ef10..4ea79f4f1 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
       "target_host parameter is going to be deprecated. "
     /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
       DeprecationWarning,
-    yolov3-tiny inference graph built in 15.66s!
+    yolov3-tiny inference graph built in 16.94s!
 
 
 
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 3c5b9970d..1e57c2b81 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
 =================
-**01:30.263** total execution time for **topic_vta_tutorials_frontend** files:
+**01:34.723** total execution time for **topic_vta_tutorials_frontend** files:
 
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:48.235 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)           | 00:49.828 | 0.0 MB |
 +------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.028 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.895 | 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 4a9a025ba..76ae43c4b 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
 =================
-**00:03.259** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.271** total execution time for **topic_vta_tutorials_optimize** files:
 
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.850 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)         | 00:02.869 | 0.0 MB |
 +--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.410 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.402 | 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 45e92eb15..c76698f5c 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
 =================
-**00:00.764** total execution time for **topic_vta_tutorials** files:
+**00:00.734** total execution time for **topic_vta_tutorials** files:
 
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.409 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.397 | 0.0 MB |
 +---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.355 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.337 | 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 d3c0e996c..840f41e9c 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,7 +207,7 @@ trials, we can load the best schedule from the log file and apply it.
 
  .. code-block:: none
 
-    *E*E
+    *E
 
 
 
@@ -333,7 +333,7 @@ We build the binary and check its correctness and performance.
 
  .. code-block:: none
 
-    Execution time of this operator: 92.236 ms
+    Execution time of this operator: 93.119 ms
 
 
 
@@ -449,11 +449,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
 operations.
 
 
-.. rst-class:: sphx-glr-timing
-
-   **Total running time of the script:** ( 1 minutes  11.696 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 c05cf58e1..fa52d5a58 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
     waiting for device...
     device available
     Get devices for measurement successfully!
-    No: 1   GFLOPS: 9.11/9.11       result: MeasureResult(costs=(0.029471841,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6021461486816406, timestamp=1661724946.3576689)        [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-    No: 2   GFLOPS: 2.14/9.11       result: MeasureResult(costs=(0.1256582872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1445271968841553, timestamp=1661724948.5297232)       [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-    No: 3   GFLOPS: 11.94/11.94     result: MeasureResult(costs=(0.022489702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5632054805755615, timestamp=1661724949.5852482)        [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-    No: 4   GFLOPS: 1.42/11.94      result: MeasureResult(costs=(0.18853694780000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.137359142303467, timestamp=1661724953.2856922) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-    No: 5   GFLOPS: 3.68/11.94      result: MeasureResult(costs=(0.0728464974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.299680471420288, timestamp=1661724954.7127228)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-    No: 6   GFLOPS: 1.63/11.94      result: MeasureResult(costs=(0.1644681828,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7887916564941406, timestamp=1661724957.546864)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-    No: 7   GFLOPS: 0.82/11.94      result: MeasureResult(costs=(0.3256161328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.327296495437622, timestamp=1661724963.4324474)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-    No: 8   GFLOPS: 10.49/11.94     result: MeasureResult(costs=(0.0256009084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5486633777618408, timestamp=1661724964.0033681)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-    No: 9   GFLOPS: 1.47/11.94      result: MeasureResult(costs=(0.1830801916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.016674757003784, timestamp=1661724967.1381662)        [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-    No: 10  GFLOPS: 2.42/11.94      result: MeasureResult(costs=(0.11074119619999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8749973773956299, timestamp=1661724969.0716505)        [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+    No: 1   GFLOPS: 9.25/9.25       result: MeasureResult(costs=(0.029018732199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6023972034454346, timestamp=1661761578.8374166)       [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+    No: 2   GFLOPS: 2.70/9.25       result: MeasureResult(costs=(0.099548106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7477777004241943, timestamp=1661761580.5970793)        [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+    No: 3   GFLOPS: 11.76/11.76     result: MeasureResult(costs=(0.0228182416,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5506212711334229, timestamp=1661761581.684402)        [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+    No: 4   GFLOPS: 1.83/11.76      result: MeasureResult(costs=(0.1464734124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.466071367263794, timestamp=1661761584.7498503)        [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+    No: 5   GFLOPS: 3.60/11.76      result: MeasureResult(costs=(0.0745418648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3305764198303223, timestamp=1661761586.211585)        [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+    No: 6   GFLOPS: 1.74/11.76      result: MeasureResult(costs=(0.154379631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6465063095092773, timestamp=1661761588.8973215)        [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+    No: 7   GFLOPS: 0.82/11.76      result: MeasureResult(costs=(0.3268341212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.347292423248291, timestamp=1661761594.8402455)        [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+    No: 8   GFLOPS: 9.68/11.76      result: MeasureResult(costs=(0.027718719599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5896084308624268, timestamp=1661761595.4487858)       [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+    No: 9   GFLOPS: 1.53/11.76      result: MeasureResult(costs=(0.1759445694,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9178578853607178, timestamp=1661761598.4879167)       [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+    No: 10  GFLOPS: 2.48/11.76      result: MeasureResult(costs=(0.108381803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.846768856048584, timestamp=1661761600.391835)  [('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 71df354ee..6cc446031 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
 
  .. code-block:: none
 
-    {'mean': 495.8759032300077, 'median': 499.2053312498683, 'std': 7.764164250480838}
+    {'mean': 498.4301331699976, 'median': 498.51982829999884, 'std': 0.4806910936114738}
 
 
 
@@ -563,30 +563,30 @@ the tuning data to.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   19.41/  19.41 GFLOPS | Progress: (4/20) | 6.22 s
    [Task  1/25]  Current/Best:    6.27/  19.41 GFLOPS | Progress: (8/20) | 9.14 s
    [Task  1/25]  Current/Best:   11.64/  23.19 GFLOPS | Progress: (12/20) | 11.51 s
    [Task  1/25]  Current/Best:   18.54/  23.23 GFLOPS | Progress: (16/20) | 13.14 s
    [Task  1/25]  Current/Best:   11.80/  24.23 GFLOPS | Progress: (20/20) | 14.87 s Done.
-
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.45/  13.27 GFLOPS | Progress: (4/20) | 3.73 s
    [Task  2/25]  Current/Best:   14.46/  18.89 GFLOPS | Progress: (8/20) | 5.03 s
    [Task  2/25]  Current/Best:   21.24/  21.24 GFLOPS | Progress: (12/20) | 6.32 s
    [Task  2/25]  Current/Best:   12.87/  21.24 GFLOPS | Progress: (16/20) | 7.55 s
    [Task  2/25]  Current/Best:   19.75/  21.24 GFLOPS | Progress: (20/20) | 9.12 s Done.
-
    [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  3/25]  Current/Best:    1.65/  11.02 GFLOPS | Progress: (4/20) | 5.76 s
    [Task  3/25]  Current/Best:   17.22/  18.81 GFLOPS | Progress: (8/20) | 7.64 s
    [Task  3/25]  Current/Best:   16.84/  18.81 GFLOPS | Progress: (12/20) | 9.28 s
    [Task  3/25]  Current/Best:    7.33/  24.22 GFLOPS | Progress: (16/20) | 11.16 s
    [Task  3/25]  Current/Best:   12.44/  24.22 GFLOPS | Progress: (20/20) | 15.62 s Done.
-
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.61/  20.33 GFLOPS | Progress: (4/20) | 2.36 s
    [Task  4/25]  Current/Best:    6.78/  20.33 GFLOPS | Progress: (8/20) | 6.59 s
    [Task  4/25]  Current/Best:   22.58/  22.58 GFLOPS | Progress: (12/20) | 10.94 s
    [Task  4/25]  Current/Best:   19.32/  22.58 GFLOPS | Progress: (16/20) | 13.16 s
    [Task  4/25]  Current/Best:   13.73/  22.58 GFLOPS | Progress: (20/20) | 15.14 s Done.
-
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.60/  10.44 GFLOPS | Progress: (4/20) | 2.59 s
    [Task  5/25]  Current/Best:   11.84/  12.88 GFLOPS | Progress: (8/20) | 4.62 s
    [Task  5/25]  Current/Best:   12.01/  18.39 GFLOPS | Progress: (12/20) | 7.51 s
    [Task  5/25]  Current/Best:   11.81/  23.07 GFLOPS | Progress: (16/20) | 8.90 s
    [Task  5/25]  Current/Best:   12.34/  23.07 GFLOPS | Progress: (20/20) | 10.74 s Done.
-
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.28/  20.34 GFLOPS | Progress: (4/20) | 3.92 s
    [Task  6/25]  Current/Best:   19.29/  20.34 GFLOPS | Progress: (8/20) | 5.67 s
    [Task  6/25]  Current/Best:   13.57/  20.34 GFLOPS | Progress: (12/20) | 7.58 s
    [Task  6/25]  Current/Best:   20.37/  20.37 GFLOPS | Progress: (16/20) | 9.77 s
    [Task  6/25]  Current/Best:    3.76/  20.37 GFLOPS | Progress: (20/20) | 12.27 s Done.
-
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.37/  12.83 GFLOPS | Progress: (4/20) | 3.59 s
    [Task  7/25]  Current/Best:   20.29/  21.45 GFLOPS | Progress: (8/20) | 5.08 s
    [Task  7/25]  Current/Best:   16.41/  21.45 GFLOPS | Progress: (12/20) | 6.97 s
    [Task  7/25]  Current/Best:   12.43/  21.45 GFLOPS | Progress: (16/20) | 8.99 s
    [Task  7/25]  Current/Best:    6.45/  22.22 GFLOPS | Progress: (20/20) | 11.39 s Done.
-
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:    9.80/  13.83 GFLOPS | Progress: (4/20) | 2.92 s
    [Task  8/25]  Current/Best:    9.36/  13.83 GFLOPS | Progress: (8/20) | 7.62 s
    [Task  8/25]  Current/Best:   12.93/  13.83 GFLOPS | Progress: (12/20) | 13.61 s
    [Task  8/25]  Current/Best:   19.10/  19.10 GFLOPS | Progress: (16/20) | 15.66 s
    [Task  8/25]  Current/Best:   19.63/  19.63 GFLOPS | Progress: (20/20) | 22.07 s Done.
-
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.61/  16.04 GFLOPS | Progress: (4/20) | 11.93 s
    [Task  9/25]  Current/Best:   23.91/  23.91 GFLOPS | Progress: (8/20) | 13.69 s
    [Task  9/25]  Current/Best:    8.37/  23.91 GFLOPS | Progress: (12/20) | 16.02 s
    [Task  9/25]  Current/Best:   18.31/  23.91 GFLOPS | Progress: (16/20) | 18.65 s
    [Task  9/25]  Current/Best:    9.33/  23.91 GFLOPS | Progress: (20/20) | 26.21 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.48/  18.48 GFLOPS | Progress: (4/20) | 2.55 s
    [Task 10/25]  Current/Best:   15.92/  18.48 GFLOPS | Progress: (8/20) | 4.13 s
    [Task 10/25]  Current/Best:   12.63/  19.22 GFLOPS | Progress: (12/20) | 5.64 s
    [Task 10/25]  Current/Best:   19.47/  20.51 GFLOPS | Progress: (16/20) | 6.71 s
    [Task 10/25]  Current/Best:    8.93/  20.51 GFLOPS | Progress: (20/20
 ) | 8.23 s Done.
-
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   12.61/  20.38 GFLOPS | Progress: (4/20) | 3.21 s
    [Task 11/25]  Current/Best:   17.12/  20.38 GFLOPS | Progress: (8/20) | 5.90 s
    [Task 11/25]  Current/Best:   18.51/  20.38 GFLOPS | Progress: (12/20) | 7.92 s
    [Task 11/25]  Current/Best:   13.78/  21.22 GFLOPS | Progress: (16/20) | 10.56 s
    [Task 11/25]  Current/Best:   19.77/  21.94 GFLOPS | Progress: (20/20) | 12.54 s Done.
-
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.97/  18.29 GFLOPS | Progress: (4/20) | 5.30 s
    [Task 12/25]  Current/Best:    5.23/  18.29 GFLOPS | Progress: (8/20) | 8.94 s
    [Task 12/25]  Current/Best:   19.25/  20.92 GFLOPS | Progress: (12/20) | 10.91 s
    [Task 12/25]  Current/Best:   15.70/  20.92 GFLOPS | Progress: (16/20) | 13.62 s
    [Task 12/25]  Current/Best:   15.36/  20.92 GFLOPS | Progress: (20/20) | 15.57 s Done.
-
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.87/  19.34 GFLOPS | Progress: (4/20) | 3.57 s
    [Task 13/25]  Current/Best:   18.02/  21.32 GFLOPS | Progress: (8/20) | 5.91 s
    [Task 13/25]  Current/Best:   20.00/  22.19 GFLOPS | Progress: (12/20) | 8.74 s
    [Task 13/25]  Current/Best:   12.53/  22.19 GFLOPS | Progress: (16/20) | 12.05 s
    [Task 13/25]  Current/Best:   19.15/  22.19 GFLOPS | Progress: (20/20) | 14.25 s Done.
-
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   14.14/  14.14 GFLOPS | Progress: (4/20) | 3.23 s
    [Task 14/25]  Current/Best:    6.22/  15.01 GFLOPS | Progress: (8/20) | 5.37 s
    [Task 14/25]  Current/Best:   21.53/  21.53 GFLOPS | Progress: (12/20) | 7.90 s
    [Task 14/25]  Current/Best:   16.99/  21.53 GFLOPS | Progress: (16/20) | 9.53 s Done.
-
    [Task 14/25]  Current/Best:   17.59/  21.53 GFLOPS | Progress: (20/20) | 11.27 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   18.14/  18.14 GFLOPS | Progress: (4/20) | 2.67 s
    [Task 15/25]  Current/Best:   14.59/  18.42 GFLOPS | Progress: (8/20) | 4.00 s
    [Task 15/25]  Current/Best:   10.57/  22.64 GFLOPS | Progress: (12/20) | 6.04 s
    [Task 15/25]  Current/Best:   22.80/  22.80 GFLOPS | Progress: (16/20) | 9.00 s
    [Task 15/25]  Current/Best:    9.86/  22.80 GFLOPS | Progress: (20/20) | 9.95 s
    [Task 16/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 16/25]  Current/Best:   20.60/  20.60 GFLOPS | Progress: (4/20) | 2.98 s
    [Task 16/25]  Current/Best:    3.07/  20.60 GFLOPS | Progress: (8/20) | 4.58 s
    [Task 16/25]  Current/Best:   19.84/  20.60 GFLOPS | Progress: (12/20) | 5.78 s
    [Task 16/25]  Current/Best:   18.15/  20.60 GFLOPS | Progress: (16/20) | 
 7.10 s
    [Task 16/25]  Current/Best:   10.51/  21.90 GFLOPS | Progress: (20/20) | 9.11 s Done.
-
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   12.71/  18.75 GFLOPS | Progress: (4/20) | 4.65 s
    [Task 17/25]  Current/Best:   14.53/  23.80 GFLOPS | Progress: (8/20) | 7.43 s
    [Task 17/25]  Current/Best:   18.78/  23.80 GFLOPS | Progress: (12/20) | 9.42 s
    [Task 17/25]  Current/Best:   18.47/  23.80 GFLOPS | Progress: (16/20) | 11.51 s
    [Task 17/25]  Current/Best:   10.22/  23.80 GFLOPS | Progress: (20/20) | 13.57 s Done.
-
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.70/  18.73 GFLOPS | Progress: (4/20) | 3.61 s
    [Task 18/25]  Current/Best:   10.78/  18.73 GFLOPS | Progress: (8/20) | 6.98 s
    [Task 18/25]  Current/Best:   19.44/  19.44 GFLOPS | Progress: (12/20) | 8.87 s
    [Task 18/25]  Current/Best:   10.67/  19.44 GFLOPS | Progress: (16/20) | 12.32 s
    [Task 18/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (20/20) | 13.80 s Done.
-
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    7.47/  22.94 GFLOPS | Progress: (4/20) | 5.82 s
    [Task 19/25]  Current/Best:    2.74/  22.94 GFLOPS | Progress: (8/20) | 9.06 s
    [Task 19/25]  Current/Best:   17.58/  22.94 GFLOPS | Progress: (12/20) | 11.87 s
    [Task 19/25]  Current/Best:   14.23/  22.94 GFLOPS | Progress: (16/20) | 14.70 s
    [Task 19/25]  Current/Best:    2.75/  23.74 GFLOPS | Progress: (20/20) | 17.51 s Done.
-
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.22/  15.58 GFLOPS | Progress: (4/20) | 3.26 s Done.
+
    [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  1/25]  Current/Best:   17.21/  17.21 GFLOPS | Progress: (4/20) | 6.49 s
    [Task  1/25]  Current/Best:    6.15/  17.21 GFLOPS | Progress: (8/20) | 9.56 s
    [Task  1/25]  Current/Best:   11.52/  22.59 GFLOPS | Progress: (12/20) | 12.01 s
    [Task  1/25]  Current/Best:   16.42/  22.73 GFLOPS | Progress: (16/20) | 13.71 s
    [Task  1/25]  Current/Best:   11.58/  23.79 GFLOPS | Progress: (20/20) | 15.46 s Done.
+
    [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  2/25]  Current/Best:   12.25/  13.16 GFLOPS | Progress: (4/20) | 3.85 s
    [Task  2/25]  Current/Best:   14.25/  18.70 GFLOPS | Progress: (8/20) | 5.15 s
    [Task  2/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (12/20) | 6.48 s
    [Task  2/25]  Current/Best:   12.74/  20.82 GFLOPS | Progress: (16/20) | 7.76 s
    [Task  2/25]  Current/Best:   19.49/  20.82 GFLOPS | Progress: (20/20) | 9.37 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/  10.73 GFLOPS | Progress: (4/20) | 5.95 s
    [Task  3/25]  Current/Best:   15.23/  16.81 GFLOPS | Progress: (8/20) | 7.90 s
    [Task  3/25]  Current/Best:   14.92/  16.81 GFLOPS | Progress: (12/20) | 9.65 s
    [Task  3/25]  Current/Best:    7.21/  23.64 GFLOPS | Progress: (16/20) | 11.61 s
    [Task  3/25]  Current/Best:   11.21/  23.64 GFLOPS | Progress: (20/20) | 16.17 s Done.
+
    [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  4/25]  Current/Best:    9.35/  20.20 GFLOPS | Progress: (4/20) | 2.47 s
    [Task  4/25]  Current/Best:    6.82/  20.20 GFLOPS | Progress: (8/20) | 6.85 s
    [Task  4/25]  Current/Best:   21.97/  21.97 GFLOPS | Progress: (12/20) | 11.37 s
    [Task  4/25]  Current/Best:   16.65/  21.97 GFLOPS | Progress: (16/20) | 13.63 s
    [Task  4/25]  Current/Best:   13.27/  21.97 GFLOPS | Progress: (20/20) | 15.66 s Done.
+
    [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  5/25]  Current/Best:    9.75/  10.26 GFLOPS | Progress: (4/20) | 2.66 s
    [Task  5/25]  Current/Best:   11.71/  13.12 GFLOPS | Progress: (8/20) | 4.71 s
    [Task  5/25]  Current/Best:    9.72/  17.90 GFLOPS | Progress: (12/20) | 7.72 s
    [Task  5/25]  Current/Best:   11.73/  22.65 GFLOPS | Progress: (16/20) | 9.15 s
    [Task  5/25]  Current/Best:   11.84/  22.65 GFLOPS | Progress: (20/20) | 11.06 s Done.
+
    [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  6/25]  Current/Best:   12.09/  20.03 GFLOPS | Progress: (4/20) | 4.07 s
    [Task  6/25]  Current/Best:   18.76/  20.03 GFLOPS | Progress: (8/20) | 5.85 s
    [Task  6/25]  Current/Best:   13.21/  20.03 GFLOPS | Progress: (12/20) | 7.79 s
    [Task  6/25]  Current/Best:   19.88/  20.03 GFLOPS | Progress: (16/20) | 10.06 s
    [Task  6/25]  Current/Best:    3.76/  20.03 GFLOPS | Progress: (20/20) | 12.58 s Done.
+
    [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  7/25]  Current/Best:   11.11/  12.16 GFLOPS | Progress: (4/20) | 3.76 s
    [Task  7/25]  Current/Best:   19.77/  21.18 GFLOPS | Progress: (8/20) | 5.29 s
    [Task  7/25]  Current/Best:   15.96/  21.18 GFLOPS | Progress: (12/20) | 7.21 s
    [Task  7/25]  Current/Best:   12.16/  21.18 GFLOPS | Progress: (16/20) | 9.26 s
    [Task  7/25]  Current/Best:    6.41/  21.64 GFLOPS | Progress: (20/20) | 11.75 s Done.
+
    [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  8/25]  Current/Best:   10.30/  14.23 GFLOPS | Progress: (4/20) | 2.98 s
    [Task  8/25]  Current/Best:    9.77/  14.23 GFLOPS | Progress: (8/20) | 7.80 s
    [Task  8/25]  Current/Best:   13.25/  14.23 GFLOPS | Progress: (12/20) | 14.08 s
    [Task  8/25]  Current/Best:   19.02/  19.02 GFLOPS | Progress: (16/20) | 16.17 s
    [Task  8/25]  Current/Best:   19.84/  19.84 GFLOPS | Progress: (20/20) | 22.76 s Done.
+
    [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task  9/25]  Current/Best:   14.16/  15.41 GFLOPS | Progress: (4/20) | 12.05 s
    [Task  9/25]  Current/Best:   23.50/  23.50 GFLOPS | Progress: (8/20) | 13.84 s
    [Task  9/25]  Current/Best:    8.25/  23.50 GFLOPS | Progress: (12/20) | 16.23 s
    [Task  9/25]  Current/Best:   17.87/  23.50 GFLOPS | Progress: (16/20) | 18.92 s
    [Task  9/25]  Current/Best:    9.07/  23.50 GFLOPS | Progress: (20/20) | 26.72 s
    [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 10/25]  Current/Best:   18.51/  18.51 GFLOPS | Progress: (4/20) | 2.61 s
    [Task 10/25]  Current/Best:   15.60/  18.51 GFLOPS | Progress: (8/20) | 4.21 s
    [Task 10/25]  Current/Best:   12.70/  19.09 GFLOPS | Progress: (12/20) | 5.76 s
    [Task 10/25]  Current/Best:   19.08/  20.28 GFLOPS | Progress: (16/20) | 6.87 s
    [Task 10/25]  Current/Best:    8.96/  20.28 GFLOPS | Progress: (20/20
 ) | 8.44 s Done.
+
    [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 11/25]  Current/Best:   11.22/  17.95 GFLOPS | Progress: (4/20) | 3.44 s
    [Task 11/25]  Current/Best:   16.17/  17.95 GFLOPS | Progress: (8/20) | 6.18 s
    [Task 11/25]  Current/Best:   17.92/  17.95 GFLOPS | Progress: (12/20) | 8.26 s
    [Task 11/25]  Current/Best:   13.50/  20.98 GFLOPS | Progress: (16/20) | 11.07 s
    [Task 11/25]  Current/Best:   19.42/  21.58 GFLOPS | Progress: (20/20) | 13.12 s Done.
+
    [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 12/25]  Current/Best:    7.77/  17.99 GFLOPS | Progress: (4/20) | 5.47 s
    [Task 12/25]  Current/Best:    5.24/  17.99 GFLOPS | Progress: (8/20) | 9.20 s
    [Task 12/25]  Current/Best:   18.95/  18.95 GFLOPS | Progress: (12/20) | 11.20 s
    [Task 12/25]  Current/Best:   13.32/  18.95 GFLOPS | Progress: (16/20) | 13.99 s
    [Task 12/25]  Current/Best:   15.13/  18.97 GFLOPS | Progress: (20/20) | 15.89 s Done.
+
    [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 13/25]  Current/Best:    8.93/  17.27 GFLOPS | Progress: (4/20) | 3.72 s
    [Task 13/25]  Current/Best:   16.03/  20.72 GFLOPS | Progress: (8/20) | 6.17 s
    [Task 13/25]  Current/Best:   19.49/  21.62 GFLOPS | Progress: (12/20) | 9.13 s
    [Task 13/25]  Current/Best:   12.21/  21.62 GFLOPS | Progress: (16/20) | 12.57 s
    [Task 13/25]  Current/Best:   18.70/  21.62 GFLOPS | Progress: (20/20) | 14.83 s Done.
+
    [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 14/25]  Current/Best:   13.67/  13.67 GFLOPS | Progress: (4/20) | 3.43 s
    [Task 14/25]  Current/Best:    6.11/  13.67 GFLOPS | Progress: (8/20) | 5.65 s
    [Task 14/25]  Current/Best:   20.77/  20.77 GFLOPS | Progress: (12/20) | 8.25 s
    [Task 14/25]  Current/Best:   17.16/  20.77 GFLOPS | Progress: (16/20) | 9.91 s Done.
+
    [Task 14/25]  Current/Best:   16.93/  20.77 GFLOPS | Progress: (20/20) | 11.71 s
    [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 15/25]  Current/Best:   16.17/  17.51 GFLOPS | Progress: (4/20) | 2.81 s
    [Task 15/25]  Current/Best:   14.10/  17.95 GFLOPS | Progress: (8/20) | 4.17 s
    [Task 15/25]  Current/Best:   10.36/  22.31 GFLOPS | Progress: (12/20) | 6.25 s
    [Task 15/25]  Current/Best:   20.36/  22.31 GFLOPS | Progress: (16/20) | 9.16 s
    [Task 15/25]  Current/Best:    9.37/  22.31 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:   20.21/  20.21 GFLOPS | Progress: (4/20) | 3.05 s
    [Task 16/25]  Current/Best:    3.03/  20.21 GFLOPS | Progress: (8/20) | 4.68 s
    [Task 16/25]  Current/Best:   19.00/  20.21 GFLOPS | Progress: (12/20) | 5.91 s
    [Task 16/25]  Current/Best:   17.77/  20.21 GFLOPS | Progress: (16/20) |
  7.26 s
    [Task 16/25]  Current/Best:    9.98/  21.78 GFLOPS | Progress: (20/20) | 9.32 s Done.
+
    [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 17/25]  Current/Best:   13.93/  18.27 GFLOPS | Progress: (4/20) | 4.79 s
    [Task 17/25]  Current/Best:   14.46/  23.10 GFLOPS | Progress: (8/20) | 7.60 s
    [Task 17/25]  Current/Best:   17.42/  23.10 GFLOPS | Progress: (12/20) | 9.64 s
    [Task 17/25]  Current/Best:   16.67/  23.10 GFLOPS | Progress: (16/20) | 11.76 s
    [Task 17/25]  Current/Best:   10.03/  23.10 GFLOPS | Progress: (20/20) | 13.90 s Done.
+
    [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 18/25]  Current/Best:   11.43/  17.97 GFLOPS | Progress: (4/20) | 3.78 s
    [Task 18/25]  Current/Best:   10.60/  19.15 GFLOPS | Progress: (8/20) | 7.24 s
    [Task 18/25]  Current/Best:   19.25/  19.25 GFLOPS | Progress: (12/20) | 9.20 s
    [Task 18/25]  Current/Best:    9.90/  19.25 GFLOPS | Progress: (16/20) | 12.82 s
    [Task 18/25]  Current/Best:   20.70/  20.70 GFLOPS | Progress: (20/20) | 14.33 s Done.
+
    [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 19/25]  Current/Best:    6.76/  20.18 GFLOPS | Progress: (4/20) | 6.23 s
    [Task 19/25]  Current/Best:    2.69/  20.18 GFLOPS | Progress: (8/20) | 9.50 s
    [Task 19/25]  Current/Best:   19.28/  20.89 GFLOPS | Progress: (12/20) | 12.27 s
    [Task 19/25]  Current/Best:   15.16/  20.89 GFLOPS | Progress: (16/20) | 15.06 s
    [Task 19/25]  Current/Best:    2.69/  22.49 GFLOPS | Progress: (20/20) | 17.87 s Done.
+
    [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 20/25]  Current/Best:    9.59/  15.09 GFLOPS | Progress: (4/20) | 3.39 s Done.
      Done.
-
    [Task 20/25]  Current/Best:   10.12/  15.58 GFLOPS | Progress: (8/20) | 6.64 s
    [Task 20/25]  Current/Best:    2.36/  16.43 GFLOPS | Progress: (12/20) | 10.42 s
    [Task 20/25]  Current/Best:   12.59/  16.43 GFLOPS | Progress: (16/20) | 14.05 s
    [Task 20/25]  Current/Best:   12.43/  22.65 GFLOPS | Progress: (20/20) | 16.11 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.53/  19.60 GFLOPS | Progress: (4/20) | 3.15 s
    [Task 21/25]  Current/Best:   14.86/  19.60 GFLOPS | Progress: (8/20) | 4.70 s
    [Task 21/25]  Current/Best:    1.64/  19.60 GFLOPS | Progress: (12/20) | 6.81 s
    [Task 21/25]  Current/Best:   18.46/  19.60 GFLOPS | Progress: (16/20) | 10.18 s
    [Task 21/25]  Current/Best:    4.53/  19.60 GFLOPS | Progress: (20/20) | 17.15 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.75/  18.89 GFLOPS | Progress: (4/20
 ) | 2.63 s
    [Task 22/25]  Current/Best:    8.91/  21.96 GFLOPS | Progress: (8/20) | 4.59 s
    [Task 22/25]  Current/Best:   20.36/  21.96 GFLOPS | Progress: (12/20) | 6.86 s
    [Task 22/25]  Current/Best:   15.67/  21.96 GFLOPS | Progress: (16/20) | 8.88 s
    [Task 22/25]  Current/Best:   14.29/  21.96 GFLOPS | Progress: (20/20) | 10.50 s Done.
-
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   18.05/  21.20 GFLOPS | Progress: (4/20) | 3.20 s
    [Task 23/25]  Current/Best:   15.05/  22.03 GFLOPS | Progress: (8/20) | 6.48 s
    [Task 23/25]  Current/Best:   21.34/  22.03 GFLOPS | Progress: (12/20) | 8.25 s
    [Task 23/25]  Current/Best:    6.66/  22.03 GFLOPS | Progress: (16/20) | 15.03 s
    [Task 23/25]  Current/Best:    8.18/  22.03 GFLOPS | Progress: (20/20) | 19.13 s Done.
-
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    9.10/   9.10 GFLOPS | Progress: (4/20) | 11.80 s
    [Task 24/25]  Current/Best:    2.13/   9.10 GFLOPS | Progress: (8/20) | 22.84 s
    [Task 24/25]  Current/Best:    4.49/   9.10 GFLOPS | Progress: (12/20) | 34.37 s Done.
-
    [Task 24/25]  Current/Best:    5.95/   9.10 GFLOPS | Progress: (16/20) | 39.61 s
    [Task 24/25]  Current/Best:    3.40/   9.10 GFLOPS | Progress: (20/20) | 45.51 s Done.
-
    [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 25/25]  Current/Best:    1.58/   2.81 GFLOPS | Progress: (4/20) | 11.55 s
    [Task 25/25]  Current/Best:    6.16/   8.47 GFLOPS | Progress: (8/20) | 22.83 s
    [Task 25/25]  Current/Best:    6.12/   8.47 GFLOPS | Progress: (12/20) | 34.27 s
    [Task 25/25]  Current/Best:    6.02/   8.71 GFLOPS | Progress: (16/20) | 35.97 s
    [Task 25/25]  Current/Best:    2.91/   9.48 GFLOPS | Progress: (20/20) | 46.69 s
+
    [Task 20/25]  Current/Best:   10.29/  15.09 GFLOPS | Progress: (8/20) | 6.89 s
    [Task 20/25]  Current/Best:    2.32/  16.71 GFLOPS | Progress: (12/20) | 10.82 s
    [Task 20/25]  Current/Best:   12.39/  16.71 GFLOPS | Progress: (16/20) | 14.48 s
    [Task 20/25]  Current/Best:   13.48/  21.64 GFLOPS | Progress: (20/20) | 16.61 s
    [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 21/25]  Current/Best:    6.39/  17.69 GFLOPS | Progress: (4/20) | 3.33 s
    [Task 21/25]  Current/Best:   14.40/  17.69 GFLOPS | Progress: (8/20) | 4.89 s
    [Task 21/25]  Current/Best:    1.61/  17.69 GFLOPS | Progress: (12/20) | 7.08 s
    [Task 21/25]  Current/Best:   18.07/  18.07 GFLOPS | Progress: (16/20) | 10.62 s
    [Task 21/25]  Current/Best:    4.46/  18.07 GFLOPS | Progress: (20/20) | 17.86 s
    [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 22/25]  Current/Best:    2.70/  16.98 GFLOPS | Progress: (4/20
 ) | 2.78 s
    [Task 22/25]  Current/Best:    9.16/  21.16 GFLOPS | Progress: (8/20) | 4.78 s
    [Task 22/25]  Current/Best:   19.61/  21.16 GFLOPS | Progress: (12/20) | 7.14 s
    [Task 22/25]  Current/Best:   15.10/  21.16 GFLOPS | Progress: (16/20) | 9.22 s
    [Task 22/25]  Current/Best:   14.80/  21.16 GFLOPS | Progress: (20/20) | 10.99 s Done.
+
    [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 23/25]  Current/Best:   17.32/  20.04 GFLOPS | Progress: (4/20) | 3.37 s
    [Task 23/25]  Current/Best:   16.09/  20.04 GFLOPS | Progress: (8/20) | 6.75 s
    [Task 23/25]  Current/Best:   20.70/  21.11 GFLOPS | Progress: (12/20) | 8.58 s
    [Task 23/25]  Current/Best:    6.20/  21.11 GFLOPS | Progress: (16/20) | 15.80 s
    [Task 23/25]  Current/Best:    7.34/  21.11 GFLOPS | Progress: (20/20) | 20.07 s Done.
+
    [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
    [Task 24/25]  Current/Best:    8.64/   8.64 GFLOPS | Progress: (4/20) | 11.91 s
    [Task 24/25]  Current/Best:    2.13/   8.64 GFLOPS | Progress: (8/20) | 22.99 s
    [Task 24/25]  Current/Best:    3.96/   8.64 GFLOPS | Progress: (12/20) | 34.58 s Done.
+
    [Task 24/25]  Current/Best:    7.02/   8.64 GFLOPS | Progress: (16/20) | 40.04 s
    [Task 24/25]  Current/Best:    3.30/   8.90 GFLOPS | Progress: (20/20) | 46.01 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) | 11.66 s
    [Task 25/25]  Current/Best:    5.80/   7.46 GFLOPS | Progress: (8/20) | 22.97 s
    [Task 25/25]  Current/Best:    5.60/   7.46 GFLOPS | Progress: (12/20) | 34.49 s
    [Task 25/25]  Current/Best:    5.69/   9.18 GFLOPS | Progress: (16/20) | 36.45 s
    [Task 25/25]  Current/Best:    2.87/   9.18 GFLOPS | Progress: (20/20) | 47.13 s
 
 
 
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
 
  .. code-block:: none
 
-    optimized: {'mean': 383.3758860499802, 'median': 383.3882426499258, 'std': 0.31093456828347843}
-    unoptimized: {'mean': 495.8759032300077, 'median': 499.2053312498683, 'std': 7.764164250480838}
+    optimized: {'mean': 413.2851679700025, 'median': 413.1391143000087, 'std': 0.6314766786546927}
+    unoptimized: {'mean': 498.4301331699976, 'median': 498.51982829999884, 'std': 0.4806910936114738}
 
 
 
@@ -772,7 +772,7 @@ profiling/benchmarking.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 10 minutes  7.553 seconds)
+   **Total running time of the script:** ( 10 minutes  26.466 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 92e03b39c..fa92d352e 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
 
  .. code-block:: none
 
-    1.2e-07 secs/op
+    1.273e-07 secs/op
 
 
 
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index c8ee457e3..18597c68e 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
 
  .. code-block:: none
 
-    [stage(a, placeholder(a, 0xdc50bb0)), stage(b, placeholder(b, 0x1789af20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+    [stage(a, placeholder(a, 0x20e383a0)), stage(b, placeholder(b, 0x21738130)), 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 [...]
 
 
 
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index f6b00357a..be4df4ed3 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
 
 Computation times
 =================
-**13:17.141** total execution time for **tutorial** files:
+**13:26.059** total execution time for **tutorial** files:
 
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:07.553 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)                 | 10:26.466 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:11.696 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:00.701 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)     | 01:00.087 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:59.456 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:29.983 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)                 | 00:31.843 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:26.199 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)               | 00:25.207 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:00.802 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)       | 00:01.490 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.678 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)                               | 00:00.722 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.134 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.164 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)                           | 00:00.005 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``)                                             | 00:00.002 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)   | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)                             | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
 | :ref:`sphx_glr_tutorial_install.py` (``install.py``)                                     | 00:00.001 | 0.0 MB |
 +------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 1cfaa853f..4cda24632 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
 
  .. code-block:: none
 
-    Numpy running time: 0.000007
+    Numpy running time: 0.000008
     naive: 0.000006
 
 
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vector: 0.000024
+    vector: 0.000025
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                   numpy    7.400050017167814e-06                    1.0
-                   naive    5.8132000000000005e-06    0.7855622578919891
-                parallel              5.8428e-06      0.7895622308558649
-                  vector             2.37836e-05      3.2139782764742155
+                   numpy    8.03192000148556e-06                     1.0
+                   naive    5.818700000000001e-06     0.7244469565090029
+                parallel              6.0602e-06      0.7545144870565349
+                  vector             2.46257e-05      3.0659792422540693
 
 
 
@@ -936,7 +936,7 @@ matrix multiplication.
 
  .. code-block:: none
 
-    Numpy running time: 0.015221
+    Numpy running time: 0.019174
 
 
 
@@ -996,7 +996,7 @@ optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    none: 3.425296
+    none: 3.330907
 
 
 
@@ -1101,7 +1101,7 @@ schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    blocking: 0.297018
+    blocking: 0.332323
 
 
 
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    vectorization: 0.324939
+    vectorization: 0.359443
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    loop permutation: 0.112317
+    loop permutation: 0.124312
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    array packing: 0.105738
+    array packing: 0.108148
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    block caching: 0.097653
+    block caching: 0.110939
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
 
     /workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
       "target_host parameter is going to be deprecated. "
-    parallelization: 0.130493
+    parallelization: 0.146840
     @main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
       attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
       buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
  .. code-block:: none
 
                 Operator                  Timing             Performance
-                    none            3.4252957738                     1.0
-                blocking            0.2970183914      0.0867132098990943
-           vectorization            0.3249389654     0.09486449838447525
-        loop permutation     0.11231713139999999     0.03279049133774399
-           array packing             0.105737908    0.030869716072050354
-           block caching            0.0976527841    0.028509299794471372
-         parallelization            0.1304927843     0.03809679307058269
+                    none            3.3309067194                     1.0
+                blocking     0.33232271850000006     0.09976944612842888
+           vectorization     0.35944334840000003     0.10791156243028834
+        loop permutation     0.12431189620000001     0.03732073776668007
+           array packing     0.10814778759999999     0.03246797245030049
+           block caching     0.11093876620000001    0.033305876010836934
+         parallelization            0.1468397339     0.04408401263378831
 
 
 
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  0.087 seconds)
+   **Total running time of the script:** ( 1 minutes  0.701 seconds)
 
 
 .. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 3f4c547c4..9be6faeba 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-534412896e6d39ee4f830d63370d02e8e5f09050
+648a29a53a641f1e923220600dce9c9215104879
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 1da3d752e..5e71562cd 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:[&#39;truck 0.9266&#39;] left:471 top:83 right:689 bottom:169
 class:[&#39;bicycle 0.9984&#39;] left:111 top:113 right:577 bottom:447
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  1.784 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  5.194 seconds)</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index e2b12772a..72cc1ac67 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;x&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe4bef291-8bb6-4e0d-9e47-a236ea289cb2 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.zipc6ac7d72-b8d6-43eb-9196-08a19b8683b4 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 30bb4fbce..0790d301b 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,12 +432,12 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip&quot; to /workspace/.oneflow/flowvision_cache/resnet18.zip
 
   0%|          | 0.00/41.5M [00:00&lt;?, ?B/s]
- 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 50.1MB/s]
- 39%|###8      | 16.0M/41.5M [00:00&lt;00:00, 56.7MB/s]
- 58%|#####7    | 24.0M/41.5M [00:00&lt;00:00, 44.8MB/s]
- 77%|#######7  | 32.1M/41.5M [00:00&lt;00:00, 54.5MB/s]
- 95%|#########4| 39.3M/41.5M [00:00&lt;00:00, 59.9MB/s]
-100%|##########| 41.5M/41.5M [00:00&lt;00:00, 54.1MB/s]
+ 19%|#9        | 7.99M/41.5M [00:00&lt;00:00, 65.3MB/s]
+ 35%|###4      | 14.3M/41.5M [00:00&lt;00:00, 63.1MB/s]
+ 56%|#####5    | 23.1M/41.5M [00:00&lt;00:00, 75.0MB/s]
+ 77%|#######7  | 32.0M/41.5M [00:00&lt;00:00, 65.8MB/s]
+ 93%|#########2| 38.5M/41.5M [00:00&lt;00:00, 63.1MB/s]
+100%|##########| 41.5M/41.5M [00:00&lt;00:00, 63.5MB/s]
 </pre></div>
 </div>
 </div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index a036a1c82..6587756ae 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,10 +414,8 @@ 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]
-  9%|9         | 4.23M/44.7M [00:00&lt;00:00, 43.9MB/s]
- 19%|#8        | 8.42M/44.7M [00:00&lt;00:00, 41.8MB/s]
- 71%|#######1  | 31.8M/44.7M [00:00&lt;00:00, 132MB/s]
-100%|##########| 44.7M/44.7M [00:00&lt;00:00, 126MB/s]
+ 42%|####1     | 18.6M/44.7M [00:00&lt;00:00, 195MB/s]
+100%|##########| 44.7M/44.7M [00:00&lt;00:00, 236MB/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 e23db7772..c8c0fcf55 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
 desk (score = 0.00019)
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  5.388 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  4.001 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 d1b07d799..1e3e6ce8f 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.291</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:11.405</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -335,44 +335,44 @@
 <col style="width: 8%" />
 </colgroup>
 <tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:05.388</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:05.194</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:01.784</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:04.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:38.254</p></td>
+<td><p>00:40.080</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:28.271</p></td>
+<td><p>00:28.599</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.576</p></td>
+<td><p>00:26.121</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.228</p></td>
+<td><p>00:25.053</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>00:21.777</p></td>
+<td><p>00:23.551</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>00:18.872</p></td>
+<td><p>00:19.792</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:15.786</p></td>
+<td><p>00:16.508</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>00:02.356</p></td>
+<td><p>00:02.504</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 01507b59e..a1a36c1e0 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  15.0291      14.4506      19.6940      14.1347       1.5876
+  16.2976      16.2951      16.4644      16.1974       0.0772
 </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 09be525e7..6ad695d20 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,14 @@ be unstable.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth&quot; to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
 
   0%|          | 0.00/170M [00:00&lt;?, ?B/s]
- 11%|#1        | 19.1M/170M [00:00&lt;00:00, 200MB/s]
- 27%|##6       | 45.3M/170M [00:00&lt;00:00, 244MB/s]
- 41%|####      | 68.9M/170M [00:00&lt;00:00, 246MB/s]
- 56%|#####5    | 94.7M/170M [00:00&lt;00:00, 255MB/s]
- 70%|#######   | 119M/170M [00:00&lt;00:00, 251MB/s]
- 84%|########4 | 143M/170M [00:00&lt;00:00, 249MB/s]
- 98%|#########8| 167M/170M [00:00&lt;00:00, 229MB/s]
-100%|##########| 170M/170M [00:00&lt;00:00, 233MB/s]
+  9%|9         | 16.0M/170M [00:00&lt;00:00, 168MB/s]
+ 23%|##3       | 39.1M/170M [00:00&lt;00:00, 212MB/s]
+ 36%|###6      | 61.8M/170M [00:00&lt;00:00, 224MB/s]
+ 51%|#####     | 86.0M/170M [00:00&lt;00:00, 236MB/s]
+ 67%|######6   | 113M/170M [00:00&lt;00:00, 253MB/s]
+ 82%|########1 | 139M/170M [00:00&lt;00:00, 260MB/s]
+ 97%|#########7| 166M/170M [00:00&lt;00:00, 265MB/s]
+100%|##########| 170M/170M [00:00&lt;00:00, 249MB/s]
 /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
   for i in range(dim)
 /usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the &#39;trunc&#39; function NOT &#39;floor&#39;). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode=&#39;trunc&#39;), or for actual floor division, use torch.div(a, b, rounding_mode=&#39;floor&#39;).
@@ -538,7 +538,7 @@ torchvision rcnn models.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  45.466 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  5.033 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 acca35774..d2a171e8b 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,7 @@ training. Other models require a full post training calibration.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: &quot;https://download.pytorch.org/models/mobilenet_v2-b0353104.pth&quot; to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
 
   0%|          | 0.00/13.6M [00:00&lt;?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00&lt;00:00, 190MB/s]
+100%|##########| 13.6M/13.6M [00:00&lt;00:00, 170MB/s]
 </pre></div>
 </div>
 </div>
@@ -569,7 +569,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  87.6873      87.5938      89.7886      87.3683       0.3204
+  90.3629      90.2958      91.0122      90.0396       0.2039
 </pre></div>
 </div>
 <div class="admonition note">
@@ -608,7 +608,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
 <div class="section" id="deploy-a-quantized-tflite-model">
 <h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
 <p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  7.082 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  12.091 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 afd6f7680..c3b1b5e2d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  115.6665     115.1263     127.4992     114.3867      1.6262
+  121.3593     121.3275     123.8800     120.6025      0.4172
 </pre></div>
 </div>
 <div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
 </ul>
 </div></blockquote>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  49.682 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  53.523 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 1eb605f3b..a5344f3f1 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
   DeprecationWarning,
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  28.696 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  22.251 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 7d2832d89..106cb80ed 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,25 +441,23 @@ to your device.</p>
 Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
 
   0%|          | 0/132723 [00:00&lt;?, ?KB/s]
-  4%|3         | 5229/132723 [00:00&lt;00:02, 52283.69KB/s]
-  9%|9         | 12562/132723 [00:00&lt;00:01, 64659.12KB/s]
- 15%|#5        | 19947/132723 [00:00&lt;00:01, 68853.09KB/s]
- 21%|##        | 27427/132723 [00:00&lt;00:01, 71189.63KB/s]
- 26%|##6       | 34856/132723 [00:00&lt;00:01, 72305.71KB/s]
- 32%|###1      | 42265/132723 [00:00&lt;00:01, 72909.44KB/s]
- 37%|###7      | 49663/132723 [00:00&lt;00:01, 73256.62KB/s]
- 43%|####3     | 57116/132723 [00:00&lt;00:01, 73660.25KB/s]
- 49%|####8     | 64483/132723 [00:00&lt;00:00, 73539.73KB/s]
- 54%|#####4    | 71838/132723 [00:01&lt;00:00, 71950.11KB/s]
- 60%|#####9    | 79293/132723 [00:01&lt;00:00, 72725.77KB/s]
- 65%|######5   | 86748/132723 [00:01&lt;00:00, 73273.82KB/s]
- 71%|#######   | 94189/132723 [00:01&lt;00:00, 73613.48KB/s]
- 77%|#######6  | 101584/132723 [00:01&lt;00:00, 73713.21KB/s]
- 82%|########2 | 109013/132723 [00:01&lt;00:00, 73881.66KB/s]
- 88%|########7 | 116485/132723 [00:01&lt;00:00, 74130.36KB/s]
- 93%|#########3| 123997/132723 [00:01&lt;00:00, 74426.42KB/s]
- 99%|#########9| 131606/132723 [00:01&lt;00:00, 74923.44KB/s]
-100%|##########| 132723/132723 [00:01&lt;00:00, 72803.15KB/s]
+  5%|4         | 6487/132723 [00:00&lt;00:01, 64862.95KB/s]
+ 11%|#1        | 14941/132723 [00:00&lt;00:01, 76422.53KB/s]
+ 18%|#7        | 23357/132723 [00:00&lt;00:01, 79943.89KB/s]
+ 24%|##4       | 31917/132723 [00:00&lt;00:01, 82165.54KB/s]
+ 30%|###       | 40134/132723 [00:00&lt;00:01, 71533.21KB/s]
+ 37%|###6      | 48619/132723 [00:00&lt;00:01, 75653.08KB/s]
+ 42%|####2     | 56356/132723 [00:00&lt;00:01, 68794.80KB/s]
+ 49%|####8     | 64760/132723 [00:00&lt;00:00, 73113.54KB/s]
+ 55%|#####5    | 73149/132723 [00:00&lt;00:00, 76218.11KB/s]
+ 62%|######1   | 81651/132723 [00:01&lt;00:00, 78783.77KB/s]
+ 68%|######7   | 90172/132723 [00:01&lt;00:00, 80672.12KB/s]
+ 74%|#######4  | 98333/132723 [00:01&lt;00:00, 80520.07KB/s]
+ 80%|########  | 106450/132723 [00:01&lt;00:00, 77082.61KB/s]
+ 86%|########6 | 114695/132723 [00:01&lt;00:00, 78624.16KB/s]
+ 93%|#########2| 123186/132723 [00:01&lt;00:00, 80453.24KB/s]
+ 99%|#########9| 131750/132723 [00:01&lt;00:00, 81974.25KB/s]
+100%|##########| 132723/132723 [00:01&lt;00:00, 77717.08KB/s]
 </pre></div>
 </div>
 <p>Create TVM runtime and do inference
@@ -502,7 +500,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
 <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  31.356 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  42.544 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 c221f907d..cec0f90d9 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:53.919</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:32.847</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 86%" />
@@ -336,39 +336,39 @@
 </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>02:45.466</p></td>
+<td><p>03:05.033</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>02:31.356</p></td>
+<td><p>02:42.544</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>01:49.682</p></td>
+<td><p>01:53.523</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>01:28.696</p></td>
+<td><p>01:22.251</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>01:07.082</p></td>
+<td><p>01:12.091</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>00:28.655</p></td>
+<td><p>00:31.474</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:21.608</p></td>
+<td><p>00:23.329</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.367</p></td>
+<td><p>00:22.595</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
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 1d3f76238..983adf277 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
 <span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0071ef9f-14bf-49ab-a4ab-4c36f8f23624 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.zip72f9f933-de15-44b4-8a4a-63b292c3a6bf from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
 </pre></div>
 </div>
 <p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 389e8c2f2..c326df325 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.025</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:43.777</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="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>00:36.989</p></td>
+<td><p>00:40.426</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>00:02.132</p></td>
+<td><p>00:02.344</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>00:00.897</p></td>
+<td><p>00:00.999</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 8c8ed6639..83c4b5dbf 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6683us [6683us] (46.14%; 46.14%)
-FoldScaleAxis: 7800us [5us] (53.86%; 53.86%)
-        FoldConstant: 7795us [1639us] (53.82%; 99.93%)
-                InferType: 6156us [6156us] (42.51%; 78.98%)
+InferType: 7102us [7102us] (46.63%; 46.63%)
+FoldScaleAxis: 8129us [7us] (53.37%; 53.37%)
+        FoldConstant: 8122us [1696us] (53.32%; 99.91%)
+                InferType: 6426us [6426us] (42.19%; 79.11%)
 </pre></div>
 </div>
 </div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6197us [6197us] (44.38%; 44.38%)
-FoldScaleAxis: 7765us [4us] (55.62%; 55.62%)
-        FoldConstant: 7761us [1680us] (55.59%; 99.95%)
-                InferType: 6081us [6081us] (43.55%; 78.35%)
+InferType: 6542us [6542us] (43.06%; 43.06%)
+FoldScaleAxis: 8651us [5us] (56.94%; 56.94%)
+        FoldConstant: 8645us [1683us] (56.91%; 99.94%)
+                InferType: 6963us [6963us] (45.83%; 80.54%)
 </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 0deea65b7..508da4024 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Convolution: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.309120 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 38.524817 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 ab5d2c763..55cb2892d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
     <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.021444 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.179388 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 90d4e2d14..be124a490 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Baseline: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.015417
-Baseline: 3.434214
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019202
+Baseline: 3.320618
 </pre></div>
 </div>
 <p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt1: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296426
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.324964
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt2: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.326353
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.352623
 </pre></div>
 </div>
 <p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt3: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.111500
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.125868
 </pre></div>
 </div>
 <p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt4: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.106720
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109626
 </pre></div>
 </div>
 <p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt5: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.099107
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112154
 </pre></div>
 </div>
 <p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Opt6: </span><span class="si">%f</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.130604
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147503
 </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 e9ad4f40c..4b050f15f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:32.968</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.964</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:30.751</p></td>
+<td><p>00:32.727</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>00:01.197</p></td>
+<td><p>00:01.263</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>00:01.019</p></td>
+<td><p>00:00.974</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 6e2acccb3..11596a963 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:08.259</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:11.346</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -336,27 +336,27 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:16.114</p></td>
+<td><p>03:20.911</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>01:20.012</p></td>
+<td><p>01:24.704</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>00:45.813</p></td>
+<td><p>00:48.404</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>00:29.355</p></td>
+<td><p>00:19.047</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>00:08.524</p></td>
+<td><p>00:09.216</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>00:08.442</p></td>
+<td><p>00:09.063</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 b974f666a..f6ef2165a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,484 +491,65 @@ 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; = 28;
-  allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
-  allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
-  allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
-  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope=&quot;local&quot;, align=32)[0] = 0f32
+  attr [IterVar(blockIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;blockIdx.x&quot;)] &quot;thread_extent&quot; = 32;
+  allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+  allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+  allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+  attr [IterVar(threadIdx.x: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392 {
+    conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope=&quot;local&quot;, align=4)[0] = 0f32
     conv2d_nchw_1[1] = 0f32
-    conv2d_nchw_1[2] = 0f32
-    conv2d_nchw_1[3] = 0f32
-    conv2d_nchw_1[4] = 0f32
-    conv2d_nchw_1[5] = 0f32
-    conv2d_nchw_1[6] = 0f32
-    conv2d_nchw_1[7] = 0f32
-    conv2d_nchw_1[8] = 0f32
-    conv2d_nchw_1[9] = 0f32
-    conv2d_nchw_1[10] = 0f32
-    conv2d_nchw_1[11] = 0f32
-    conv2d_nchw_1[12] = 0f32
-    conv2d_nchw_1[13] = 0f32
-    for (rc.outer.outer: int32, 0, 64) {
-      for (ry.outer.outer: int32, 0, 3) {
-        let cse_var_2: int32 = (rc.outer.outer*72)
-        let cse_var_1: int32 = (ry.outer.outer*3)
-         {
-          attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64 {
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope=&quot;shared&quot;)[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1*4), 9))) &amp;&amp; (floormod((threadIdx.x_1*4), 9) &lt; 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) +  [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 1), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 1), 9) &lt; 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 2), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 2), 9) &lt; 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
-            }
-            if @tir.likely((threadIdx.x_1 &lt; 18), dtype=bool) {
-              pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 &lt;= (ry.outer.outer + floormod(blockIdx.x, 7))) &amp;&amp; ((ry.outer.outer + floormod(blockIdx.x, 7)) &lt; 8)) &amp;&amp; (1 &lt;= floormod(((threadIdx.x_1*4) + 3), 9))) &amp;&amp; (floormod(((threadIdx.x_1*4) + 3), 9) &lt; 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
-            }
-          }
-          attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
-          attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 64;
-          kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
-          conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
-          conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+    for (rc.outer.outer: int32, 0, 32) {
+      let cse_var_2: int32 = (rc.outer.outer*784)
+      let cse_var_1: int32 = (rc.outer.outer*144)
+       {
+        attr [IterVar(threadIdx.x_1: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope=&quot;shared&quot;)[threadIdx.x_1] = @tir.if_then_else(((((9 &lt;= floormod(threadIdx.x_1, 81)) &amp;&amp; (floormod(threadIdx.x_1, 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod(threadIdx.x_1, 9))) &amp;&amp; (floormod(threadIdx.x_1, 9) &lt; 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 68), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 68), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 5), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 5), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 55), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 55), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 1), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 1), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+        attr [IterVar(threadIdx.x_1, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        if @tir.likely((threadIdx.x_1 &lt; 120), dtype=bool) {
+          pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 &lt;= floormod((threadIdx.x_1 + 42), 81)) &amp;&amp; (floormod((threadIdx.x_1 + 42), 81) &lt; 72)) &amp;&amp; (1 &lt;= floormod((threadIdx.x_1 + 6), 9))) &amp;&amp; (floormod((threadIdx.x_1 + 6), 9) &lt; 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+        }
+        attr [IterVar(threadIdx.x_2: int32, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope=&quot;shared&quot;)[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 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; = 392;
+        kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+        attr [IterVar(threadIdx.x_2, (nullptr), &quot;ThreadIndex&quot;, &quot;threadIdx.x&quot;)] &quot;thread_extent&quot; = 392;
+        if @tir.likely((threadIdx.x_2 &lt; 344), dtype=bool) {
+          kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+        }
+        for (rc.outer.inner: int32, 0, 16) {
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9))]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1152)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1153)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 2)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1154)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 3)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1155)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 4)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1156)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 5)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1157)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 6)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1158)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 7)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1159)]))
+          conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 8)]))
+          conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*9)) + 1160)]))
         }
       }
     }
-    for (i1.inner: int32, 0, 2) {
-      for (i3.inner: int32, 0, 7) {
-        compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
-      }
-    }
+    compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
+    compute[(((blockIdx.x*784) + threadIdx.x) + 392)] = max((conv2d_nchw_1[1] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 49)) + 8)]), 0f32)
   }
 }
 </pre></div>
@@ -1004,7 +585,7 @@ 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: 0.359 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.276 ms
 </pre></div>
 </div>
 </div>
@@ -1034,35 +615,35 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
 conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
 conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
 conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
 conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
 conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
 conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
 conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
 conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_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=16)
 conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
 conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
 conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
 s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
 compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
 compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
 compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
 compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
 compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
 compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
 s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
 s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1082,14 +663,14 @@ 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=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
 s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
 pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
 s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
 s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis(&quot;threadIdx.x&quot;))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;auto_unroll_max_step&quot;, 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, &quot;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:
@@ -1107,431 +688,52 @@ CUDA source code:
   #define int64_t long long
   #define uint64_t unsigned long long
 #endif
-extern &quot;C&quot; __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
-  float conv2d_nchw[14];
-  __shared__ float pad_temp_shared[72];
-  __shared__ float kernel_shared[3072];
+extern &quot;C&quot; __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+  float conv2d_nchw[2];
+  __shared__ float pad_temp_shared[1296];
+  __shared__ float kernel_shared[2304];
   conv2d_nchw[0] = 0.000000e+00f;
   conv2d_nchw[1] = 0.000000e+00f;
-  conv2d_nchw[2] = 0.000000e+00f;
-  conv2d_nchw[3] = 0.000000e+00f;
-  conv2d_nchw[4] = 0.000000e+00f;
-  conv2d_nchw[5] = 0.000000e+00f;
-  conv2d_nchw[6] = 0.000000e+00f;
-  conv2d_nchw[7] = 0.000000e+00f;
-  conv2d_nchw[8] = 0.000000e+00f;
-  conv2d_nchw[9] = 0.000000e+00f;
-  conv2d_nchw[10] = 0.000000e+00f;
-  conv2d_nchw[11] = 0.000000e+00f;
-  conv2d_nchw[12] = 0.000000e+00f;
-  conv2d_nchw[13] = 0.000000e+00f;
-  for (int rc_outer_outer = 0; rc_outer_outer &lt; 64; ++rc_outer_outer) {
-    for (int ry_outer_outer = 0; ry_outer_outer &lt; 3; ++ry_outer_outer) {
-      __syncthreads();
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) * 4) % 9))) &amp;&amp; (((((int)threadIdx.x) * 4) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 1) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 1) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 2) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 2) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
-      }
-      if (((int)threadIdx.x) &lt; 18) {
-        pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 &lt;= (ry_outer_outer + (((int)blockIdx.x) % 7))) &amp;&amp; ((ry_outer_outer + (((int)blockIdx.x) % 7)) &lt; 8)) &amp;&amp; (1 &lt;= (((((int)threadIdx.x) * 4) + 3) % 9))) &amp;&amp; ((((((int)threadIdx.x) * 4) + 3) % 9) &lt; 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
-      }
-      kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
-      kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
-      kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
-      kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
-      kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
-      kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
-      kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
-      kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
-      kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
-      kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
-      kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
-      kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
-      kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
-      kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
-      kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
-      kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
-      kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
-      __syncthreads();
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
-      conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
-      conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+  for (int rc_outer_outer = 0; rc_outer_outer &lt; 32; ++rc_outer_outer) {
+    __syncthreads();
+    pad_temp_shared[((int)threadIdx.x)] = (((((9 &lt;= (((int)threadIdx.x) % 81)) &amp;&amp; ((((int)threadIdx.x) % 81) &lt; 72)) &amp;&amp; (1 &lt;= (((int)threadIdx.x) % 9))) &amp;&amp; ((((int)threadIdx.x) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 &lt;= ((((int)threadIdx.x) + 68) % 81)) &amp;&amp; (((((int)threadIdx.x) + 68) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 5) % 9))) &amp;&amp; (((((int)threadIdx.x) + 5) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+    pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 &lt;= ((((int)threadIdx.x) + 55) % 81)) &amp;&amp; (((((int)threadIdx.x) + 55) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 1) % 9))) &amp;&amp; (((((int)threadIdx.x) + 1) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+    if (((int)threadIdx.x) &lt; 120) {
+      pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 &lt;= ((((int)threadIdx.x) + 42) % 81)) &amp;&amp; (((((int)threadIdx.x) + 42) % 81) &lt; 72)) &amp;&amp; (1 &lt;= ((((int)threadIdx.x) + 6) % 9))) &amp;&amp; (((((int)threadIdx.x) + 6) % 9) &lt; 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
     }
-  }
-  for (int i1_inner = 0; i1_inner &lt; 2; ++i1_inner) {
-    for (int i3_inner = 0; i3_inner &lt; 7; ++i3_inner) {
-      compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+    kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+    kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+    kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 24) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+    kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+    if (((int)threadIdx.x) &lt; 344) {
+      kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+    }
+    __syncthreads();
+    for (int rc_outer_inner = 0; rc_outer_inner &lt; 16; ++rc_outer_inner) {
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9))]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1152)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1153)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 2)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1154)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 3)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1155)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 4)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1156)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 5)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1157)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 6)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1158)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 7)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1159)]));
+      conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 8)]));
+      conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 9)) + 1160)]));
     }
   }
+  compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
+  compute[(((((int)blockIdx.x) * 784) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49)) + 8)]), 0.000000e+00f);
 }
 </pre></div>
 </div>
@@ -1567,7 +769,7 @@ In the example below we resume the status and do more 5 trials.</p>
 Get devices for measurement successfully!
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  16.114 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  20.911 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 596538af8..7b55e01b5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-   9.8441       9.8558       9.8899       9.7867       0.0429
+   9.7366       9.7491       9.7752       9.6855       0.0377
 </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 e2e65e899..cad03e684 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
 Evaluate inference time cost...
 Execution time summary:
  mean (ms)   median (ms)    max (ms)     min (ms)     std (ms)
-  724.5897     725.6453     725.9321     722.1918      1.6997
+  754.9634     753.7135     758.5801     752.5968      2.5976
 </pre></div>
 </div>
 </div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
 To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
 with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
 </ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  20.012 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  24.704 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 4f2afcc38..034792f6c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,30 +625,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
              placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
              compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
   buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
-  preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
-  for (i0.outer.i1.outer.fused: int32, 0, 128) &quot;parallel&quot; {
-    allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
-      for (nb_j.inner: int32, 0, 2) {
-        for (i.inner.init: int32, 0, 16) {
-          for (j.init: int32, 0, 16) {
-            compute_5: Buffer(compute_4, float32, [512], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+  preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+  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 (nb_j.inner: int32, 0, 2) {
+          for (i.inner.init: int32, 0, 32) {
+            let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+             {
+              compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+              compute_5[(cse_var_1 + 1)] = 0f32
+              compute_5[(cse_var_1 + 2)] = 0f32
+              compute_5[(cse_var_1 + 3)] = 0f32
+              compute_5[(cse_var_1 + 4)] = 0f32
+              compute_5[(cse_var_1 + 5)] = 0f32
+              compute_5[(cse_var_1 + 6)] = 0f32
+              compute_5[(cse_var_1 + 7)] = 0f32
+              compute_5[(cse_var_1 + 8)] = 0f32
+              compute_5[(cse_var_1 + 9)] = 0f32
+              compute_5[(cse_var_1 + 10)] = 0f32
+              compute_5[(cse_var_1 + 11)] = 0f32
+              compute_5[(cse_var_1 + 12)] = 0f32
+              compute_5[(cse_var_1 + 13)] = 0f32
+              compute_5[(cse_var_1 + 14)] = 0f32
+              compute_5[(cse_var_1 + 15)] = 0f32
+            }
           }
-        }
-        for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
-          for (i.inner: int32, 0, 16) {
-            for (j: int32, 0, 16) {
-              let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
-              let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
-              compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+          for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+            for (i.inner: int32, 0, 32) {
+              let cse_var_21: int32 = (elem_idx*16)
+              let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+              let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+              let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
+              let cse_var_17: int32 = (cse_var_19 + 9)
+              let cse_var_16: int32 = (cse_var_19 + 8)
+              let cse_var_15: int32 = (cse_var_19 + 7)
+              let cse_var_14: int32 = (cse_var_19 + 6)
+              let cse_var_13: int32 = (cse_var_19 + 5)
+              let cse_var_12: int32 = (cse_var_19 + 4)
+              let cse_var_11: int32 = (cse_var_19 + 3)
+              let cse_var_10: int32 = (cse_var_19 + 2)
+              let cse_var_9: int32 = (cse_var_19 + 15)
+              let cse_var_8: int32 = (cse_var_19 + 14)
+              let cse_var_7: int32 = (cse_var_19 + 13)
+              let cse_var_6: int32 = (cse_var_19 + 12)
+              let cse_var_5: int32 = (cse_var_19 + 11)
+              let cse_var_4: int32 = (cse_var_19 + 10)
+              let cse_var_3: int32 = (cse_var_19 + 1)
+               {
+                compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+                compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+              }
             }
           }
         }
       }
-      for (i0.inner: int32, 0, 16) {
-        for (i1.inner: int32, 0, 32) {
-          let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
-          compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
-        }
+      for (i0.inner: int32, 0, 64) {
+        let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+        compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
       }
     }
   }
@@ -686,7 +734,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.344 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.706 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 21711d625..946c923df 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.955</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.012</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.920</p></td>
+<td><p>00:45.975</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.021</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
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 d543e3798..731f628ff 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8   GFLOPS: 0.00/0.00       result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 1, 64]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4909501
-No: 9   GFLOPS: 124.23/124.23   result: MeasureResult(costs=(0.0018635354464285713,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0049548149108887, timestamp=1661726143.1269948)      [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
-No: 10  GFLOPS: 0.00/124.23     result: Traceback (most recent call last):
+No: 9   GFLOPS: 80.76/80.76     result: MeasureResult(costs=(0.002866645114285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6300137042999268, timestamp=1661762819.134481)        [(&#39;tile_f&#39;, [-1, 1, 4, 8]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 2, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5072689
+No: 10  GFLOPS: 0.00/80.76      result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 64, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,5092711
-No: 11  GFLOPS: 261.55/261.55   result: MeasureResult(costs=(0.0008851109226519337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7494337558746338, timestamp=1661726144.0495627)      [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
-No: 12  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 11  GFLOPS: 260.38/260.38   result: MeasureResult(costs=(0.0008890813314917127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8063113689422607, timestamp=1661762820.0628433)      [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
+No: 12  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 128, 1, 2]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 256]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 0)],None,183542
-No: 13  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 13  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 4, 8, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 64]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2482196
-No: 14  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 14  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 64, 1, 4]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 2]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10306226
-No: 15  GFLOPS: 5.31/261.55     result: MeasureResult(costs=(0.0436028125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7915902137756348, timestamp=1661726148.5534027)       [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
-No: 16  GFLOPS: 3.36/261.55     result: MeasureResult(costs=(0.0689840615,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.487291097640991, timestamp=1661726149.780498) [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
-No: 17  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 15  GFLOPS: 5.32/260.38     result: MeasureResult(costs=(0.04353801625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8395516872406006, timestamp=1661762824.6931133)      [(&#39;tile_f&#39;, [-1, 2, 2, 8]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 8]), (&#39;tile_ry&#39;, [-1, 1, 1]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,5330964
+No: 16  GFLOPS: 3.34/260.38     result: MeasureResult(costs=(0.06939788649999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6329381465911865, timestamp=1661762825.9308784)        [(&#39;tile_f&#39;, [-1, 8, 4, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 7]), (&#39;tile_x&#39;, [-1, 1, 1, 7]), (&#39;tile_rc&#39;, [-1, 4, 1]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 1]), (&#39;auto_unroll_max_step&#39;, 512), (&#39;unroll_explicit&#39;, 0)],None,2140058
+No: 17  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 142, in build
     res = future.result()
   File &quot;/usr/lib/python3.7/concurrent/futures/_base.py&quot;, line 435, in result
@@ -1950,8 +1950,8 @@ No: 17  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
 TimeoutError
 
         [(&#39;tile_f&#39;, [-1, 2, 2, 1]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 16]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 1)],None,10195251
-No: 18  GFLOPS: 28.15/261.55    result: MeasureResult(costs=(0.008223709142857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2816195487976074, timestamp=1661726160.8156836)       [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
-No: 19  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 18  GFLOPS: 27.06/260.38    result: MeasureResult(costs=(0.0085550076875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3366832733154297, timestamp=1661762837.0193772)    [(&#39;tile_f&#39;, [-1, 4, 8, 4]), (&#39;tile_y&#39;, [-1, 1, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 1, 1]), (&#39;tile_rc&#39;, [-1, 1, 4]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6068603
+No: 19  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 871, in verify_pass
     raise InstantiationError(&quot;Skipped because of invalid gpu kernel&quot;)
 tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel        [(&#39;tile_f&#39;, [-1, 16, 4, 8]), (&#39;tile_y&#39;, [-1, 1, 7, 1]), (&#39;tile_x&#39;, [-1, 7, 1, 1]), (&#39;tile_rc&#39;, [-1, 4, 128]), (&#39;tile_ry&#39;, [-1, 1, 3]), (&#39;tile_rx&#39;, [-1, 1, 3]), (&#39;auto_unroll_max_step&#39;, 0), (&#39;unroll_explicit&#39;, 1)],None,6956993
-No: 20  GFLOPS: 0.00/261.55     result: Traceback (most recent call last):
+No: 20  GFLOPS: 0.00/260.38     result: Traceback (most recent call last):
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 588, in __call__
     func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
   File &quot;/workspace/python/tvm/autotvm/measure/measure_methods.py&quot;, line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
 Best config:
 [(&#39;tile_f&#39;, [-1, 8, 2, 1]), (&#39;tile_y&#39;, [-1, 7, 1, 1]), (&#39;tile_x&#39;, [-1, 1, 7, 1]), (&#39;tile_rc&#39;, [-1, 2, 1]), (&#39;tile_ry&#39;, [-1, 3, 1]), (&#39;tile_rx&#39;, [-1, 3, 1]), (&#39;auto_unroll_max_step&#39;, 1500), (&#39;unroll_explicit&#39;, 0)],None,4264713
 Finish loading 20 records
-Time cost of this operator: 0.001235
+Time cost of this operator: 0.001281
 </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 02ace7506..62389eaba 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
 ########## Build without Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  305.6     98.732   (1, 2, 10, 10, 3)  2       1        [305.6]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       2.958     0.956    (1, 6, 10, 10)     1       1        [2.958]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.967     0.312    (1, 1, 10, 10, 3)  1       1        [0.967]
-Total_time                                    -                                             309.525   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  313.7     98.75    (1, 2, 10, 10, 3)  2       1        [313.7]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       3.018     0.95     (1, 6, 10, 10)     1       1        [3.018]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.952     0.3      (1, 1, 10, 10, 3)  1       1        [0.952]
+Total_time                                    -                                             317.67    -        -                  -       -        -
 </pre></div>
 </div>
 </div>
@@ -640,10 +640,10 @@ Total_time                                    -
 ########## Build with Autotuning ##########
 Node Name                                     Ops                                           Time(us)  Time(%)  Shape              Inputs  Outputs  Measurements(us)
 ---------                                     ---                                           --------  -------  -----              ------  -------  ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  120.875   97.825   (1, 6, 10, 10, 1)  2       1        [120.875]
-tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.751     1.417    (1, 6, 10, 10)     1       1        [1.751]
-tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.937     0.758    (1, 1, 10, 10, 3)  1       1        [0.937]
-Total_time                                    -                                             123.563   -        -                  -       -        -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc  tvmgen_default_fused_nn_contrib_conv2d_NCHWc  118.1     97.732   (1, 6, 10, 10, 1)  2       1        [118.1]
+tvmgen_default_fused_layout_transform_1       tvmgen_default_fused_layout_transform_1       1.788     1.48     (1, 6, 10, 10)     1       1        [1.788]
+tvmgen_default_fused_layout_transform         tvmgen_default_fused_layout_transform         0.952     0.788    (1, 1, 10, 10, 3)  1       1        [0.952]
+Total_time                                    -                                             120.84    -        -                  -       -        -
 </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 ee9d96d57..015606bb1 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
 <a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpwu2s8058/images/random&#39;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&#39;/tmp/tmpgbf7djs4/images/random&#39;
 </pre></div>
 </div>
 </div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
     <span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">&quot;off&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpwu2s8058/images/target contains 8144 images
-/tmp/tmpwu2s8058/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/tmpgbf7djs4/images/target contains 8144 images
+/tmp/tmpgbf7djs4/images/random contains 5000 images
 </pre></div>
 </div>
 </div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 52s - loss: 0.2231 - accuracy: 0.9247 - val_loss: 0.1298 - val_accuracy: 0.9588
+328/328 - 56s - loss: 0.2194 - accuracy: 0.9227 - val_loss: 0.1336 - val_accuracy: 0.9547
 Epoch 2/3
-328/328 - 49s - loss: 0.0932 - accuracy: 0.9647 - val_loss: 0.1130 - val_accuracy: 0.9694
+328/328 - 53s - loss: 0.0964 - accuracy: 0.9636 - val_loss: 0.1116 - val_accuracy: 0.9660
 Epoch 3/3
-328/328 - 49s - loss: 0.0641 - accuracy: 0.9765 - val_loss: 0.2279 - val_accuracy: 0.9324
+328/328 - 53s - loss: 0.0647 - accuracy: 0.9748 - val_loss: 0.1574 - val_accuracy: 0.9494
 
-&lt;keras.callbacks.History object at 0x7ff92532b950&gt;
+&lt;keras.callbacks.History object at 0x7f23697c1790&gt;
 </pre></div>
 </div>
 </div>
@@ -957,7 +957,7 @@ as intended.</p>
 <p>From here, we could modify the model to read live images from the camera - we have another
 Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
 <a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  45.363 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes  45.830 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 ee77c2468..c7a668b55 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:37.381</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:41.380</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,19 +336,19 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:45.363</p></td>
+<td><p>04:45.830</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:41.017</p></td>
+<td><p>00:43.729</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.786</p></td>
+<td><p>00:08.426</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.214</p></td>
+<td><p>00:03.393</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 087fe1297..6622ab15c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.236</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.090</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,15 +336,15 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.713</p></td>
+<td><p>00:32.186</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.163</p></td>
+<td><p>00:10.316</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.353</p></td>
+<td><p>00:01.581</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 47d255e8a..f227fb61c 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
 <a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">&quot;tir.exp&quot;</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">&quot;cuda&quot;</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7ff91d7dc050&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;function my_cuda_math_rule at 0x7f22dd418170&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 164cb600d..a583e0aec 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.152</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.159</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.911</p></td>
+<td><p>00:01.897</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.000</p></td>
+<td><p>00:01.013</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
@@ -348,19 +348,19 @@
 <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>00:00.524</p></td>
+<td><p>00:00.519</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>00:00.106</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.041</p></td>
+<td><p>00:00.042</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.026</p></td>
+<td><p>00:00.028</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index f0992300e..25fc2c9a6 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
              C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
   buffer_map = {A_1: A, B_1: B, C_1: C}
   preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
-  attr [IterVar(i: int32, (nullptr), &quot;DataPar&quot;, &quot;&quot;)] &quot;pragma_import_llvm&quot; = &quot;; ModuleID = &#39;/tmp/tmpkfa4_a16/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpkfa4_a16/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/tmpyj99edgt/input0.cc&#39;\nsource_filename = \&quot;/tmp/tmpyj99edgt/input0.cc\&quot;\ntarget datalayout = \&quot;e-m:e-i64:64-f80:128-n8:16:32:64-S128\&quot;\ntarget triple = \&quot;x86_64-pc-linux-gnu\&quot;\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n  %7 = allo [...]
   for (i, 0, 1024) {
     for (j.outer: int32, 0, 32) {
       @tir.call_extern(&quot;gemv_update&quot;, @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index aa2238b85..3153785d7 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,17 +224,7 @@
               <p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
 <ul class="current">
 <li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
 <li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
index 476df3bc3..d92ac4862 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
@@ -92,9 +92,10 @@ $(function() {
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">operator==</a>(const ObjectRef &amp;other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
   <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae81f559342e4628ea1bffce6db36e547">PyDatabase</a>(PyDatabaseNode::FHasWorkload f_has_workload, PyDatabaseNode::FCommitWorkload f_commit_workload, PyDatabaseNode::FCommitTuningRecord f_commit_tuning_record, PyDatabaseNode::FGetTopK f_get_top_k, PyDatabaseNode::FGetAllTuningRecords f_get_all_tuning_records, PyDatabaseNode::FSize f_size)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedul [...]
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#ae31a5b9f40781d60a2901994ead700e8">same_as</a>(const ObjectRef &amp;other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afb40a32e35f299ee0c6cd6f99f1ed44a">TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS</a>(Database, runtime::ObjectRef, DatabaseNode)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"></td></tr>
-  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a0ae0da21d247cd87ea94fe3777c4405e">use_count</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">ScheduleFnDatabase</a>(runtime::TypedPackedFunc&lt; bool(tir::Schedule)&gt; schedule_fn)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afb40a32e35f299ee0c6cd6f99f1ed44a">TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS</a>(Database, runtime::ObjectRef, DatabaseNode)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a0ae0da21d247cd87ea94fe3777c4405e">use_count</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
 </table></div><!-- contents -->
 <!-- start footer part -->
 <hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
index 0696dd46a..4e159658a 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
@@ -78,13 +78,13 @@ $(function() {
 <div class="dynheader">
 Inheritance diagram for tvm::meta_schedule::Database:</div>
 <div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg" width="198" height="580"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg" width="198" height="595"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
 </div>
 </div>
 <div class="dynheader">
 Collaboration diagram for tvm::meta_schedule::Database:</div>
 <div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__coll__graph.svg" width="198" height="868"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__coll__graph.svg" width="198" height="883"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
 </div>
 </div>
 <table class="memberdecls">
@@ -136,6 +136,9 @@ Public Member Functions</h2></td></tr>
 Static Public Member Functions</h2></td></tr>
 <tr class="memitem:ad1c38592f69cc782314f4e1450230ace"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a>&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ad1c38592f69cc782314f4e1450230ace">MemoryDatabase</a> ()</td></tr>
 <tr class="separator:ad1c38592f69cc782314f4e1450230ace"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:afd3cddb62e6fad7974e457b708c895a4"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a>&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">ScheduleFnDatabase</a> (<a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>&lt; bool(<a class="el" href="class [...]
+<tr class="memdesc:afd3cddb62e6fad7974e457b708c895a4"><td class="mdescLeft">&#160;</td><td class="mdescRight">A database for injecting handcrafted schedule functions.  <a href="#afd3cddb62e6fad7974e457b708c895a4">More...</a><br /></td></tr>
+<tr class="separator:afd3cddb62e6fad7974e457b708c895a4"><td class="memSeparator" colspan="2">&#160;</td></tr>
 <tr class="memitem:a9eba4e789ead8b3ffd53280390660d1e"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a>&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#a9eba4e789ead8b3ffd53280390660d1e">JSONDatabase</a> (<a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> path_workload, <a class="el" href="classtvm_1_1runtime_1_1String.ht [...]
 <tr class="memdesc:a9eba4e789ead8b3ffd53280390660d1e"><td class="mdescLeft">&#160;</td><td class="mdescRight">Create a default database that uses JSON file for tuning records.  <a href="#a9eba4e789ead8b3ffd53280390660d1e">More...</a><br /></td></tr>
 <tr class="separator:a9eba4e789ead8b3ffd53280390660d1e"><td class="memSeparator" colspan="2">&#160;</td></tr>
@@ -392,6 +395,40 @@ Additional Inherited Members</h2></td></tr>
 </dl>
 <dl class="section return"><dt>Returns</dt><dd>The created database. </dd></dl>
 
+</div>
+</div>
+<a id="afd3cddb62e6fad7974e457b708c895a4"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#afd3cddb62e6fad7974e457b708c895a4">&#9670;&nbsp;</a></span>ScheduleFnDatabase()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+  <tr>
+  <td class="mlabels-left">
+      <table class="memname">
+        <tr>
+          <td class="memname">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> tvm::meta_schedule::Database::ScheduleFnDatabase </td>
+          <td>(</td>
+          <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>&lt; bool(<a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a>)&gt;&#160;</td>
+          <td class="paramname"><em>schedule_fn</em></td><td>)</td>
+          <td></td>
+        </tr>
+      </table>
+  </td>
+  <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">static</span></span>  </td>
+  </tr>
+</table>
+</div><div class="memdoc">
+
+<p>A database for injecting handcrafted schedule functions. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+  <table class="params">
+    <tr><td class="paramname">schedule_fn</td><td>The function to do scheduling, which takes a TIR schedule, and returns a boolean indicating if the schedule is successful. </td></tr>
+  </table>
+  </dd>
+</dl>
+
 </div>
 </div>
 <a id="afb40a32e35f299ee0c6cd6f99f1ed44a"></a>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode-members.html
index 49e56f134..a2bd828e8 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode-members.html
@@ -96,9 +96,9 @@ $(function() {
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &amp;&amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
   <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &amp;&amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">QueryIRModule</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
-  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">QuerySchedule</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">QueryTuningRecord</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">QueryIRModule</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">QuerySchedule</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">QueryTuningRecord</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
   <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode.html
index 617e4f719..4d6e3e4c9 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1DatabaseNode.html
@@ -108,15 +108,15 @@ Public Member Functions</h2></td></tr>
 <tr class="memitem:aae5b9ab9f7e497654b90c23a2159a5cc"><td class="memItemLeft" align="right" valign="top">virtual int64_t&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aae5b9ab9f7e497654b90c23a2159a5cc">Size</a> ()=0</td></tr>
 <tr class="memdesc:aae5b9ab9f7e497654b90c23a2159a5cc"><td class="mdescLeft">&#160;</td><td class="mdescRight">Get the size of the database.  <a href="#aae5b9ab9f7e497654b90c23a2159a5cc">More...</a><br /></td></tr>
 <tr class="separator:aae5b9ab9f7e497654b90c23a2159a5cc"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:acd794ded30c3943f5e976e3d360bd178"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1meta__schedule_1_1TuningRecord.html">TuningRecord</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">QueryTuningRecord</a> (<a class="el" href="classtvm_1_1IRMo [...]
-<tr class="memdesc:acd794ded30c3943f5e976e3d360bd178"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best record of the given workload from the database.  <a href="#acd794ded30c3943f5e976e3d360bd178">More...</a><br /></td></tr>
-<tr class="separator:acd794ded30c3943f5e976e3d360bd178"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:af06e8cb22826d2e5f29d5ec9ede6095b"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">QuerySchedule</a> (<a class="el" href="classtvm_1_1IRModule.html">IRModul [...]
-<tr class="memdesc:af06e8cb22826d2e5f29d5ec9ede6095b"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best schedule of the given workload from the database.  <a href="#af06e8cb22826d2e5f29d5ec9ede6095b">More...</a><br /></td></tr>
-<tr class="separator:af06e8cb22826d2e5f29d5ec9ede6095b"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:a8f6ea7a73c34b3645e17cb673c81def6"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">QueryIRModule</a> (<a class="el" href="classtvm_1_1IRModule.html">IRModule</a> mod, < [...]
-<tr class="memdesc:a8f6ea7a73c34b3645e17cb673c81def6"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> of the given workload from the database.  <a href="#a8f6ea7a73c34b3645e17cb673c81def6">More...</a><br /></td></tr>
-<tr class="separator:a8f6ea7a73c34b3645e17cb673c81def6"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:adb5dd2d61af2ac335d68b402c057d612"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1meta__schedule_1_1TuningRecord.html">TuningRecord</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">QueryTuningRecord</a> (const <a class="el" href="classtvm_1 [...]
+<tr class="memdesc:adb5dd2d61af2ac335d68b402c057d612"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best record of the given workload from the database.  <a href="#adb5dd2d61af2ac335d68b402c057d612">More...</a><br /></td></tr>
+<tr class="separator:adb5dd2d61af2ac335d68b402c057d612"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:a638febf77b9cb7590d6babb28a97a020"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">QuerySchedule</a> (const <a class="el" href="classtvm_1_1IRModule.html">I [...]
+<tr class="memdesc:a638febf77b9cb7590d6babb28a97a020"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best schedule of the given workload from the database.  <a href="#a638febf77b9cb7590d6babb28a97a020">More...</a><br /></td></tr>
+<tr class="separator:a638febf77b9cb7590d6babb28a97a020"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:aeb4101db551afa93ea144b9b173783a0"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">QueryIRModule</a> (const <a class="el" href="classtvm_1_1IRModule.html">IRModule</a>  [...]
+<tr class="memdesc:aeb4101db551afa93ea144b9b173783a0"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> of the given workload from the database.  <a href="#aeb4101db551afa93ea144b9b173783a0">More...</a><br /></td></tr>
+<tr class="separator:aeb4101db551afa93ea144b9b173783a0"><td class="memSeparator" colspan="2">&#160;</td></tr>
 <tr class="memitem:ae7ea55bfa3703dfb6452573afc31a45e"><td class="memItemLeft" align="right" valign="top">&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#ae7ea55bfa3703dfb6452573afc31a45e">TVM_DECLARE_BASE_OBJECT_INFO</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">DatabaseNode</a>, <a class="el" href="classtvm_1_1runtime_1_1Object.html">runtime::Object</a>)</td></tr>
 <tr class="separator:ae7ea55bfa3703dfb6452573afc31a45e"><td class="memSeparator" colspan="2">&#160;</td></tr>
 <tr class="inherit_header pub_methods_classtvm_1_1runtime_1_1Object"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1runtime_1_1Object')"><img src="closed.png" alt="-"/>&#160;Public Member Functions inherited from <a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td></tr>
@@ -425,8 +425,8 @@ Additional Inherited Members</h2></td></tr>
 
 </div>
 </div>
-<a id="a8f6ea7a73c34b3645e17cb673c81def6"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a8f6ea7a73c34b3645e17cb673c81def6">&#9670;&nbsp;</a></span>QueryIRModule()</h2>
+<a id="aeb4101db551afa93ea144b9b173783a0"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aeb4101db551afa93ea144b9b173783a0">&#9670;&nbsp;</a></span>QueryIRModule()</h2>
 
 <div class="memitem">
 <div class="memproto">
@@ -437,14 +437,20 @@ Additional Inherited Members</h2></td></tr>
         <tr>
           <td class="memname">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt;<a class="el" href="classtvm_1_1IRModule.html">IRModule</a>&gt; tvm::meta_schedule::DatabaseNode::QueryIRModule </td>
           <td>(</td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1IRModule.html">IRModule</a>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &amp;&#160;</td>
           <td class="paramname"><em>mod</em>, </td>
         </tr>
         <tr>
           <td class="paramkey"></td>
           <td></td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1Target.html">Target</a>&#160;</td>
-          <td class="paramname"><em>target</em>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1Target.html">Target</a> &amp;&#160;</td>
+          <td class="paramname"><em>target</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> &amp;&#160;</td>
+          <td class="paramname"><em>workload_name</em>&#160;</td>
         </tr>
         <tr>
           <td></td>
@@ -464,6 +470,7 @@ Additional Inherited Members</h2></td></tr>
   <table class="params">
     <tr><td class="paramname">mod</td><td>The <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> to be searched for. </td></tr>
     <tr><td class="paramname">target</td><td>The target to be searched for. </td></tr>
+    <tr><td class="paramname">workload_name</td><td>The name of the workload to be searched for. </td></tr>
   </table>
   </dd>
 </dl>
@@ -471,8 +478,8 @@ Additional Inherited Members</h2></td></tr>
 
 </div>
 </div>
-<a id="af06e8cb22826d2e5f29d5ec9ede6095b"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#af06e8cb22826d2e5f29d5ec9ede6095b">&#9670;&nbsp;</a></span>QuerySchedule()</h2>
+<a id="a638febf77b9cb7590d6babb28a97a020"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a638febf77b9cb7590d6babb28a97a020">&#9670;&nbsp;</a></span>QuerySchedule()</h2>
 
 <div class="memitem">
 <div class="memproto">
@@ -483,14 +490,20 @@ Additional Inherited Members</h2></td></tr>
         <tr>
           <td class="memname">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt;<a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a>&gt; tvm::meta_schedule::DatabaseNode::QuerySchedule </td>
           <td>(</td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1IRModule.html">IRModule</a>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &amp;&#160;</td>
           <td class="paramname"><em>mod</em>, </td>
         </tr>
         <tr>
           <td class="paramkey"></td>
           <td></td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1Target.html">Target</a>&#160;</td>
-          <td class="paramname"><em>target</em>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1Target.html">Target</a> &amp;&#160;</td>
+          <td class="paramname"><em>target</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> &amp;&#160;</td>
+          <td class="paramname"><em>workload_name</em>&#160;</td>
         </tr>
         <tr>
           <td></td>
@@ -510,6 +523,7 @@ Additional Inherited Members</h2></td></tr>
   <table class="params">
     <tr><td class="paramname">mod</td><td>The <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> to be searched for. </td></tr>
     <tr><td class="paramname">target</td><td>The target to be searched for. </td></tr>
+    <tr><td class="paramname">workload_name</td><td>The name of the workload to be searched for. </td></tr>
   </table>
   </dd>
 </dl>
@@ -517,8 +531,8 @@ Additional Inherited Members</h2></td></tr>
 
 </div>
 </div>
-<a id="acd794ded30c3943f5e976e3d360bd178"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#acd794ded30c3943f5e976e3d360bd178">&#9670;&nbsp;</a></span>QueryTuningRecord()</h2>
+<a id="adb5dd2d61af2ac335d68b402c057d612"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#adb5dd2d61af2ac335d68b402c057d612">&#9670;&nbsp;</a></span>QueryTuningRecord()</h2>
 
 <div class="memitem">
 <div class="memproto">
@@ -529,14 +543,20 @@ Additional Inherited Members</h2></td></tr>
         <tr>
           <td class="memname">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt;<a class="el" href="classtvm_1_1meta__schedule_1_1TuningRecord.html">TuningRecord</a>&gt; tvm::meta_schedule::DatabaseNode::QueryTuningRecord </td>
           <td>(</td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1IRModule.html">IRModule</a>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &amp;&#160;</td>
           <td class="paramname"><em>mod</em>, </td>
         </tr>
         <tr>
           <td class="paramkey"></td>
           <td></td>
-          <td class="paramtype"><a class="el" href="classtvm_1_1Target.html">Target</a>&#160;</td>
-          <td class="paramname"><em>target</em>&#160;</td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1Target.html">Target</a> &amp;&#160;</td>
+          <td class="paramname"><em>target</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> &amp;&#160;</td>
+          <td class="paramname"><em>workload_name</em>&#160;</td>
         </tr>
         <tr>
           <td></td>
@@ -556,6 +576,7 @@ Additional Inherited Members</h2></td></tr>
   <table class="params">
     <tr><td class="paramname">mod</td><td>The <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> to be searched for. </td></tr>
     <tr><td class="paramname">target</td><td>The target to be searched for. </td></tr>
+    <tr><td class="paramname">workload_name</td><td>The name of the workload to be searched for. </td></tr>
   </table>
   </dd>
 </dl>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
index 63d0eb9c9..7076f6710 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
@@ -4,26 +4,27 @@
 <!-- Generated by graphviz version 2.40.1 (20161225.0304)
  -->
 <!-- Title: tvm::meta_schedule::Database Pages: 1 -->
-<svg width="148pt" height="651pt"
- viewBox="0.00 0.00 148.00 651.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 647)">
+<svg width="148pt" height="662pt"
+ viewBox="0.00 0.00 148.00 662.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 658)">
 <title>tvm::meta_schedule::Database</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-647 144,-647 144,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-658 144,-658 144,4 -4,4"/>
 <!-- Node2 -->
 <g id="node1" class="node">
 <title>Node2</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-156.5 140,-156.5 140,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="70" y="-133.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
-<polyline fill="none" stroke="#000000" points="0,-126.5 140,-126.5 "/>
-<text text-anchor="middle" x="70" y="-114.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-107.5 140,-107.5 "/>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-167.5 140,-167.5 140,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-155.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="70" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
+<polyline fill="none" stroke="#000000" points="0,-137.5 140,-137.5 "/>
+<text text-anchor="middle" x="70" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-118.5 140,-118.5 "/>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
 <text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
 <text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PyDatabase()</text>
 <text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Current()</text>
@@ -32,66 +33,66 @@
 <g id="node2" class="node">
 <title>Node3</title>
 <g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="3,-194.5 3,-416.5 137,-416.5 137,-194.5 3,-194.5"/>
-<text text-anchor="middle" x="70" y="-404.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="3,-397.5 137,-397.5 "/>
-<text text-anchor="start" x="11" y="-385.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="3,-378.5 137,-378.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="3,-205.5 3,-427.5 137,-427.5 137,-205.5 3,-205.5"/>
+<text text-anchor="middle" x="70" y="-415.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="3,-408.5 137,-408.5 "/>
+<text text-anchor="start" x="11" y="-396.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="3,-389.5 137,-389.5 "/>
+<text text-anchor="start" x="11" y="-377.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
 <text text-anchor="start" x="11" y="-366.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="11" y="-333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="11" y="-322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="11" y="-311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&lt;()</text>
-<text text-anchor="start" x="11" y="-300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="11" y="-289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="11" y="-278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
-<text text-anchor="start" x="11" y="-267.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="11" y="-256.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="11" y="-245.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="11" y="-234.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="11" y="-223.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="11" y="-212.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="11" y="-201.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<text text-anchor="start" x="11" y="-355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="11" y="-344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="11" y="-333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="11" y="-322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&lt;()</text>
+<text text-anchor="start" x="11" y="-311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="11" y="-300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="11" y="-289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
+<text text-anchor="start" x="11" y="-278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="11" y="-267.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="11" y="-256.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="11" y="-245.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="11" y="-234.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="11" y="-223.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="11" y="-212.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
 </a>
 </g>
 </g>
 <!-- Node3&#45;&gt;Node2 -->
 <g id="edge1" class="edge">
 <title>Node3&#45;&gt;Node2</title>
-<path fill="none" stroke="#191970" d="M70,-184.2158C70,-174.9116 70,-165.6775 70,-156.7651"/>
-<polygon fill="none" stroke="#191970" points="66.5001,-184.3275 70,-194.3275 73.5001,-184.3275 66.5001,-184.3275"/>
+<path fill="none" stroke="#191970" d="M70,-195.2104C70,-185.8646 70,-176.5624 70,-167.5459"/>
+<polygon fill="none" stroke="#191970" points="66.5001,-195.3571 70,-205.3572 73.5001,-195.3572 66.5001,-195.3571"/>
 </g>
 <!-- Node4 -->
 <g id="node3" class="node">
 <title>Node4</title>
 <g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\&lt; tvm::runtime::Object \&gt;\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator&#45;\&gt;()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="0,-464.5 0,-642.5 140,-642.5 140,-464.5 0,-464.5"/>
-<text text-anchor="start" x="8" y="-630.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="70" y="-619.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">&lt; tvm::runtime::Object &gt;</text>
-<polyline fill="none" stroke="#000000" points="0,-612.5 140,-612.5 "/>
-<text text-anchor="middle" x="70" y="-600.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-593.5 140,-593.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="0,-475.5 0,-653.5 140,-653.5 140,-475.5 0,-475.5"/>
+<text text-anchor="start" x="8" y="-641.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="70" y="-630.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">&lt; tvm::runtime::Object &gt;</text>
+<polyline fill="none" stroke="#000000" points="0,-623.5 140,-623.5 "/>
+<text text-anchor="middle" x="70" y="-611.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-604.5 140,-604.5 "/>
+<text text-anchor="start" x="8" y="-592.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
 <text text-anchor="start" x="8" y="-581.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
 <text text-anchor="start" x="8" y="-570.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
 <text text-anchor="start" x="8" y="-559.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
 <text text-anchor="start" x="8" y="-548.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
 <text text-anchor="start" x="8" y="-537.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-526.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-515.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-504.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="8" y="-493.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="8" y="-482.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
-<text text-anchor="start" x="8" y="-471.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<text text-anchor="start" x="8" y="-526.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="8" y="-515.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="8" y="-504.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="8" y="-493.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
+<text text-anchor="start" x="8" y="-482.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
 </a>
 </g>
 </g>
 <!-- Node4&#45;&gt;Node3 -->
 <g id="edge2" class="edge">
 <title>Node4&#45;&gt;Node3</title>
-<path fill="none" stroke="#404040" d="M70,-464.3167C70,-452.8765 70,-441.0062 70,-429.1402"/>
-<polygon fill="none" stroke="#404040" points="70.0001,-428.7944 66,-422.7944 70,-416.7944 74,-422.7943 70.0001,-428.7944"/>
-<text text-anchor="middle" x="89.5" y="-438" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M70,-475.3167C70,-463.8765 70,-452.0062 70,-440.1402"/>
+<polygon fill="none" stroke="#404040" points="70.0001,-439.7944 66,-433.7944 70,-427.7944 74,-433.7943 70.0001,-439.7944"/>
+<text text-anchor="middle" x="89.5" y="-449" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
 </g>
 </g>
 </svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
index f23ca6c24..fe7c2ef2d 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
@@ -4,26 +4,27 @@
 <!-- Generated by graphviz version 2.40.1 (20161225.0304)
  -->
 <!-- Title: tvm::meta_schedule::Database Pages: 1 -->
-<svg width="148pt" height="435pt"
- viewBox="0.00 0.00 148.00 435.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 431)">
+<svg width="148pt" height="446pt"
+ viewBox="0.00 0.00 148.00 446.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 442)">
 <title>tvm::meta_schedule::Database</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-431 144,-431 144,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-442 144,-442 144,4 -4,4"/>
 <!-- Node0 -->
 <g id="node1" class="node">
 <title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-156.5 140,-156.5 140,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="70" y="-133.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
-<polyline fill="none" stroke="#000000" points="0,-126.5 140,-126.5 "/>
-<text text-anchor="middle" x="70" y="-114.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-107.5 140,-107.5 "/>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-167.5 140,-167.5 140,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-155.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="70" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
+<polyline fill="none" stroke="#000000" points="0,-137.5 140,-137.5 "/>
+<text text-anchor="middle" x="70" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-118.5 140,-118.5 "/>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
 <text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
 <text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PyDatabase()</text>
 <text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Current()</text>
@@ -32,36 +33,36 @@
 <g id="node2" class="node">
 <title>Node1</title>
 <g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="3,-193.5 3,-426.5 137,-426.5 137,-193.5 3,-193.5"/>
-<text text-anchor="middle" x="70" y="-414.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="3,-407.5 137,-407.5 "/>
-<text text-anchor="start" x="11" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<text text-anchor="start" x="11" y="-384.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
-<polyline fill="none" stroke="#000000" points="3,-377.5 137,-377.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="3,-204.5 3,-437.5 137,-437.5 137,-204.5 3,-204.5"/>
+<text text-anchor="middle" x="70" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="3,-418.5 137,-418.5 "/>
+<text text-anchor="start" x="11" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<text text-anchor="start" x="11" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
+<polyline fill="none" stroke="#000000" points="3,-388.5 137,-388.5 "/>
+<text text-anchor="start" x="11" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
 <text text-anchor="start" x="11" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="11" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="11" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="11" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&lt;()</text>
-<text text-anchor="start" x="11" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="11" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="11" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
-<text text-anchor="start" x="11" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="11" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="11" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="11" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="11" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="11" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="11" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<text text-anchor="start" x="11" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="11" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="11" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="11" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&lt;()</text>
+<text text-anchor="start" x="11" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="11" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="11" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator&#45;&gt;()</text>
+<text text-anchor="start" x="11" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="11" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="11" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="11" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="11" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="11" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="11" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
 </a>
 </g>
 </g>
 <!-- Node1&#45;&gt;Node0 -->
 <g id="edge1" class="edge">
 <title>Node1&#45;&gt;Node0</title>
-<path fill="none" stroke="#191970" d="M70,-183.108C70,-174.1638 70,-165.3093 70,-156.7606"/>
-<polygon fill="none" stroke="#191970" points="66.5001,-183.2326 70,-193.2327 73.5001,-183.2327 66.5001,-183.2326"/>
+<path fill="none" stroke="#191970" d="M70,-194.0814C70,-185.1022 70,-176.1877 70,-167.5456"/>
+<polygon fill="none" stroke="#191970" points="66.5001,-194.2358 70,-204.2358 73.5001,-194.2358 66.5001,-194.2358"/>
 </g>
 </g>
 </svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode-members.html
index 63b63cd12..8d0532c07 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode-members.html
@@ -108,9 +108,9 @@ $(function() {
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &amp;&amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
   <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &amp;&amp;other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">QueryIRModule</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
-  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">QuerySchedule</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
-  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">QueryTuningRecord</a>(IRModule mod, Target target)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">QueryIRModule</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">QuerySchedule</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+  <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">QueryTuningRecord</a>(const IRModule &amp;mod, const Target &amp;target, const String &amp;workload_name)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
   <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
   <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode.html
index 6e118a9b7..7eefff8f0 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PyDatabaseNode.html
@@ -145,15 +145,15 @@ Public Member Functions</h2></td></tr>
 <tr class="memitem:a776359f44ac6b51e337d4a1efc3f04a9 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a776359f44ac6b51e337d4a1efc3f04a9">~DatabaseNode</a> ()=default</td></tr>
 <tr class="memdesc:a776359f44ac6b51e337d4a1efc3f04a9 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Default destructor.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a776359f44ac6b51e337d4a1efc3f04a9">More...</a><br /></td></tr>
 <tr class="separator:a776359f44ac6b51e337d4a1efc3f04a9 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:acd794ded30c3943f5e976e3d360bd178 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1meta__schedule_1_1TuningRecord.html">TuningRecord</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd1 [...]
-<tr class="memdesc:acd794ded30c3943f5e976e3d360bd178 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best record of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">More...</a><br /></td></tr>
-<tr class="separator:acd794ded30c3943f5e976e3d360bd178 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:af06e8cb22826d2e5f29d5ec9ede6095b inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">QuerySched [...]
-<tr class="memdesc:af06e8cb22826d2e5f29d5ec9ede6095b inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best schedule of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">More...</a><br /></td></tr>
-<tr class="separator:af06e8cb22826d2e5f29d5ec9ede6095b inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
-<tr class="memitem:a8f6ea7a73c34b3645e17cb673c81def6 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">QueryIRModule</a> (<a  [...]
-<tr class="memdesc:a8f6ea7a73c34b3645e17cb673c81def6 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">More...</a><br /></td></tr>
-<tr class="separator:a8f6ea7a73c34b3645e17cb673c81def6 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:adb5dd2d61af2ac335d68b402c057d612 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1meta__schedule_1_1TuningRecord.html">TuningRecord</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d6 [...]
+<tr class="memdesc:adb5dd2d61af2ac335d68b402c057d612 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best record of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">More...</a><br /></td></tr>
+<tr class="separator:adb5dd2d61af2ac335d68b402c057d612 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:a638febf77b9cb7590d6babb28a97a020 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1tir_1_1Schedule.html">tir::Schedule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">QuerySched [...]
+<tr class="memdesc:a638febf77b9cb7590d6babb28a97a020 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best schedule of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">More...</a><br /></td></tr>
+<tr class="separator:a638febf77b9cb7590d6babb28a97a020 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:aeb4101db551afa93ea144b9b173783a0 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>&lt; <a class="el" href="classtvm_1_1IRModule.html">IRModule</a> &gt;&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">QueryIRModule</a> (con [...]
+<tr class="memdesc:aeb4101db551afa93ea144b9b173783a0 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="mdescLeft">&#160;</td><td class="mdescRight">Query the best <a class="el" href="classtvm_1_1IRModule.html" title="Managed reference class to IRModuleNode. ">IRModule</a> of the given workload from the database.  <a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">More...</a><br /></td></tr>
+<tr class="separator:aeb4101db551afa93ea144b9b173783a0 inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
 <tr class="memitem:ae7ea55bfa3703dfb6452573afc31a45e inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memItemLeft" align="right" valign="top">&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#ae7ea55bfa3703dfb6452573afc31a45e">TVM_DECLARE_BASE_OBJECT_INFO</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">DatabaseNode</a>, <a class="el" href="classtvm_1_1runtime_1_1Objec [...]
 <tr class="separator:ae7ea55bfa3703dfb6452573afc31a45e inherit pub_methods_classtvm_1_1meta__schedule_1_1DatabaseNode"><td class="memSeparator" colspan="2">&#160;</td></tr>
 <tr class="inherit_header pub_methods_classtvm_1_1runtime_1_1Object"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1runtime_1_1Object')"><img src="closed.png" alt="-"/>&#160;Public Member Functions inherited from <a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td></tr>
diff --git a/docs/reference/api/doxygen/database_8h_source.html b/docs/reference/api/doxygen/database_8h_source.html
index 62798d825..1fa809d07 100644
--- a/docs/reference/api/doxygen/database_8h_source.html
+++ b/docs/reference/api/doxygen/database_8h_source.html
@@ -66,9 +66,9 @@ $(function() {
 <div class="title">database.h</div>  </div>
 </div><!--header-->
 <div class="contents">
-<a href="database_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno">    1</span>&#160;<span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno">    2</span>&#160;<span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno">    3</span>&#160;<span class="comment"> * or more co [...]
+<a href="database_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno">    1</span>&#160;<span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno">    2</span>&#160;<span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno">    3</span>&#160;<span class="comment"> * or more co [...]
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_a93d2f3debadefcc713bbc045127ca8f7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#a93d2f3debadefcc713bbc045127ca8f7">tvm::meta_schedule::WorkloadNode::TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_FINAL_OBJECT_INFO(WorkloadNode, runtime::Object)</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a7d7d50ae9b6c43e064b38db91bc8123d"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a7d7d50ae9b6c43e064b38db91bc8123d">tvm::meta_schedule::PyDatabaseNode::f_commit_tuning_record</a></div><div class="ttdeci">FCommitTuningRecord f_commit_tuning_record</div><div class="ttdoc">The packed function to the CommitTuningRecord function. </div><div class="ttdef"><b>Definition:</b> database.h:275</d [...]
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a7d7d50ae9b6c43e064b38db91bc8123d"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a7d7d50ae9b6c43e064b38db91bc8123d">tvm::meta_schedule::PyDatabaseNode::f_commit_tuning_record</a></div><div class="ttdeci">FCommitTuningRecord f_commit_tuning_record</div><div class="ttdoc">The packed function to the CommitTuningRecord function. </div><div class="ttdef"><b>Definition:</b> database.h:281</d [...]
 <div class="ttc" id="trace_8h_html"><div class="ttname"><a href="trace_8h.html">trace.h</a></div></div>
 <div class="ttc" id="object_8h_html_a98fa3013ab23958a9f05200330e35805"><div class="ttname"><a href="object_8h.html#a98fa3013ab23958a9f05200330e35805">TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:758</div></div>
 <div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadHash_html"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadHash.html">tvm::meta_schedule::WorkloadHash</a></div><div class="ttdoc">The hash method for Workload. </div><div class="ttdef"><b>Definition:</b> database.h:90</div></div>
@@ -79,29 +79,30 @@ $(function() {
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a45a380cfa2edfd63056fb1a00f9aac35"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a45a380cfa2edfd63056fb1a00f9aac35">tvm::meta_schedule::TuningRecordNode::target</a></div><div class="ttdeci">Optional&lt; Target &gt; target</div><div class="ttdoc">The target for tuning. </div><div class="ttdef"><b>Definition:</b> database.h:114</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_aad19a5cb8e2c623e355ca5e2a98c4c18"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#aad19a5cb8e2c623e355ca5e2a98c4c18">tvm::meta_schedule::WorkloadNode::THashCode</a></div><div class="ttdeci">size_t THashCode</div><div class="ttdoc">The type of structural hash. </div><div class="ttdef"><b>Definition:</b> database.h:40</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1DatabaseNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1DatabaseNode.html">tvm::meta_schedule::DatabaseNode</a></div><div class="ttdef"><b>Definition:</b> database.h:168</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a52fb1116090619e95fb6b28352308eed"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a52fb1116090619e95fb6b28352308eed">tvm::meta_schedule::PyDatabaseNode::f_get_top_k</a></div><div class="ttdeci">FGetTopK f_get_top_k</div><div class="ttdoc">The packed function to the GetTopK function. </div><div class="ttdef"><b>Definition:</b> database.h:277</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a52fb1116090619e95fb6b28352308eed"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a52fb1116090619e95fb6b28352308eed">tvm::meta_schedule::PyDatabaseNode::f_get_top_k</a></div><div class="ttdeci">FGetTopK f_get_top_k</div><div class="ttdoc">The packed function to the GetTopK function. </div><div class="ttdef"><b>Definition:</b> database.h:283</div></div>
 <div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadHash_html_a7cb09ddc6c76d9d00ddbeab8502d97cb"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadHash.html#a7cb09ddc6c76d9d00ddbeab8502d97cb">tvm::meta_schedule::WorkloadHash::operator()</a></div><div class="ttdeci">size_t operator()(const Workload &amp;a) const</div><div class="ttdef"><b>Definition:</b> database.h:91</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html">tvm::meta_schedule::PyDatabaseNode</a></div><div class="ttdoc">The database with customized methods on the python-side. </div><div class="ttdef"><b>Definition:</b> database.h:233</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html">tvm::meta_schedule::PyDatabaseNode</a></div><div class="ttdoc">The database with customized methods on the python-side. </div><div class="ttdef"><b>Definition:</b> database.h:239</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:659</div></div>
 <div class="ttc" id="classtvm_1_1StructuralEqual_html"><div class="ttname"><a href="classtvm_1_1StructuralEqual.html">tvm::StructuralEqual</a></div><div class="ttdoc">Content-aware structural equality comparator for objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:103</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a8cc2d64f796593a1a774eef259f17b29"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29">tvm::meta_schedule::TuningRecordNode::trace</a></div><div class="ttdeci">tir::Trace trace</div><div class="ttdoc">The trace tuned. </div><div class="ttdef"><b>Definition:</b> database.h:108</div></div>
 <div class="ttc" id="arg__info_8h_html"><div class="ttname"><a href="arg__info_8h.html">arg_info.h</a></div></div>
 <div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_ac7ae1a05fe5c7858f5860133a82bc7b7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#ac7ae1a05fe5c7858f5860133a82bc7b7">tvm::meta_schedule::PyDatabaseNode::f_size</a></div><div class="ttdeci">FSize f_size</div><div class="ttdoc">The packed function to the Size function. </div><div class="ttdef"><b>Definition:</b> database.h:281</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_ac7ae1a05fe5c7858f5860133a82bc7b7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#ac7ae1a05fe5c7858f5860133a82bc7b7">tvm::meta_schedule::PyDatabaseNode::f_size</a></div><div class="ttdeci">FSize f_size</div><div class="ttdoc">The packed function to the Size function. </div><div class="ttdef"><b>Definition:</b> database.h:287</div></div>
 <div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a09f1921d607d7ef4397876c15d2f0b08"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a09f1921d607d7ef4397876c15d2f0b08">tvm::meta_schedule::TuningRecordNode::args_info</a></div><div class="ttdeci">Optional&lt; Array&lt; ArgInfo &gt; &gt; args_info</div><div class="ttdoc">The argument information. </div><div class="ttdef"><b>Definition:</b> database.h:116</div></div>
 <div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadEqual_html_aa29256c62e52bef8c9a0f7881d3fc601"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadEqual.html#aa29256c62e52bef8c9a0f7881d3fc601">tvm::meta_schedule::WorkloadEqual::operator()</a></div><div class="ttdeci">bool operator()(const Workload &amp;a, const Workload &amp;b) const</div><div class="ttdef"><b>Definition:</b> database.h:96</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1Database_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></div><div class="ttdoc">Managed reference to DatabaseNode. </div><div class="ttdef"><b>Definition:</b> database.h:335</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1Database_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></div><div class="ttdoc">Managed reference to DatabaseNode. </div><div class="ttdef"><b>Definition:</b> database.h:341</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1Array_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html">tvm::runtime::Array</a></div><div class="ttdoc">Array, container representing a contiguous sequence of ObjectRefs. </div><div class="ttdef"><b>Definition:</b> array.h:270</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a38195f2c3aea9ae4890477393ab2c624"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a38195f2c3aea9ae4890477393ab2c624">tvm::meta_schedule::PyDatabaseNode::HasWorkload</a></div><div class="ttdeci">bool HasWorkload(const IRModule &amp;mod) final</div><div class="ttdoc">Check if the database has the given workload. </div><div class="ttdef"><b>Definition:</b> database.h:295</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a38195f2c3aea9ae4890477393ab2c624"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a38195f2c3aea9ae4890477393ab2c624">tvm::meta_schedule::PyDatabaseNode::HasWorkload</a></div><div class="ttdeci">bool HasWorkload(const IRModule &amp;mod) final</div><div class="ttdoc">Check if the database has the given workload. </div><div class="ttdef"><b>Definition:</b> database.h:301</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_a3929f2761c168c25de6be2247b913911"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#a3929f2761c168c25de6be2247b913911">tvm::meta_schedule::WorkloadNode::mod</a></div><div class="ttdeci">IRModule mod</div><div class="ttdoc">The workload&amp;#39;s IRModule. </div><div class="ttdef"><b>Definition:</b> database.h:42</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a00aeeedbe4d1d6008224d98c62739581"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a00aeeedbe4d1d6008224d98c62739581">tvm::meta_schedule::TuningRecordNode::run_secs</a></div><div class="ttdeci">Optional&lt; Array&lt; FloatImm &gt; &gt; run_secs</div><div class="ttdoc">The profiling result in seconds. </div><div class="ttdef"><b>Definition:</b> database.h:112</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:97</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1TypedPackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TypedPackedFunc.html">tvm::runtime::TypedPackedFunc&lt; bool(const IRModule &amp;)&gt;</a></div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a36817d04978253571fef7d01427ce9c0"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0">tvm::meta_schedule::PyDatabaseNode::Size</a></div><div class="ttdeci">int64_t Size() final</div><div class="ttdoc">Get the size of the database. </div><div class="ttdef"><b>Definition:</b> database.h:322</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a36817d04978253571fef7d01427ce9c0"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0">tvm::meta_schedule::PyDatabaseNode::Size</a></div><div class="ttdeci">int64_t Size() final</div><div class="ttdoc">Get the size of the database. </div><div class="ttdef"><b>Definition:</b> database.h:328</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_ab533ae06bb310ffbd8acb954e253b7db"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#ab533ae06bb310ffbd8acb954e253b7db">tvm::meta_schedule::WorkloadNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> database.h:46</div></div>
 <div class="ttc" id="classtvm_1_1Target_html"><div class="ttname"><a href="classtvm_1_1Target.html">tvm::Target</a></div><div class="ttdoc">Managed reference class to TargetNode. </div><div class="ttdef"><b>Definition:</b> target.h:181</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_ad07d7d9e78771eaa2e6e65f84e032401"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#ad07d7d9e78771eaa2e6e65f84e032401">tvm::meta_schedule::PyDatabaseNode::GetAllTuningRecords</a></div><div class="ttdeci">Array&lt; TuningRecord &gt; GetAllTuningRecords() final</div><div class="ttdoc">Get all tuning records from the database. </div><div class="ttdef"><b>Definition:</b> database.h:316</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_ad07d7d9e78771eaa2e6e65f84e032401"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#ad07d7d9e78771eaa2e6e65f84e032401">tvm::meta_schedule::PyDatabaseNode::GetAllTuningRecords</a></div><div class="ttdeci">Array&lt; TuningRecord &gt; GetAllTuningRecords() final</div><div class="ttdoc">Get all tuning records from the database. </div><div class="ttdef"><b>Definition:</b> database.h:322</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidate_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">tvm::meta_schedule::MeasureCandidate</a></div><div class="ttdoc">Managed reference to MeasureCandidateNode. </div><div class="ttdef"><b>Definition:</b> measure_candidate.h:53</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html">tvm::meta_schedule::TuningRecordNode</a></div><div class="ttdoc">The class of tuning records. </div><div class="ttdef"><b>Definition:</b> database.h:105</div></div>
@@ -109,19 +110,19 @@ $(function() {
 <div class="ttc" id="object_8h_html"><div class="ttname"><a href="object_8h.html">object.h</a></div><div class="ttdoc">A managed object in the TVM runtime. </div></div>
 <div class="ttc" id="classtvm_1_1IRModule_html"><div class="ttname"><a href="classtvm_1_1IRModule.html">tvm::IRModule</a></div><div class="ttdoc">Managed reference class to IRModuleNode. </div><div class="ttdef"><b>Definition:</b> module.h:352</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_aa0ee452b287813b9509e649397846a3c"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#aa0ee452b287813b9509e649397846a3c">tvm::meta_schedule::WorkloadNode::AsJSON</a></div><div class="ttdeci">ObjectRef AsJSON() const</div><div class="ttdoc">Export the workload to a JSON string. </div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_add146bf1e2006f72ed1534b2004bcb06"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#add146bf1e2006f72ed1534b2004bcb06">tvm::meta_schedule::PyDatabaseNode::f_has_workload</a></div><div class="ttdeci">FHasWorkload f_has_workload</div><div class="ttdoc">The packed function to the HasWorkload function. </div><div class="ttdef"><b>Definition:</b> database.h:271</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a00614b22bd1cae147dc0d83cdd071187"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a00614b22bd1cae147dc0d83cdd071187">tvm::meta_schedule::PyDatabaseNode::CommitTuningRecord</a></div><div class="ttdeci">void CommitTuningRecord(const TuningRecord &amp;record) final</div><div class="ttdoc">Add a tuning record to the database. </div><div class="ttdef"><b>Definition:</b> database.h:305</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_aa0bd64983cde2fc6ef1547448352981c"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#aa0bd64983cde2fc6ef1547448352981c">tvm::meta_schedule::PyDatabaseNode::f_commit_workload</a></div><div class="ttdeci">FCommitWorkload f_commit_workload</div><div class="ttdoc">The packed function to the CommitWorkload function. </div><div class="ttdef"><b>Definition:</b> database.h:273</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_add146bf1e2006f72ed1534b2004bcb06"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#add146bf1e2006f72ed1534b2004bcb06">tvm::meta_schedule::PyDatabaseNode::f_has_workload</a></div><div class="ttdeci">FHasWorkload f_has_workload</div><div class="ttdoc">The packed function to the HasWorkload function. </div><div class="ttdef"><b>Definition:</b> database.h:277</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a00614b22bd1cae147dc0d83cdd071187"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a00614b22bd1cae147dc0d83cdd071187">tvm::meta_schedule::PyDatabaseNode::CommitTuningRecord</a></div><div class="ttdeci">void CommitTuningRecord(const TuningRecord &amp;record) final</div><div class="ttdoc">Add a tuning record to the database. </div><div class="ttdef"><b>Definition:</b> database.h:311</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_aa0bd64983cde2fc6ef1547448352981c"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#aa0bd64983cde2fc6ef1547448352981c">tvm::meta_schedule::PyDatabaseNode::f_commit_workload</a></div><div class="ttdeci">FCommitWorkload f_commit_workload</div><div class="ttdoc">The packed function to the CommitWorkload function. </div><div class="ttdef"><b>Definition:</b> database.h:279</div></div>
 <div class="ttc" id="target_8h_html"><div class="ttname"><a href="target_8h.html">target.h</a></div><div class="ttdoc">Compilation target object. </div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a12d64aa44d3d2ab37a6600d17be3e708"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a12d64aa44d3d2ab37a6600d17be3e708">tvm::meta_schedule::PyDatabaseNode::CommitWorkload</a></div><div class="ttdeci">Workload CommitWorkload(const IRModule &amp;mod) final</div><div class="ttdoc">Look up or add workload to the database if missing. </div><div class="ttdef"><b>Definition:</b> database.h:300</d [...]
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a12d64aa44d3d2ab37a6600d17be3e708"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a12d64aa44d3d2ab37a6600d17be3e708">tvm::meta_schedule::PyDatabaseNode::CommitWorkload</a></div><div class="ttdeci">Workload CommitWorkload(const IRModule &amp;mod) final</div><div class="ttdoc">Look up or add workload to the database if missing. </div><div class="ttdef"><b>Definition:</b> database.h:306</d [...]
 <div class="ttc" id="classtvm_1_1tir_1_1Trace_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Trace.html">tvm::tir::Trace</a></div><div class="ttdoc">Managed reference to TraceNode. </div><div class="ttdef"><b>Definition:</b> trace.h:141</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_aafdd0874be052072521b2aa8a6c56d5f"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#aafdd0874be052072521b2aa8a6c56d5f">tvm::meta_schedule::PyDatabaseNode::f_get_all_tuning_records</a></div><div class="ttdeci">FGetAllTuningRecords f_get_all_tuning_records</div><div class="ttdoc">The packed function to the GetAllTuningRecords function. </div><div class="ttdef"><b>Definition:</b> database.h: [...]
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_aafdd0874be052072521b2aa8a6c56d5f"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#aafdd0874be052072521b2aa8a6c56d5f">tvm::meta_schedule::PyDatabaseNode::f_get_all_tuning_records</a></div><div class="ttdeci">FGetAllTuningRecords f_get_all_tuning_records</div><div class="ttdoc">The packed function to the GetAllTuningRecords function. </div><div class="ttdef"><b>Definition:</b> database.h: [...]
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_a96812f1418c68d5aeb11331fd76aab1c"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#a96812f1418c68d5aeb11331fd76aab1c">tvm::meta_schedule::WorkloadNode::shash</a></div><div class="ttdeci">THashCode shash</div><div class="ttdoc">The workload&amp;#39;s structural hash. </div><div class="ttdef"><b>Definition:</b> database.h:44</div></div>
 <div class="ttc" id="classtvm_1_1runtime_1_1Optional_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Optional.html">tvm::runtime::Optional</a></div><div class="ttdoc">Optional container that to represent to a Nullable variant of T. </div><div class="ttdef"><b>Definition:</b> optional.h:51</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1Workload_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1Workload.html">tvm::meta_schedule::Workload</a></div><div class="ttdoc">Managed reference to WorkloadNode. </div><div class="ttdef"><b>Definition:</b> database.h:65</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_adebe3a6bfb55e5ce0807b97f12a6c39e"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#adebe3a6bfb55e5ce0807b97f12a6c39e">tvm::meta_schedule::PyDatabaseNode::GetTopK</a></div><div class="ttdeci">Array&lt; TuningRecord &gt; GetTopK(const Workload &amp;workload, int top_k) final</div><div class="ttdoc">Get the top K tuning records of given workload from the database. </div><div class="ttdef">< [...]
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_adebe3a6bfb55e5ce0807b97f12a6c39e"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#adebe3a6bfb55e5ce0807b97f12a6c39e">tvm::meta_schedule::PyDatabaseNode::GetTopK</a></div><div class="ttdeci">Array&lt; TuningRecord &gt; GetTopK(const Workload &amp;workload, int top_k) final</div><div class="ttdoc">Get the top K tuning records of given workload from the database. </div><div class="ttdef">< [...]
 <div class="ttc" id="reflection_8h_html"><div class="ttname"><a href="reflection_8h.html">reflection.h</a></div><div class="ttdoc">Reflection and serialization of compiler IR/AST nodes. </div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a1a24b977e3d25a7ffab704e12457fb66"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a1a24b977e3d25a7ffab704e12457fb66">tvm::meta_schedule::PyDatabaseNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> database.h:283</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a1a24b977e3d25a7ffab704e12457fb66"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a1a24b977e3d25a7ffab704e12457fb66">tvm::meta_schedule::PyDatabaseNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> database.h:289</div></div>
 <div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecord_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecord.html">tvm::meta_schedule::TuningRecord</a></div><div class="ttdoc">The managed reference of TuningRecordNode. </div><div class="ttdef"><b>Definition:</b> database.h:144</div></div>
 <div class="ttc" id="object_8h_html_ac2b7418e9549512b5db0126cf2a716f1"><div class="ttname"><a href="object_8h.html#ac2b7418e9549512b5db0126cf2a716f1">TVM_DECLARE_BASE_OBJECT_INFO</a></div><div class="ttdeci">#define TVM_DECLARE_BASE_OBJECT_INFO(TypeName, ParentType)</div><div class="ttdoc">helper macro to declare a base object type that can be inherited. </div><div class="ttdef"><b>Definition:</b> object.h:648</div></div>
 <div class="ttc" id="object_8h_html_a782d0de62fbf75736e29c1e79c22c7f1"><div class="ttname"><a href="object_8h.html#a782d0de62fbf75736e29c1e79c22c7f1">TVM_DEFINE_NOTNULLABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_NOTNULLABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:728</div></div>
diff --git a/docs/reference/api/doxygen/functions_func_q.html b/docs/reference/api/doxygen/functions_func_q.html
index 9912c62a8..57ebb884c 100644
--- a/docs/reference/api/doxygen/functions_func_q.html
+++ b/docs/reference/api/doxygen/functions_func_q.html
@@ -62,13 +62,13 @@ $(function() {
 
 <h3><a id="index_q"></a>- q -</h3><ul>
 <li>QueryIRModule()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">tvm::meta_schedule::DatabaseNode</a>
 </li>
 <li>QuerySchedule()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">tvm::meta_schedule::DatabaseNode</a>
 </li>
 <li>QueryTuningRecord()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">tvm::meta_schedule::DatabaseNode</a>
 </li>
 </ul>
 </div><!-- contents -->
diff --git a/docs/reference/api/doxygen/functions_func_r.html b/docs/reference/api/doxygen/functions_func_r.html
index c41fb95cd..f0abe7b43 100644
--- a/docs/reference/api/doxygen/functions_func_r.html
+++ b/docs/reference/api/doxygen/functions_func_r.html
@@ -296,7 +296,7 @@ $(function() {
 , <a class="el" href="classtvm_1_1relay_1_1MixedModeMutator.html#a4c93a9094db80cace013ef02e6bcd724">tvm::relay::MixedModeMutator</a>
 </li>
 <li>Rewrite_()
-: <a class="el" href="classtvm_1_1relay_1_1ExprRewriter.html#a75b4f0d342f6bd253b4f0b5d036a9156">tvm::relay::ExprRewriter</a>
+: <a class="el" href="classtvm_1_1relay_1_1ExprRewriter.html#afd8e949e00f51987ee9062c0b67c5f70">tvm::relay::ExprRewriter</a>
 , <a class="el" href="classtvm_1_1relay_1_1MixedModeMutator.html#a3b53908f4b8cc3708ca75892e47f0929">tvm::relay::MixedModeMutator</a>
 </li>
 <li>RewriteCooperativeFetch()
diff --git a/docs/reference/api/doxygen/functions_func_s.html b/docs/reference/api/doxygen/functions_func_s.html
index 6dd2de464..1e2a181f1 100644
--- a/docs/reference/api/doxygen/functions_func_s.html
+++ b/docs/reference/api/doxygen/functions_func_s.html
@@ -103,6 +103,9 @@ $(function() {
 <li>ScheduleFn()
 : <a class="el" href="classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa6dd3790fd633db9046015c69aca3735">tvm::meta_schedule::SpaceGenerator</a>
 </li>
+<li>ScheduleFnDatabase()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">tvm::meta_schedule::Database</a>
+</li>
 <li>ScheduleState()
 : <a class="el" href="classtvm_1_1tir_1_1ScheduleState.html#a1f8d0fc95f0d91de0aba3142a57552ad">tvm::tir::ScheduleState</a>
 </li>
@@ -435,7 +438,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1relay_1_1ShapePattern.html#a853201a9d5df8de96713a58c292e8698">tvm::relay::ShapePattern</a>
 </li>
 <li>ShapeTuple()
-: <a class="el" href="classtvm_1_1runtime_1_1ShapeTuple.html#a7015b56c1a918607b1e220b43fc86d10">tvm::runtime::ShapeTuple</a>
+: <a class="el" href="classtvm_1_1runtime_1_1ShapeTuple.html#a6836ad757cbcac207ddf025a74ac2ef2">tvm::runtime::ShapeTuple</a>
 </li>
 <li>SHashReduce()
 : <a class="el" href="classtvm_1_1arith_1_1IntConstraintsNode.html#add6e128afc66485e71854a8800c90c7a">tvm::arith::IntConstraintsNode</a>
@@ -559,7 +562,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1SHashReducer_1_1Handler.html#a1bb22d4bb3983b4c3ca87b0daef7f93b">tvm::SHashReducer::Handler</a>
 </li>
 <li>SHashReducer()
-: <a class="el" href="classtvm_1_1SHashReducer.html#af7eb7ccc3e5863fe580f1b8dceac5d88">tvm::SHashReducer</a>
+: <a class="el" href="classtvm_1_1SHashReducer.html#acb4d90cb74f617620d0027649adf8f17">tvm::SHashReducer</a>
 </li>
 <li>ShouldLinkParameters()
 : <a class="el" href="classtvm_1_1IRModuleNode.html#a6bb288d971d067764448a2c715702a8c">tvm::IRModuleNode</a>
@@ -617,7 +620,7 @@ $(function() {
 , <a class="el" href="classtvm_1_1TracedArray.html#a52b30a89b5c68811d0789f9f32b12627">tvm::TracedArray&lt; T &gt;</a>
 </li>
 <li>SizeVar()
-: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05">tvm::tir::SizeVar</a>
+: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd">tvm::tir::SizeVar</a>
 </li>
 <li>Slice()
 : <a class="el" href="classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3">tvm::te::Tensor::Slice</a>
@@ -629,7 +632,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1parser_1_1Source.html#a0ef9f726abcc6c4c9e81b3a257055df8">tvm::parser::Source</a>
 </li>
 <li>SourceMap()
-: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#afc48463cc0967ab79876178613a5aff2">tvm::parser::SourceMap</a>
+: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#a5fd3cc7160f57f7adcf1a0633603c72e">tvm::parser::SourceMap</a>
 </li>
 <li>SpaceGenerator()
 : <a class="el" href="classtvm_1_1meta__schedule_1_1SpaceGenerator.html#a4f11a841acdf7a66893eeefc1feb04ae">tvm::meta_schedule::SpaceGenerator</a>
@@ -664,8 +667,8 @@ $(function() {
 : <a class="el" href="classtvm_1_1auto__scheduler_1_1SplitStep.html#a184575a8029d77f7a3bee23d81141df5">tvm::auto_scheduler::SplitStep</a>
 </li>
 <li>Stage()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#af0643fe8c1298451c9a322f915c48843">tvm::auto_scheduler::Stage</a>
-, <a class="el" href="classtvm_1_1te_1_1Stage.html#aa6ace38b6312e42aaf9389c8749ae0a4">tvm::te::Stage</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#a39ffbb1b4e189180bc4067e74965f42b">tvm::auto_scheduler::Stage</a>
+, <a class="el" href="classtvm_1_1te_1_1Stage.html#afec82602b9321c489b88632a005335f8">tvm::te::Stage</a>
 </li>
 <li>Start()
 : <a class="el" href="classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88">tvm::runtime::profiling::MetricCollectorNode</a>
@@ -743,7 +746,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1runtime_1_1DeviceAPI.html#ac29b9295c432a87658392872c644864f">tvm::runtime::DeviceAPI</a>
 </li>
 <li>String()
-: <a class="el" href="classtvm_1_1runtime_1_1String.html#ac5d930b522e9fef9c07e51819d96d2f3">tvm::runtime::String</a>
+: <a class="el" href="classtvm_1_1runtime_1_1String.html#acf549b3c43142639879e0fc31ea5cd77">tvm::runtime::String</a>
 </li>
 <li>StringImm()
 : <a class="el" href="classtvm_1_1tir_1_1StringImm.html#a0f2830290e055f677c5d5dea98aab726">tvm::tir::StringImm</a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index 3814756e4..b0d462bd8 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -1132,7 +1132,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a5882f7eda112e825eb5a87e45aeb85b0">tvm::runtime::TVMArgsSetter</a>
 </li>
 <li>TVMArgValue()
-: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a987b2fb283cea5484d4655e3f711c046">tvm::runtime::TVMArgValue</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a5fbd71750e5bbba6edc9094178af9276">tvm::runtime::TVMArgValue</a>
 </li>
 <li>TVMMovableArgValue_()
 : <a class="el" href="classtvm_1_1runtime_1_1TVMMovableArgValue__.html#a8eca9048535541f374a5806f9648131b">tvm::runtime::TVMMovableArgValue_</a>
@@ -1170,10 +1170,10 @@ $(function() {
 : <a class="el" href="classtvm_1_1TypeData.html#a0a98fd1095812379d2bd1337db1511c1">tvm::TypeData</a>
 </li>
 <li>TypedEnvFunc()
-: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">tvm::TypedEnvFunc&lt; R(Args...)&gt;</a>
+: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc&lt; R(Args...)&gt;</a>
 </li>
 <li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8941c80982a1b2a289440f3c79bb0ac8">tvm::runtime::TypedPackedFunc&lt; R(Args...)&gt;</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a4abadc6786dd14a3aed6e2b5b342d1d6">tvm::runtime::TypedPackedFunc&lt; R(Args...)&gt;</a>
 </li>
 <li>TypeIndex2Key()
 : <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1196,7 +1196,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1TypeRelation.html#ac26b1897eab8197ed26606ab81b7403b">tvm::TypeRelation</a>
 </li>
 <li>TypeReporter()
-: <a class="el" href="classtvm_1_1TypeReporter.html#a8e7e05a07f9f7ad9bea91f27afac9051">tvm::TypeReporter</a>
+: <a class="el" href="classtvm_1_1TypeReporter.html#aa3dc38a3c84d324d0b3a9f358460a091">tvm::TypeReporter</a>
 </li>
 <li>TypeVar()
 : <a class="el" href="classtvm_1_1TypeVar.html#adf5ef8e89d162735519b5d125c89e3e3">tvm::TypeVar</a>
diff --git a/docs/reference/api/doxygen/functions_func_u.html b/docs/reference/api/doxygen/functions_func_u.html
index 88e21c212..31fb74a2d 100644
--- a/docs/reference/api/doxygen/functions_func_u.html
+++ b/docs/reference/api/doxygen/functions_func_u.html
@@ -103,7 +103,7 @@ $(function() {
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html#ae35b2b678760b8da57a43d3ae9c24da5">tvm::auto_scheduler::CostModelNode</a>
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a2d7849df6c7dbe93bf363c1d9f860a26">tvm::auto_scheduler::PythonBasedModelNode</a>
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a7febac6c05d8e2d407f466467769ee32">tvm::auto_scheduler::RandomModelNode</a>
-, <a class="el" href="classtvm_1_1IRModuleNode.html#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">tvm::IRModuleNode</a>
 , <a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html#a1bba32eba84db583fe90d1a5bce085f1">tvm::meta_schedule::CostModelNode</a>
 , <a class="el" href="classtvm_1_1meta__schedule_1_1PyCostModelNode.html#a970b00b0eb1bf6b88eea2711b58c4d1d">tvm::meta_schedule::PyCostModelNode</a>
 </li>
diff --git a/docs/reference/api/doxygen/functions_m.html b/docs/reference/api/doxygen/functions_m.html
index 63d1e1cf7..0f1d2c239 100644
--- a/docs/reference/api/doxygen/functions_m.html
+++ b/docs/reference/api/doxygen/functions_m.html
@@ -342,7 +342,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536">tvm::DiagnosticContextNode</a>
 </li>
 <li>Module()
-: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9">tvm::runtime::Module</a>
+: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4">tvm::runtime::Module</a>
 , <a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d">tvm::runtime::ModuleNode</a>
 </li>
 <li>module_handle
diff --git a/docs/reference/api/doxygen/functions_q.html b/docs/reference/api/doxygen/functions_q.html
index b177dfa2a..45344fea4 100644
--- a/docs/reference/api/doxygen/functions_q.html
+++ b/docs/reference/api/doxygen/functions_q.html
@@ -62,13 +62,13 @@ $(function() {
 
 <h3><a id="index_q"></a>- q -</h3><ul>
 <li>QueryIRModule()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0">tvm::meta_schedule::DatabaseNode</a>
 </li>
 <li>QuerySchedule()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020">tvm::meta_schedule::DatabaseNode</a>
 </li>
 <li>QueryTuningRecord()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178">tvm::meta_schedule::DatabaseNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612">tvm::meta_schedule::DatabaseNode</a>
 </li>
 </ul>
 </div><!-- contents -->
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index d80979c23..3b4ab797e 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -152,6 +152,9 @@ $(function() {
 <li>ScheduleFn()
 : <a class="el" href="classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa6dd3790fd633db9046015c69aca3735">tvm::meta_schedule::SpaceGenerator</a>
 </li>
+<li>ScheduleFnDatabase()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">tvm::meta_schedule::Database</a>
+</li>
 <li>ScheduleState()
 : <a class="el" href="classtvm_1_1tir_1_1ScheduleState.html#a1f8d0fc95f0d91de0aba3142a57552ad">tvm::tir::ScheduleState</a>
 </li>
@@ -773,7 +776,7 @@ $(function() {
 : <a class="el" href="structtvm_1_1relay_1_1MultiBoxPriorAttrs.html#ad6d089344fa741021584222ffa70a451">tvm::relay::MultiBoxPriorAttrs</a>
 </li>
 <li>SizeVar()
-: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05">tvm::tir::SizeVar</a>
+: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd">tvm::tir::SizeVar</a>
 </li>
 <li>Slice()
 : <a class="el" href="classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3">tvm::te::Tensor::Slice</a>
@@ -818,7 +821,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1script_1_1printer_1_1DocNode.html#a29e21c8f39639d1d30697971267847a8">tvm::script::printer::DocNode</a>
 </li>
 <li>SourceMap()
-: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#a5fd3cc7160f57f7adcf1a0633603c72e">tvm::parser::SourceMap</a>
+: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#afc48463cc0967ab79876178613a5aff2">tvm::parser::SourceMap</a>
 </li>
 <li>space_generator
 : <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a7bdfdd48530bfe380c5f6c143158a07f">tvm::meta_schedule::TuneContextNode</a>
@@ -913,8 +916,8 @@ $(function() {
 : <a class="el" href="structtvm_1_1relay_1_1DeviceCopyAttrs.html#aac5b2c76325a587bbefaa5af87b4138f">tvm::relay::DeviceCopyAttrs</a>
 </li>
 <li>Stage()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#a39ffbb1b4e189180bc4067e74965f42b">tvm::auto_scheduler::Stage</a>
-, <a class="el" href="classtvm_1_1te_1_1Stage.html#aa6ace38b6312e42aaf9389c8749ae0a4">tvm::te::Stage</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#af0643fe8c1298451c9a322f915c48843">tvm::auto_scheduler::Stage</a>
+, <a class="el" href="classtvm_1_1te_1_1Stage.html#afec82602b9321c489b88632a005335f8">tvm::te::Stage</a>
 </li>
 <li>stage_id
 : <a class="el" href="classtvm_1_1auto__scheduler_1_1StepNode.html#afcc7aaf263348f66139307affbfcee09">tvm::auto_scheduler::StepNode</a>
@@ -997,7 +1000,7 @@ $(function() {
 : <a class="el" href="classtvm_1_1script_1_1printer_1_1StmtDoc.html#adec8d59e41d8a4093fb310089bf2c3ba">tvm::script::printer::StmtDoc</a>
 </li>
 <li>StmtNode()
-: <a class="el" href="classtvm_1_1tir_1_1StmtNode.html#a79e21b14d3ab57209577bf4a8f694a87">tvm::tir::StmtNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1StmtNode.html#a67693c4e97ae49890ea74605fe1b1f74">tvm::tir::StmtNode</a>
 </li>
 <li>stmts
 : <a class="el" href="classtvm_1_1script_1_1printer_1_1StmtBlockDocNode.html#a17862bcb50fd1ef49cd9a47f065e612c">tvm::script::printer::StmtBlockDocNode</a>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index 2e6d5e34b..dbe7fec74 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -1341,7 +1341,7 @@ $(function() {
 <li>TVMPODValue_
 : <a class="el" href="classtvm_1_1runtime_1_1NDArray.html#a9a9fd94393cfd7d4b6e6029348e3e19a">tvm::runtime::NDArray</a>
 , <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a9a9fd94393cfd7d4b6e6029348e3e19a">tvm::runtime::ObjectPtr&lt; T &gt;</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMPODValue__.html#a2f46b59a6c1d5eb4575d7f583b5f1a0c">tvm::runtime::TVMPODValue_</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMPODValue__.html#afe1837bdbafe8341c2031c5cebcf6e74">tvm::runtime::TVMPODValue_</a>
 </li>
 <li>TVMRetValue
 : <a class="el" href="classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb">tvm::BaseAttrsNode</a>
@@ -1428,10 +1428,10 @@ $(function() {
 : <a class="el" href="classtvm_1_1TypeData.html#a0a98fd1095812379d2bd1337db1511c1">tvm::TypeData</a>
 </li>
 <li>TypedEnvFunc()
-: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">tvm::TypedEnvFunc&lt; R(Args...)&gt;</a>
+: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc&lt; R(Args...)&gt;</a>
 </li>
 <li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa3663a440db7a6951abd767109b9bf90">tvm::runtime::TypedPackedFunc&lt; R(Args...)&gt;</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8941c80982a1b2a289440f3c79bb0ac8">tvm::runtime::TypedPackedFunc&lt; R(Args...)&gt;</a>
 </li>
 <li>TypeIndex2Key()
 : <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
diff --git a/docs/reference/api/doxygen/functions_u.html b/docs/reference/api/doxygen/functions_u.html
index 73373a1b4..981d4ef19 100644
--- a/docs/reference/api/doxygen/functions_u.html
+++ b/docs/reference/api/doxygen/functions_u.html
@@ -119,7 +119,7 @@ $(function() {
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html#ae35b2b678760b8da57a43d3ae9c24da5">tvm::auto_scheduler::CostModelNode</a>
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a2d7849df6c7dbe93bf363c1d9f860a26">tvm::auto_scheduler::PythonBasedModelNode</a>
 , <a class="el" href="classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a7febac6c05d8e2d407f466467769ee32">tvm::auto_scheduler::RandomModelNode</a>
-, <a class="el" href="classtvm_1_1IRModuleNode.html#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">tvm::IRModuleNode</a>
 , <a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html#a1bba32eba84db583fe90d1a5bce085f1">tvm::meta_schedule::CostModelNode</a>
 , <a class="el" href="classtvm_1_1meta__schedule_1_1PyCostModelNode.html#a970b00b0eb1bf6b88eea2711b58c4d1d">tvm::meta_schedule::PyCostModelNode</a>
 </li>
diff --git a/docs/reference/api/doxygen/search/all_12.js b/docs/reference/api/doxygen/search/all_12.js
index d45e78a54..54bb62ddb 100644
--- a/docs/reference/api/doxygen/search/all_12.js
+++ b/docs/reference/api/doxygen/search/all_12.js
@@ -2,7 +2,7 @@ var searchData=
 [
   ['q_5fmultiply_5fshift',['q_multiply_shift',['../namespacetvm_1_1tir_1_1builtin.html#a0c2ebdcec34d7c79dc8480e5dab8547a',1,'tvm::tir::builtin::q_multiply_shift()'],['../namespacetvm.html#ac788f9eb54a8971596779537afc6c896',1,'tvm::q_multiply_shift()']]],
   ['quantizeattrs',['QuantizeAttrs',['../structtvm_1_1relay_1_1qnn_1_1QuantizeAttrs.html',1,'tvm::relay::qnn']]],
-  ['queryirmodule',['QueryIRModule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6',1,'tvm::meta_schedule::DatabaseNode']]],
-  ['queryschedule',['QuerySchedule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b',1,'tvm::meta_schedule::DatabaseNode']]],
-  ['querytuningrecord',['QueryTuningRecord',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178',1,'tvm::meta_schedule::DatabaseNode']]]
+  ['queryirmodule',['QueryIRModule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0',1,'tvm::meta_schedule::DatabaseNode']]],
+  ['queryschedule',['QuerySchedule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020',1,'tvm::meta_schedule::DatabaseNode']]],
+  ['querytuningrecord',['QueryTuningRecord',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612',1,'tvm::meta_schedule::DatabaseNode']]]
 ];
diff --git a/docs/reference/api/doxygen/search/all_13.js b/docs/reference/api/doxygen/search/all_13.js
index 0a029e786..6b71495eb 100644
--- a/docs/reference/api/doxygen/search/all_13.js
+++ b/docs/reference/api/doxygen/search/all_13.js
@@ -12,7 +12,7 @@ var searchData=
   ['randomcomputelocation',['RandomComputeLocation',['../classtvm_1_1meta__schedule_1_1ScheduleRule.html#a1bf485537817533eaf711226f687778c',1,'tvm::meta_schedule::ScheduleRule']]],
   ['randommodel',['RandomModel',['../classtvm_1_1auto__scheduler_1_1RandomModel.html',1,'tvm::auto_scheduler::RandomModel'],['../classtvm_1_1auto__scheduler_1_1RandomModel.html#aa456abf1dc91cbf76935189424d8954f',1,'tvm::auto_scheduler::RandomModel::RandomModel()'],['../classtvm_1_1auto__scheduler_1_1RandomModel.html#ac2b355e61135f2ff57d4f96fe2fba845',1,'tvm::auto_scheduler::RandomModel::RandomModel(::tvm::runtime::ObjectPtr&lt;::tvm::runtime::Object &gt; n)']]],
   ['randommodelnode',['RandomModelNode',['../classtvm_1_1auto__scheduler_1_1RandomModelNode.html',1,'tvm::auto_scheduler']]],
-  ['range',['Range',['../classtvm_1_1Range.html',1,'tvm::Range'],['../classtvm_1_1auto__scheduler_1_1IteratorNode.html#a2751c3164971b3154ffc506e3aebaf91',1,'tvm::auto_scheduler::IteratorNode::range()'],['../classtvm_1_1Range.html#a9d58cccc53897fee0c80ab1437da1f0f',1,'tvm::Range::Range()']]],
+  ['range',['Range',['../classtvm_1_1Range.html',1,'tvm::Range'],['../classtvm_1_1Range.html#a9d58cccc53897fee0c80ab1437da1f0f',1,'tvm::Range::Range()'],['../classtvm_1_1auto__scheduler_1_1IteratorNode.html#a2751c3164971b3154ffc506e3aebaf91',1,'tvm::auto_scheduler::IteratorNode::range()']]],
   ['rangenode',['RangeNode',['../classtvm_1_1RangeNode.html',1,'tvm::RangeNode'],['../classtvm_1_1RangeNode.html#ab845f7ed4ed85e360b730df3450d1aab',1,'tvm::RangeNode::RangeNode()'],['../classtvm_1_1RangeNode.html#a4bbc33969cb484c20306da1d2b9fa1fd',1,'tvm::RangeNode::RangeNode(PrimExpr min, PrimExpr extent, Span span=Span())']]],
   ['ranges',['ranges',['../classtvm_1_1arith_1_1IntConstraintsNode.html#ab23d4d806766c88b0df69dbfb5ebd63c',1,'tvm::arith::IntConstraintsNode']]],
   ['rate',['rate',['../structtvm_1_1relay_1_1DropoutAttrs.html#a0b5a52c24a1be53dbb122a1df9fe22af',1,'tvm::relay::DropoutAttrs']]],
@@ -119,7 +119,7 @@ var searchData=
   ['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
   ['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
   ['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
-  ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
+  ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
   ['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html',1,'tvm::auto_scheduler::ReorderStep'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array&lt; Integer &gt; &amp;after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
   ['reorderstepnode',['ReorderStepNode',['../classtvm_1_1auto__scheduler_1_1ReorderStepNode.html',1,'tvm::auto_scheduler']]],
   ['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
@@ -194,7 +194,7 @@ var searchData=
   ['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
   ['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a1836b2278bc24fdc227c490896d92980',1,'tvm::meta_schedule::Postproc']]],
   ['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
-  ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
+  ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
   ['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html',1,'tvm::auto_scheduler::RfactorStep'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
   ['rfactorstepnode',['RfactorStepNode',['../classtvm_1_1auto__scheduler_1_1RfactorStepNode.html',1,'tvm::auto_scheduler']]],
   ['rhs',['rhs',['../classtvm_1_1relay_1_1ClauseNode.html#a93217eeea15c1f7c1a659da3da86d3bd',1,'tvm::relay::ClauseNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1AssignDocNode.html#a436fcace00d445213fc367ece59c4067',1,'tvm::script::printer::AssignDocNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1ForDocNode.html#aa72614136675287310ea08520f596642',1,'tvm::script::printer::ForDocNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1ScopeDocNode.html#abf3636ac2820118a3d48f2fea32b2b0b' [...]
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index caefbc3db..80b3bccf2 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -51,6 +51,7 @@ var searchData=
   ['scheduledebugmask',['ScheduleDebugMask',['../namespacetvm_1_1tir.html#a230fa4eb6152910f125f636dab3bd4e0',1,'tvm::tir']]],
   ['scheduleerrorrenderlevel',['ScheduleErrorRenderLevel',['../namespacetvm_1_1tir.html#a9ae244600a5e56c4adc9faf6d88f931e',1,'tvm::tir']]],
   ['schedulefn',['ScheduleFn',['../classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa6dd3790fd633db9046015c69aca3735',1,'tvm::meta_schedule::SpaceGenerator']]],
+  ['schedulefndatabase',['ScheduleFnDatabase',['../classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4',1,'tvm::meta_schedule::Database']]],
   ['schedulenode',['ScheduleNode',['../classtvm_1_1te_1_1ScheduleNode.html',1,'tvm::te::ScheduleNode'],['../classtvm_1_1tir_1_1ScheduleNode.html',1,'tvm::tir::ScheduleNode']]],
   ['scheduleops',['ScheduleOps',['../namespacetvm_1_1te.html#ac5f0fdd7c2d3deb15b7855c5b1ff1aff',1,'tvm::te']]],
   ['schedulepostproctoprimfunc',['SchedulePostProcToPrimFunc',['../namespacetvm_1_1te.html#a9eb39ad3aa5af348b1b27e755074f525',1,'tvm::te']]],
@@ -219,7 +220,7 @@ var searchData=
   ['singleton',['Singleton',['../classtvm_1_1te_1_1Singleton.html',1,'tvm::te::Singleton'],['../classtvm_1_1te_1_1Singleton.html#a94450b853dcd5e9865546d8c8fe351a1',1,'tvm::te::Singleton::Singleton()']]],
   ['singletonnode',['SingletonNode',['../classtvm_1_1te_1_1SingletonNode.html',1,'tvm::te']]],
   ['sinh',['sinh',['../namespacetvm.html#ad828bc801c73df761c58d9f8877d52ee',1,'tvm::sinh()'],['../namespacetvm_1_1topi.html#af9694f5470ba2cabc19866be3b00fe8d',1,'tvm::topi::sinh()']]],
-  ['size',['size',['../structtvm_1_1relay_1_1Resize1DAttrs.html#afb1175c0ff019e485ed65d98305b5f62',1,'tvm::relay::Resize1DAttrs::size()'],['../structtvm_1_1relay_1_1Resize2DAttrs.html#ab3e26dbbc2dc1da40764832a99459c30',1,'tvm::relay::Resize2DAttrs::size()'],['../structtvm_1_1relay_1_1Resize3DAttrs.html#aab61649fe8417a8a7fbc849090bac083',1,'tvm::relay::Resize3DAttrs::size()'],['../structtvm_1_1relay_1_1LRNAttrs.html#a3758ed1f8a8bcf73008ae1dd2bfa148e',1,'tvm::relay::LRNAttrs::size()'],['.. [...]
+  ['size',['Size',['../classtvm_1_1TensorTypeNode.html#a1f08dac86ae8aea81d058ef64cfd38b4',1,'tvm::TensorTypeNode::Size()'],['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aae5b9ab9f7e497654b90c23a2159a5cc',1,'tvm::meta_schedule::DatabaseNode::Size()'],['../classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0',1,'tvm::meta_schedule::PyDatabaseNode::Size()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1FrameBuffer.html#ae395a0f1c6e79e825aa7a244c74a5d7b',1,' [...]
   ['size_5f',['size_',['../classtvm_1_1runtime_1_1MapNode.html#a2285f106f6afa29f512a7818ad59e9e5',1,'tvm::runtime::MapNode']]],
   ['size_5fbytes',['size_bytes',['../structtvm_1_1tir_1_1usmp_1_1BufferInfoNode.html#a0a5d4bd6072c268df05b90d267b4c0a0',1,'tvm::tir::usmp::BufferInfoNode']]],
   ['size_5fhint_5fbytes',['size_hint_bytes',['../structtvm_1_1PoolInfoNode.html#ac073aeb75bf031ff8687e132bc112f92',1,'tvm::PoolInfoNode::size_hint_bytes()'],['../structtvm_1_1PoolInfoPropertiesNode.html#aed7c5573ffc8db9424e77e3a85cad120',1,'tvm::PoolInfoPropertiesNode::size_hint_bytes()']]],
@@ -265,7 +266,7 @@ var searchData=
   ['spacegeneratornode',['SpaceGeneratorNode',['../classtvm_1_1meta__schedule_1_1SpaceGeneratorNode.html',1,'tvm::meta_schedule']]],
   ['spacegeneratorunion',['SpaceGeneratorUnion',['../classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa13f2244870b18f3e9788d41a400636e',1,'tvm::meta_schedule::SpaceGenerator']]],
   ['spacetobatchndattrs',['SpaceToBatchNDAttrs',['../structtvm_1_1relay_1_1SpaceToBatchNDAttrs.html',1,'tvm::relay']]],
-  ['span',['Span',['../classtvm_1_1Span.html',1,'tvm::Span'],['../classtvm_1_1support_1_1Span.html',1,'tvm::support::Span&lt; T, W &gt;'],['../classtvm_1_1AffineTypeNode.html#aa45c91e3c8ebcff609d10f6a921f3fa2',1,'tvm::AffineTypeNode::span()'],['../classtvm_1_1DiagnosticNode.html#af5469f228f87711ad8bd3f4f78f3bb54',1,'tvm::DiagnosticNode::span()'],['../classtvm_1_1DiagnosticBuilder.html#a52d9cc3cb33e655c5d82af47daa74c66',1,'tvm::DiagnosticBuilder::span()'],['../classtvm_1_1CompileError.htm [...]
+  ['span',['Span',['../classtvm_1_1Span.html',1,'tvm::Span'],['../classtvm_1_1support_1_1Span.html',1,'tvm::support::Span&lt; T, W &gt;'],['../classtvm_1_1Span.html#a5216631b639e8c802263d87d3fe9e5f6',1,'tvm::Span::Span()'],['../classtvm_1_1support_1_1Span.html#a77653730a2542edf93b7c4413a72f3ec',1,'tvm::support::Span::Span(T *begin, int num_elements)'],['../classtvm_1_1support_1_1Span.html#a3c22dd06856e7029e7107adf38eb72f5',1,'tvm::support::Span::Span(T *begin, T *end)'],['../classtvm_1_1 [...]
   ['span_2eh',['span.h',['../ir_2span_8h.html',1,'(Global Namespace)'],['../support_2span_8h.html',1,'(Global Namespace)']]],
   ['spannode',['SpanNode',['../classtvm_1_1SpanNode.html',1,'tvm::SpanNode'],['../namespacetvm_1_1relay.html#a7d0fa6578e97d0d64b08865f94f04827',1,'tvm::relay::SpanNode()']]],
   ['sparse_5flhs',['sparse_lhs',['../structtvm_1_1relay_1_1SparseDenseAttrs.html#ae52d5465cb3421f342607abcc1cb1d5c',1,'tvm::relay::SparseDenseAttrs']]],
@@ -280,7 +281,7 @@ var searchData=
   ['specialize',['Specialize',['../namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782',1,'tvm::tir']]],
   ['specializedcondition',['SpecializedCondition',['../classtvm_1_1te_1_1SpecializedCondition.html',1,'tvm::te::SpecializedCondition'],['../classtvm_1_1te_1_1SpecializedCondition.html#a48d119ee1c6033929a5592cfc2592e60',1,'tvm::te::SpecializedCondition::SpecializedCondition()']]],
   ['specializedconditionnode',['SpecializedConditionNode',['../classtvm_1_1te_1_1SpecializedConditionNode.html',1,'tvm::te']]],
-  ['split',['Split',['../classtvm_1_1te_1_1Split.html',1,'tvm::te::Split'],['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_schedule [...]
+  ['split',['Split',['../classtvm_1_1te_1_1Split.html',1,'tvm::te::Split'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_scheduler::State::split()'],['../classtvm_1_1te_1_1Stage.html#a5a7cd562be59b68a187ad97085a3425d',1,'tvm::te::Stage::split()'],['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split( [...]
   ['split_5fby_5fnparts',['split_by_nparts',['../classtvm_1_1te_1_1Stage.html#a51432f38d9ec4792a2525023179ae604',1,'tvm::te::Stage']]],
   ['split_5fsections',['split_sections',['../namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619',1,'tvm::topi']]],
   ['splitargs',['SplitArgs',['../namespacetvm_1_1relay_1_1transform.html#a2425d757b896168a109498e8d34ba960',1,'tvm::relay::transform']]],
@@ -321,13 +322,13 @@ var searchData=
   ['stagenode',['StageNode',['../classtvm_1_1auto__scheduler_1_1StageNode.html',1,'tvm::auto_scheduler::StageNode'],['../classtvm_1_1te_1_1StageNode.html',1,'tvm::te::StageNode']]],
   ['stages',['stages',['../classtvm_1_1auto__scheduler_1_1StateNode.html#a881e14990bf228ee3fddb3721c451b9e',1,'tvm::auto_scheduler::StateNode::stages()'],['../classtvm_1_1te_1_1ScheduleNode.html#ab5649969db603d6b7b4d155c0d09cdd5',1,'tvm::te::ScheduleNode::stages()']]],
   ['stagetoaxesmap',['StageToAxesMap',['../namespacetvm_1_1auto__scheduler.html#a8f12e558fc4b8fbb990e7e204c06beeb',1,'tvm::auto_scheduler']]],
-  ['start',['Start',['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88',1,'tvm::runtime::profiling::MetricCollectorNode::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#aee5452075c8e022b8aaa6fb365f68e14 [...]
+  ['start',['start',['../structtvm_1_1relay_1_1ArangeAttrs.html#ae8ae5bc1551b406a4f52395af343c2ce',1,'tvm::relay::ArangeAttrs::start()'],['../classtvm_1_1script_1_1printer_1_1SliceDocNode.html#a16de0189a979a6cf9d8f14b39cb5fb54',1,'tvm::script::printer::SliceDocNode::start()'],['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::S [...]
   ['start_5findex',['start_index',['../namespacetvm_1_1topi_1_1nn.html#a752c4130dac73fd2de0390c5f6b24b15',1,'tvm::topi::nn']]],
   ['startcall',['StartCall',['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#a1fe322f7ba92be44d7e7c8cb184f3833',1,'tvm::runtime::profiling::Profiler']]],
   ['startmessage',['StartMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#acd512b977c6dd888f90c4fd6d2b9500f',1,'tvm::runtime::micro_rpc::Session']]],
   ['startpacket',['StartPacket',['../classtvm_1_1runtime_1_1micro__rpc_1_1Framer.html#ade10d3bd3a26e3b7af881ae134e9a998',1,'tvm::runtime::micro_rpc::Framer']]],
   ['startsession',['StartSession',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a15d3f9ecb8b22bf2d330f6f0a16c5239',1,'tvm::runtime::micro_rpc::Session']]],
-  ['state',['State',['../classtvm_1_1auto__scheduler_1_1State.html',1,'tvm::auto_scheduler::State'],['../classtvm_1_1auto__scheduler_1_1State.html#a9e8198b1f51b42cfbbee4b9f42160749',1,'tvm::auto_scheduler::State::State()'],['../classtvm_1_1auto__scheduler_1_1MeasureInputNode.html#afb23aaf6133189687d2541ec6e1352f4',1,'tvm::auto_scheduler::MeasureInputNode::state()'],['../classtvm_1_1tir_1_1ScheduleNode.html#abb3612c2598fa2d3ee0e6e3fc3de8a26',1,'tvm::tir::ScheduleNode::state()']]],
+  ['state',['State',['../classtvm_1_1auto__scheduler_1_1State.html',1,'tvm::auto_scheduler::State'],['../classtvm_1_1auto__scheduler_1_1MeasureInputNode.html#afb23aaf6133189687d2541ec6e1352f4',1,'tvm::auto_scheduler::MeasureInputNode::state()'],['../classtvm_1_1tir_1_1ScheduleNode.html#abb3612c2598fa2d3ee0e6e3fc3de8a26',1,'tvm::tir::ScheduleNode::state()'],['../classtvm_1_1auto__scheduler_1_1State.html#a9e8198b1f51b42cfbbee4b9f42160749',1,'tvm::auto_scheduler::State::State()']]],
   ['state_2eh',['state.h',['../state_8h.html',1,'']]],
   ['state_5fplaceholder',['state_placeholder',['../classtvm_1_1te_1_1ScanOpNode.html#a69105f6a84dd4fb912a16bfaa68aebf6',1,'tvm::te::ScanOpNode']]],
   ['statenode',['StateNode',['../classtvm_1_1auto__scheduler_1_1StateNode.html',1,'tvm::auto_scheduler']]],
diff --git a/docs/reference/api/doxygen/search/all_15.js b/docs/reference/api/doxygen/search/all_15.js
index c6aff272a..d6b0fa9d6 100644
--- a/docs/reference/api/doxygen/search/all_15.js
+++ b/docs/reference/api/doxygen/search/all_15.js
@@ -71,7 +71,7 @@ var searchData=
   ['te',['te',['../namespacetvm_1_1te.html',1,'tvm']]],
   ['tempexpr',['TempExpr',['../classtvm_1_1relay_1_1TempExpr.html',1,'tvm::relay']]],
   ['tempexprnode',['TempExprNode',['../classtvm_1_1relay_1_1TempExprNode.html',1,'tvm::relay']]],
-  ['tensor',['Tensor',['../classtvm_1_1te_1_1Tensor.html',1,'tvm::te::Tensor'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a22de469ea5521ba12e14f1e8181bae56',1,'tvm::runtime::vm::Instruction::tensor()'],['../classtvm_1_1te_1_1Tensor.html#afc8d8e74d1c840359661b39514d6fecf',1,'tvm::te::Tensor::Tensor()']]],
+  ['tensor',['Tensor',['../classtvm_1_1te_1_1Tensor.html',1,'tvm::te::Tensor'],['../classtvm_1_1te_1_1Tensor.html#afc8d8e74d1c840359661b39514d6fecf',1,'tvm::te::Tensor::Tensor()'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a22de469ea5521ba12e14f1e8181bae56',1,'tvm::runtime::vm::Instruction::tensor()']]],
   ['tensor_2eh',['tensor.h',['../tensor_8h.html',1,'']]],
   ['tensor_5fintrin',['tensor_intrin',['../classtvm_1_1te_1_1IterVarAttrNode.html#a6a0d96bbebfd716f851b2ad01738cb3f',1,'tvm::te::IterVarAttrNode']]],
   ['tensor_5fintrin_2eh',['tensor_intrin.h',['../tensor__intrin_8h.html',1,'']]],
@@ -90,7 +90,7 @@ var searchData=
   ['tensorintrincall',['TensorIntrinCall',['../classtvm_1_1te_1_1TensorIntrinCall.html',1,'tvm::te::TensorIntrinCall'],['../classtvm_1_1te_1_1TensorIntrinCall.html#a91c10074ce6babeba78fe72a0aab4b52',1,'tvm::te::TensorIntrinCall::TensorIntrinCall()']]],
   ['tensorintrincallnode',['TensorIntrinCallNode',['../classtvm_1_1te_1_1TensorIntrinCallNode.html',1,'tvm::te']]],
   ['tensorintrinnode',['TensorIntrinNode',['../classtvm_1_1te_1_1TensorIntrinNode.html',1,'tvm::te::TensorIntrinNode'],['../classtvm_1_1tir_1_1TensorIntrinNode.html',1,'tvm::tir::TensorIntrinNode'],['../classtvm_1_1te_1_1TensorIntrinNode.html#ad59e7f2b881fc798a8c64fd3959f929c',1,'tvm::te::TensorIntrinNode::TensorIntrinNode()']]],
-  ['tensorize',['Tensorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &amp;loop_rv, const String &amp;intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &amp;block_rv, const String &amp;intrin)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()']]],
+  ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &amp;loop_rv, const String &amp;intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &amp;block_rv, const String &amp;intrin)=0']]],
   ['tensornode',['TensorNode',['../classtvm_1_1te_1_1TensorNode.html',1,'tvm::te::TensorNode'],['../classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8',1,'tvm::te::TensorNode::TensorNode()']]],
   ['tensors',['tensors',['../classtvm_1_1auto__scheduler_1_1ComputeDAGNode.html#afc71b9ecc0d6b82a5c2ab3250f01514b',1,'tvm::auto_scheduler::ComputeDAGNode::tensors()'],['../classtvm_1_1te_1_1TensorIntrinCallNode.html#a92b543750ea55b9cfd6852139e2ddbd6',1,'tvm::te::TensorIntrinCallNode::tensors()']]],
   ['tensortype',['TensorType',['../classtvm_1_1TensorType.html',1,'tvm::TensorType'],['../classtvm_1_1TensorType.html#ade4460e9b02b42757a83808dec478b87',1,'tvm::TensorType::TensorType()'],['../namespacetvm_1_1relay.html#a52c13723bba53f4953dfd10c34d480f8',1,'tvm::relay::TensorType()']]],
@@ -156,7 +156,7 @@ var searchData=
   ['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
   ['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
   ['tparent',['TParent',['../classtvm_1_1OpAttrMap.html#a316480ca7450209650fc1a62f7ce4a14',1,'tvm::OpAttrMap::TParent()'],['../classtvm_1_1TargetKindAttrMap.html#a37eb6bfb0d881cf897147b17ff7d3265',1,'tvm::TargetKindAttrMap::TParent()']]],
-  ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array&lt; Instruction &gt; insts, Map&lt; Instruction, ObjectRef &gt; decisions)'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::tra [...]
+  ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::trace()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb [...]
   ['trace_2eh',['trace.h',['../trace_8h.html',1,'']]],
   ['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
   ['traced_5fobject_2eh',['traced_object.h',['../traced__object_8h.html',1,'']]],
@@ -470,7 +470,7 @@ var searchData=
   ['tvmsystemlibentrypoint',['TVMSystemLibEntryPoint',['../runtime_2crt_2module_8h.html#a32fdb5a1df93075a184a36d2549833fa',1,'module.h']]],
   ['tvmtensorinfo',['TVMTensorInfo',['../structTVMTensorInfo.html',1,'']]],
   ['tvmvalue',['TVMValue',['../unionTVMValue.html',1,'']]],
-  ['type',['Type',['../classtvm_1_1Type.html',1,'tvm::Type'],['../structtvm_1_1detail_1_1is__specialized.html#a3ea7783c457d7ddc82100674292724f4',1,'tvm::detail::is_specialized::type()'],['../structtvm_1_1detail_1_1is__specialized_3_01Container_3_01Args_8_8_8_01_4_00_01Container_01_4.html#a8dee3a1604498d6bc64948f1c0d19dc2',1,'tvm::detail::is_specialized&lt; Container&lt; Args... &gt;, Container &gt;::type()'],['../classtvm_1_1relay_1_1TypePatternNode.html#aab5faa2a58862707b8dc18b59cccac19 [...]
+  ['type',['Type',['../classtvm_1_1Type.html',1,'tvm::Type'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tvm::detail::TracedObjectWrapperSelector&lt; T, false &gt;::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01true_01_4.html#ab1da2c0d7b63a70812c5f27f60aeb695',1,'tvm::detail::TracedObjectWrapperSelector&lt; T, true &gt;::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelect [...]
   ['type_2eh',['type.h',['../ir_2type_8h.html',1,'(Global Namespace)'],['../relay_2type_8h.html',1,'(Global Namespace)']]],
   ['type_5fannotation',['type_annotation',['../classtvm_1_1relay_1_1VarNode.html#a79a56885eaf2a9326ff490164a5c1f0e',1,'tvm::relay::VarNode::type_annotation()'],['../classtvm_1_1tir_1_1VarNode.html#a7a84c6d137a79e9a5b9c4b6183f18353',1,'tvm::tir::VarNode::type_annotation()']]],
   ['type_5fargs',['type_args',['../classtvm_1_1relay_1_1CallNode.html#ad23d97a6ae1cc1bea903d4c714f811d6',1,'tvm::relay::CallNode']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index cea508f3d..c2f930cf4 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -24,9 +24,9 @@ var searchData=
   ['unknownattributeaccesspathnode',['UnknownAttributeAccessPathNode',['../classtvm_1_1UnknownAttributeAccessPathNode.html',1,'tvm::UnknownAttributeAccessPathNode'],['../classtvm_1_1UnknownAttributeAccessPathNode.html#a1882e9e591466a2785acc761dc63d56e',1,'tvm::UnknownAttributeAccessPathNode::UnknownAttributeAccessPathNode()']]],
   ['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
   ['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
-  ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
+  ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
   ['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
-  ['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
+  ['update',['update',['../classtvm_1_1te_1_1ScanOpNode.html#ace2bf7e43cd4197324ec6363626fc60a',1,'tvm::te::ScanOpNode::update()'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::a [...]
   ['update_5ffunc',['update_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#ade9364c152a36501d4f24fa4f0111519',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
   ['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
   ['updateiters',['UpdateIters',['../classtvm_1_1auto__scheduler_1_1AttachMap.html#ab45b991ef2bcfb1bc191601aac42e778',1,'tvm::auto_scheduler::AttachMap']]],
diff --git a/docs/reference/api/doxygen/search/all_17.js b/docs/reference/api/doxygen/search/all_17.js
index 02a86886b..d9501da52 100644
--- a/docs/reference/api/doxygen/search/all_17.js
+++ b/docs/reference/api/doxygen/search/all_17.js
@@ -18,7 +18,7 @@ var searchData=
   ['values',['values',['../structTVMArgs.html#ab2d2a8c794bc11fdb56b294e711ff63c',1,'TVMArgs::values()'],['../classtvm_1_1runtime_1_1TVMArgs.html#a3b99059e2f1ad08c99b42b5bee82752f',1,'tvm::runtime::TVMArgs::values()'],['../classtvm_1_1script_1_1printer_1_1DictDocNode.html#a08d71431d889cd4588d57c06c12140c4',1,'tvm::script::printer::DictDocNode::values()']]],
   ['values_5fcount',['values_count',['../structTVMArgs.html#afa042427dc87d770d0def130f497f3f5',1,'TVMArgs']]],
   ['valuetypeinfomaker',['ValueTypeInfoMaker',['../structtvm_1_1detail_1_1ValueTypeInfoMaker.html',1,'tvm::detail']]],
-  ['var',['Var',['../classtvm_1_1tir_1_1Var.html',1,'tvm::tir::Var'],['../classtvm_1_1relay_1_1Var.html',1,'tvm::relay::Var'],['../classtvm_1_1relay_1_1PatternVarNode.html#acfa1269806fbf19e7badd424c19c64bf',1,'tvm::relay::PatternVarNode::var()'],['../classtvm_1_1relay_1_1LetPatternNode.html#aff0c6dec182a3173fe0cb601a5b74ed1',1,'tvm::relay::LetPatternNode::var()'],['../classtvm_1_1relay_1_1LetNode.html#a3a841faeeb71a7e59f99feffb182a7c1',1,'tvm::relay::LetNode::var()'],['../classtvm_1_1tir [...]
+  ['var',['Var',['../classtvm_1_1tir_1_1Var.html',1,'tvm::tir::Var'],['../classtvm_1_1relay_1_1Var.html',1,'tvm::relay::Var'],['../classtvm_1_1relay_1_1Var.html#a06ef8ae1d07a5b8a3c25ca7775d17762',1,'tvm::relay::Var::Var(String name_hint, Type type_annotation, Span span=Span())'],['../classtvm_1_1relay_1_1Var.html#a45372a62057ee9332a391e29845505ff',1,'tvm::relay::Var::Var(Id vid, Type type_annotation, Span span=Span())'],['../classtvm_1_1tir_1_1Var.html#a21ba7568a83bfc2a5896f9e0ff181129', [...]
   ['var_2eh',['var.h',['../var_8h.html',1,'']]],
   ['var_5ftable_2eh',['var_table.h',['../var__table_8h.html',1,'']]],
   ['vardefframe',['VarDefFrame',['../classtvm_1_1script_1_1printer_1_1VarDefFrame.html',1,'tvm::script::printer::VarDefFrame'],['../classtvm_1_1script_1_1printer_1_1VarDefFrame.html#a8094608662f9111d64ca3eca3b11673a',1,'tvm::script::printer::VarDefFrame::VarDefFrame()']]],
diff --git a/docs/reference/api/doxygen/search/all_18.js b/docs/reference/api/doxygen/search/all_18.js
index 37489c02b..ec7a0a551 100644
--- a/docs/reference/api/doxygen/search/all_18.js
+++ b/docs/reference/api/doxygen/search/all_18.js
@@ -33,7 +33,7 @@ var searchData=
   ['withframe',['WithFrame',['../classtvm_1_1script_1_1printer_1_1IRDocsifierNode.html#aeb321e859e30f7a3917a4ca8db71d472',1,'tvm::script::printer::IRDocsifierNode']]],
   ['withhost',['WithHost',['../classtvm_1_1Target.html#a509ce63995f082c80742ea5ca6ac112f',1,'tvm::Target']]],
   ['withoutattr',['WithoutAttr',['../namespacetvm.html#a7e2bc626db8be997b1562c79df3d9e11',1,'tvm']]],
-  ['workload',['Workload',['../classtvm_1_1meta__schedule_1_1Workload.html',1,'tvm::meta_schedule::Workload'],['../classtvm_1_1meta__schedule_1_1Workload.html#a21ccf9c956b82d50a2579f1c0f592fd0',1,'tvm::meta_schedule::Workload::Workload(IRModule mod)'],['../classtvm_1_1meta__schedule_1_1Workload.html#a8880877517679c82ae63520e28d5e1d8',1,'tvm::meta_schedule::Workload::Workload(IRModule mod, THashCode shash)'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a42c87f1ec62dae6806c3fe9 [...]
+  ['workload',['Workload',['../classtvm_1_1meta__schedule_1_1Workload.html',1,'tvm::meta_schedule::Workload'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a42c87f1ec62dae6806c3fe9629c5e7f0',1,'tvm::meta_schedule::TuningRecordNode::workload()'],['../classtvm_1_1meta__schedule_1_1Workload.html#a21ccf9c956b82d50a2579f1c0f592fd0',1,'tvm::meta_schedule::Workload::Workload(IRModule mod)'],['../classtvm_1_1meta__schedule_1_1Workload.html#a8880877517679c82ae63520e28d5e1d8',1,'tvm::me [...]
   ['workload_5fkey',['workload_key',['../classtvm_1_1auto__scheduler_1_1SearchTaskNode.html#a20045d677ba2bc5c5ce461e78543b3e2',1,'tvm::auto_scheduler::SearchTaskNode']]],
   ['workloadequal',['WorkloadEqual',['../structtvm_1_1meta__schedule_1_1WorkloadEqual.html',1,'tvm::meta_schedule']]],
   ['workloadhash',['WorkloadHash',['../structtvm_1_1meta__schedule_1_1WorkloadHash.html',1,'tvm::meta_schedule']]],
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index a86c32bfb..ffc7552f7 100644
--- a/docs/reference/api/doxygen/search/all_e.js
+++ b/docs/reference/api/doxygen/search/all_e.js
@@ -175,7 +175,7 @@ var searchData=
   ['microtvmruntimegetoutput',['MicroTVMRuntimeGetOutput',['../microtvm__runtime_8h.html#a76129be7b6de972791a3f9a1b312acfa',1,'microtvm_runtime.h']]],
   ['microtvmruntimerun',['MicroTVMRuntimeRun',['../microtvm__runtime_8h.html#ac43a544f675dd716e8c279c3e41f6e45',1,'microtvm_runtime.h']]],
   ['microtvmruntimesetinput',['MicroTVMRuntimeSetInput',['../microtvm__runtime_8h.html#aa593edc600f4356f2b560702aa01b113',1,'microtvm_runtime.h']]],
-  ['min',['Min',['../classtvm_1_1tir_1_1Min.html',1,'tvm::tir::Min'],['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../classtvm_1_1RangeNode.html#a43d2fb12bb61cf05936a1972d0158b49',1,'tvm::RangeNode::min()'],['../classtvm_1_1tir_1_1ForNode.html#a1d1aa2006328bd84e4911f6d43ceca5c',1,'tvm::tir::ForNode::min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1L [...]
+  ['min',['Min',['../classtvm_1_1tir_1_1Min.html',1,'tvm::tir::Min'],['../classtvm_1_1RangeNode.html#a43d2fb12bb61cf05936a1972d0158b49',1,'tvm::RangeNode::min()'],['../classtvm_1_1tir_1_1ForNode.html#a1d1aa2006328bd84e4911f6d43ceca5c',1,'tvm::tir::ForNode::min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongrue [...]
   ['min_5frepeat_5fms',['min_repeat_ms',['../classtvm_1_1auto__scheduler_1_1ProgramRunnerNode.html#a39a865216db9ed6f57dfb22160cae1ff',1,'tvm::auto_scheduler::ProgramRunnerNode']]],
   ['min_5fvalue',['min_value',['../classtvm_1_1arith_1_1ConstIntBoundNode.html#a0761897bf16ab73b848bf360e9b195a3',1,'tvm::arith::ConstIntBoundNode::min_value()'],['../namespacetvm.html#a3b37fa55ea93d6868751a2441996b072',1,'tvm::min_value()']]],
   ['minimum',['minimum',['../namespacetvm_1_1topi.html#a7ac1dc0d99ce93090a4cdf90ab19d4b8',1,'tvm::topi::minimum(const tvm::PrimExpr &amp;a, const tvm::PrimExpr &amp;b)'],['../namespacetvm_1_1topi.html#a0e19dc06a2b1ecbb83b0942fdf836169',1,'tvm::topi::minimum(const tvm::te::Tensor &amp;A, const tvm::te::Tensor &amp;B, std::string name=&quot;T_&quot; &quot;minimum&quot;, std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a28d4ef4b3426bff237215ce356dd5681',1,'tvm::topi::minimum(con [...]
@@ -201,7 +201,7 @@ var searchData=
   ['modularset',['ModularSet',['../classtvm_1_1arith_1_1ModularSet.html',1,'tvm::arith::ModularSet'],['../classtvm_1_1arith_1_1ModularSet.html#a9f54896d98169246c6a24cc338fde500',1,'tvm::arith::ModularSet::ModularSet()']]],
   ['modularsetanalyzer',['ModularSetAnalyzer',['../classtvm_1_1arith_1_1ModularSetAnalyzer.html',1,'tvm::arith']]],
   ['modularsetnode',['ModularSetNode',['../classtvm_1_1arith_1_1ModularSetNode.html',1,'tvm::arith']]],
-  ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536',1,'tvm::DiagnosticContextNode::module()'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f81 [...]
+  ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4',1,'tvm::runtime::Module::Module(ObjectPtr&lt; Object &gt; n)'],['../classtvm_1_1DiagnosticContextN [...]
   ['module_2eh',['module.h',['../ir_2module_8h.html',1,'(Global Namespace)'],['../runtime_2crt_2module_8h.html',1,'(Global Namespace)'],['../runtime_2module_8h.html',1,'(Global Namespace)']]],
   ['module_5fhandle',['module_handle',['../structTVMAotExecutor.html#a0d4158663d39f79d88d2bc0355c9f1eb',1,'TVMAotExecutor']]],
   ['moduleinternal',['ModuleInternal',['../classtvm_1_1runtime_1_1ModuleNode.html#a2b490c1acecd166b5824e4e96f17c64e',1,'tvm::runtime::ModuleNode']]],
diff --git a/docs/reference/api/doxygen/search/all_f.js b/docs/reference/api/doxygen/search/all_f.js
index c663b1076..5fdc499aa 100644
--- a/docs/reference/api/doxygen/search/all_f.js
+++ b/docs/reference/api/doxygen/search/all_f.js
@@ -3,7 +3,7 @@ var searchData=
   ['n_5ffft',['n_fft',['../structtvm_1_1relay_1_1StftAttrs.html#a4363adcb567c32e1b814ece68d321b3e',1,'tvm::relay::StftAttrs']]],
   ['n_5fparallel',['n_parallel',['../classtvm_1_1auto__scheduler_1_1ProgramBuilderNode.html#aaa056bbd3887751729ca207de8c6c792',1,'tvm::auto_scheduler::ProgramBuilderNode::n_parallel()'],['../classtvm_1_1auto__scheduler_1_1RPCRunnerNode.html#a33dc20205dc39f9b23a4d25939298923',1,'tvm::auto_scheduler::RPCRunnerNode::n_parallel()']]],
   ['n_5fsplit',['n_split',['../classtvm_1_1auto__scheduler_1_1FollowSplitStepNode.html#a365ea1b81b21e382ac350a66326f1b86',1,'tvm::auto_scheduler::FollowSplitStepNode']]],
-  ['name',['Name',['../classtvm_1_1script_1_1ir__builder_1_1IRBuilder.html#ace475c7a85ef508d912beba48ef4183a',1,'tvm::script::ir_builder::IRBuilder::Name()'],['../classtvm_1_1script_1_1ir__builder_1_1details_1_1Namer.html#a22da1264beaa8681bab998a5c597369f',1,'tvm::script::ir_builder::details::Namer::Name()'],['../classtvm_1_1auto__scheduler_1_1IteratorNode.html#afb44a9dd3077356de0545daf7899b402',1,'tvm::auto_scheduler::IteratorNode::name()'],['../classtvm_1_1AttrFieldInfoNode.html#ad918a [...]
+  ['name',['name',['../classtvm_1_1auto__scheduler_1_1IteratorNode.html#afb44a9dd3077356de0545daf7899b402',1,'tvm::auto_scheduler::IteratorNode::name()'],['../classtvm_1_1AttrFieldInfoNode.html#ad918a5375ed2f8db7557ba50f95e026b',1,'tvm::AttrFieldInfoNode::name()'],['../classtvm_1_1EnvFuncNode.html#a02d22636502da6754661d3698ea338ad',1,'tvm::EnvFuncNode::name()'],['../classtvm_1_1instrument_1_1PassInstrumentNode.html#abb8ed0c496c5f9d85b33903a10954cbc',1,'tvm::instrument::PassInstrumentNode [...]
   ['name_5f',['name_',['../classtvm_1_1runtime_1_1Registry.html#a4d8221b67729bafee4c2c5b424ed80ea',1,'tvm::runtime::Registry::name_()'],['../classtvm_1_1GenericFuncNode.html#ade1da360d3e314360fd5399b2d76d3a1',1,'tvm::GenericFuncNode::name_()']]],
   ['name_5fhint',['name_hint',['../classtvm_1_1ConstructorNode.html#ad94b373e9c4669fc5d472a9194483d66',1,'tvm::ConstructorNode::name_hint()'],['../classtvm_1_1GlobalVarNode.html#ab82974132026f07d89afcf409a2ca616',1,'tvm::GlobalVarNode::name_hint()'],['../structtvm_1_1ConstantInfoNode.html#a054eb75fb628ae03d5cb4c4c7f7e8846',1,'tvm::ConstantInfoNode::name_hint()'],['../classtvm_1_1TypeVarNode.html#a8f040892b1484a503c58870b4f0b70f6',1,'tvm::TypeVarNode::name_hint()'],['../classtvm_1_1Global [...]
   ['name_5fsupply_2eh',['name_supply.h',['../name__supply_8h.html',1,'']]],
diff --git a/docs/reference/api/doxygen/search/functions_11.js b/docs/reference/api/doxygen/search/functions_11.js
index f705daa89..3e7cccf81 100644
--- a/docs/reference/api/doxygen/search/functions_11.js
+++ b/docs/reference/api/doxygen/search/functions_11.js
@@ -1,7 +1,7 @@
 var searchData=
 [
   ['q_5fmultiply_5fshift',['q_multiply_shift',['../namespacetvm_1_1tir_1_1builtin.html#a0c2ebdcec34d7c79dc8480e5dab8547a',1,'tvm::tir::builtin::q_multiply_shift()'],['../namespacetvm.html#ac788f9eb54a8971596779537afc6c896',1,'tvm::q_multiply_shift()']]],
-  ['queryirmodule',['QueryIRModule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#a8f6ea7a73c34b3645e17cb673c81def6',1,'tvm::meta_schedule::DatabaseNode']]],
-  ['queryschedule',['QuerySchedule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#af06e8cb22826d2e5f29d5ec9ede6095b',1,'tvm::meta_schedule::DatabaseNode']]],
-  ['querytuningrecord',['QueryTuningRecord',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#acd794ded30c3943f5e976e3d360bd178',1,'tvm::meta_schedule::DatabaseNode']]]
+  ['queryirmodule',['QueryIRModule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aeb4101db551afa93ea144b9b173783a0',1,'tvm::meta_schedule::DatabaseNode']]],
+  ['queryschedule',['QuerySchedule',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#a638febf77b9cb7590d6babb28a97a020',1,'tvm::meta_schedule::DatabaseNode']]],
+  ['querytuningrecord',['QueryTuningRecord',['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#adb5dd2d61af2ac335d68b402c057d612',1,'tvm::meta_schedule::DatabaseNode']]]
 ];
diff --git a/docs/reference/api/doxygen/search/functions_12.js b/docs/reference/api/doxygen/search/functions_12.js
index 811961ac9..5de05b32b 100644
--- a/docs/reference/api/doxygen/search/functions_12.js
+++ b/docs/reference/api/doxygen/search/functions_12.js
@@ -56,7 +56,7 @@ var searchData=
   ['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
   ['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
   ['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
-  ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
+  ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
   ['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array&lt; Integer &gt; &amp;after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
   ['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
   ['repeat',['repeat',['../namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687',1,'tvm::topi']]],
@@ -96,7 +96,7 @@ var searchData=
   ['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
   ['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a1836b2278bc24fdc227c490896d92980',1,'tvm::meta_schedule::Postproc']]],
   ['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
-  ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
+  ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
   ['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
   ['right_5fshift',['right_shift',['../namespacetvm.html#ae8ecc0382685a855187bede0c97d93e6',1,'tvm::right_shift(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.html#af49dde9dfdeea62e8ad3a6d8db53de0b',1,'tvm::right_shift(const PrimExpr &amp;a, int b, Span span=Span())'],['../namespacetvm.html#a98ff4361d0a24570f8dc32d03cde972a',1,'tvm::right_shift(int a, const PrimExpr &amp;b, Span span=Span())'],['../namespacetvm_1_1topi.html#a9673b9caffb46404b566c3f04a492dfe',1,'tvm::topi:: [...]
   ['rocblas_5fbatch_5fmatmul',['rocblas_batch_matmul',['../namespacetvm_1_1topi_1_1contrib.html#abf1113dd429e1285752b48f62fe12848',1,'tvm::topi::contrib']]],
diff --git a/docs/reference/api/doxygen/search/functions_13.js b/docs/reference/api/doxygen/search/functions_13.js
index 12ecbcce6..a31666255 100644
--- a/docs/reference/api/doxygen/search/functions_13.js
+++ b/docs/reference/api/doxygen/search/functions_13.js
@@ -27,6 +27,7 @@ var searchData=
   ['schedule_5freduce',['schedule_reduce',['../namespacetvm_1_1topi_1_1cuda.html#a674cabb64c0a45fd58c595389beb4919',1,'tvm::topi::cuda::schedule_reduce()'],['../namespacetvm_1_1topi_1_1rocm.html#aa4e0bacdd895904427bfc300ca9ace32',1,'tvm::topi::rocm::schedule_reduce()']]],
   ['schedule_5fsoftmax',['schedule_softmax',['../namespacetvm_1_1topi_1_1cuda.html#a4a2a33ae8186abc6af4dae2ffd12ff91',1,'tvm::topi::cuda::schedule_softmax()'],['../namespacetvm_1_1topi_1_1rocm.html#ab71ce2b3685f0ce5f30d2d661c5e799b',1,'tvm::topi::rocm::schedule_softmax()']]],
   ['schedulefn',['ScheduleFn',['../classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa6dd3790fd633db9046015c69aca3735',1,'tvm::meta_schedule::SpaceGenerator']]],
+  ['schedulefndatabase',['ScheduleFnDatabase',['../classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4',1,'tvm::meta_schedule::Database']]],
   ['scheduleops',['ScheduleOps',['../namespacetvm_1_1te.html#ac5f0fdd7c2d3deb15b7855c5b1ff1aff',1,'tvm::te']]],
   ['schedulepostproctoprimfunc',['SchedulePostProcToPrimFunc',['../namespacetvm_1_1te.html#a9eb39ad3aa5af348b1b27e755074f525',1,'tvm::te']]],
   ['schedulereduce',['ScheduleReduce',['../namespacetvm_1_1topi_1_1cuda.html#a3dbbf8bdb78533c15e62ab0e874eb360',1,'tvm::topi::cuda']]],
@@ -131,7 +132,7 @@ var searchData=
   ['singlepoint',['SinglePoint',['../classtvm_1_1arith_1_1IntSet.html#a58aeb0d34656b1b43ac2532e4dfa12ed',1,'tvm::arith::IntSet']]],
   ['singleton',['Singleton',['../classtvm_1_1te_1_1Singleton.html#a94450b853dcd5e9865546d8c8fe351a1',1,'tvm::te::Singleton']]],
   ['sinh',['sinh',['../namespacetvm.html#ad828bc801c73df761c58d9f8877d52ee',1,'tvm::sinh()'],['../namespacetvm_1_1topi.html#af9694f5470ba2cabc19866be3b00fe8d',1,'tvm::topi::sinh()']]],
-  ['size',['size',['../classtvm_1_1runtime_1_1ADT.html#af51613add20f67643684b1c7fdd5569a',1,'tvm::runtime::ADT::size()'],['../classtvm_1_1runtime_1_1ArrayNode.html#a3e88cee6eb31d0e495f7debd94b7573d',1,'tvm::runtime::ArrayNode::size()'],['../classtvm_1_1runtime_1_1Array.html#aed6387e67d18b9d5ad18f510fd600a25',1,'tvm::runtime::Array::size()'],['../classtvm_1_1runtime_1_1MapNode.html#a5c0c770f7667f911aa8bec879e3ac214',1,'tvm::runtime::MapNode::size()'],['../classtvm_1_1runtime_1_1Map.html#a [...]
+  ['size',['Size',['../classtvm_1_1TensorTypeNode.html#a1f08dac86ae8aea81d058ef64cfd38b4',1,'tvm::TensorTypeNode::Size()'],['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aae5b9ab9f7e497654b90c23a2159a5cc',1,'tvm::meta_schedule::DatabaseNode::Size()'],['../classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0',1,'tvm::meta_schedule::PyDatabaseNode::Size()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1FrameBuffer.html#ae395a0f1c6e79e825aa7a244c74a5d7b',1,' [...]
   ['sizevar',['SizeVar',['../classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05',1,'tvm::tir::SizeVar::SizeVar(ObjectPtr&lt; Object &gt; n)'],['../classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd',1,'tvm::tir::SizeVar::SizeVar(String name_hint=&quot;s&quot;, DataType t=DataType::Int(32), Span span=Span())']]],
   ['skipassert',['SkipAssert',['../namespacetvm_1_1tir_1_1transform.html#a6fdd5910b00af823071dcdddd21cd2d3',1,'tvm::tir::transform']]],
   ['slice',['Slice',['../classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3',1,'tvm::te::Tensor::Slice']]],
@@ -152,7 +153,7 @@ var searchData=
   ['sparse_5fto_5fdense',['sparse_to_dense',['../namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c',1,'tvm::topi']]],
   ['specialize',['Specialize',['../namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782',1,'tvm::tir']]],
   ['specializedcondition',['SpecializedCondition',['../classtvm_1_1te_1_1SpecializedCondition.html#a48d119ee1c6033929a5592cfc2592e60',1,'tvm::te::SpecializedCondition']]],
-  ['split',['Split',['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_scheduler::State::split()'],['../classtvm_1_1te_1_1Stage.html#a [...]
+  ['split',['split',['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_scheduler::State::split()'],['../classtvm_1_1te_1_1Stage.html#a5a7cd562be59b68a187ad97085a3425d',1,'tvm::te::Stage::split()'],['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab [...]
   ['split_5fby_5fnparts',['split_by_nparts',['../classtvm_1_1te_1_1Stage.html#a51432f38d9ec4792a2525023179ae604',1,'tvm::te::Stage']]],
   ['split_5fsections',['split_sections',['../namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619',1,'tvm::topi']]],
   ['splitargs',['SplitArgs',['../namespacetvm_1_1relay_1_1transform.html#a2425d757b896168a109498e8d34ba960',1,'tvm::relay::transform']]],
@@ -173,7 +174,7 @@ var searchData=
   ['startmessage',['StartMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#acd512b977c6dd888f90c4fd6d2b9500f',1,'tvm::runtime::micro_rpc::Session']]],
   ['startpacket',['StartPacket',['../classtvm_1_1runtime_1_1micro__rpc_1_1Framer.html#ade10d3bd3a26e3b7af881ae134e9a998',1,'tvm::runtime::micro_rpc::Framer']]],
   ['startsession',['StartSession',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a15d3f9ecb8b22bf2d330f6f0a16c5239',1,'tvm::runtime::micro_rpc::Session']]],
-  ['state',['State',['../classtvm_1_1auto__scheduler_1_1State.html#a9e8198b1f51b42cfbbee4b9f42160749',1,'tvm::auto_scheduler::State::State()'],['../classtvm_1_1tir_1_1ScheduleNode.html#abb3612c2598fa2d3ee0e6e3fc3de8a26',1,'tvm::tir::ScheduleNode::state()']]],
+  ['state',['state',['../classtvm_1_1tir_1_1ScheduleNode.html#abb3612c2598fa2d3ee0e6e3fc3de8a26',1,'tvm::tir::ScheduleNode::state()'],['../classtvm_1_1auto__scheduler_1_1State.html#a9e8198b1f51b42cfbbee4b9f42160749',1,'tvm::auto_scheduler::State::State()']]],
   ['stats',['Stats',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#a5445bd71aa14ec97552fa099dc3bd787',1,'tvm::runtime::vm::Executable']]],
   ['stepapplytoschedule',['StepApplyToSchedule',['../namespacetvm_1_1auto__scheduler.html#ac58f7548a94b92f801b2b9a6f65bd785',1,'tvm::auto_scheduler']]],
   ['stepapplytostate',['StepApplyToState',['../namespacetvm_1_1auto__scheduler.html#a6909bc5a99d1cc8372201e9392717832',1,'tvm::auto_scheduler']]],
diff --git a/docs/reference/api/doxygen/search/functions_14.js b/docs/reference/api/doxygen/search/functions_14.js
index 55df422df..7e6f92995 100644
--- a/docs/reference/api/doxygen/search/functions_14.js
+++ b/docs/reference/api/doxygen/search/functions_14.js
@@ -20,7 +20,7 @@ var searchData=
   ['tensorintrin',['TensorIntrin',['../classtvm_1_1te_1_1TensorIntrin.html#a4ff4237911227bf80b3076906dc3b7ea',1,'tvm::te::TensorIntrin::TensorIntrin()'],['../classtvm_1_1tir_1_1TensorIntrin.html#af5a94c7b098b56056e02eaf187e6871c',1,'tvm::tir::TensorIntrin::TensorIntrin()']]],
   ['tensorintrincall',['TensorIntrinCall',['../classtvm_1_1te_1_1TensorIntrinCall.html#a91c10074ce6babeba78fe72a0aab4b52',1,'tvm::te::TensorIntrinCall']]],
   ['tensorintrinnode',['TensorIntrinNode',['../classtvm_1_1te_1_1TensorIntrinNode.html#ad59e7f2b881fc798a8c64fd3959f929c',1,'tvm::te::TensorIntrinNode']]],
-  ['tensorize',['Tensorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &amp;loop_rv, const String &amp;intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &amp;block_rv, const String &amp;intrin)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()']]],
+  ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &amp;loop_rv, const String &amp;intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &amp;block_rv, const String &amp;intrin)=0']]],
   ['tensornode',['TensorNode',['../classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8',1,'tvm::te::TensorNode']]],
   ['tensortype',['TensorType',['../classtvm_1_1TensorType.html#ade4460e9b02b42757a83808dec478b87',1,'tvm::TensorType']]],
   ['terminalrenderer',['TerminalRenderer',['../namespacetvm.html#a69a0e3f559d3a3b98d42701117d93ed0',1,'tvm']]],
@@ -51,7 +51,7 @@ var searchData=
   ['totupletype',['ToTupleType',['../namespacetvm_1_1relay.html#ae6757a008816e31cce4109e8dfc2bc16',1,'tvm::relay']]],
   ['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
   ['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
-  ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array&lt; Instruction &gt; insts, Map&lt; Instruction, ObjectRef &gt; decisions)'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()']]],
+  ['trace',['trace',['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array&lt; Instruction &gt; insts, Map&lt; Instruction, ObjectRef &gt; decisions)']]],
   ['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
   ['tracedarray',['TracedArray',['../classtvm_1_1TracedArray.html#a7b1ab76aea02b3357239cbe6b521bc39',1,'tvm::TracedArray']]],
   ['tracedarrayiterator',['TracedArrayIterator',['../classtvm_1_1TracedArrayIterator.html#a684a4dfb9a548bff64120cf40822a3b9',1,'tvm::TracedArrayIterator']]],
diff --git a/docs/reference/api/doxygen/search/functions_15.js b/docs/reference/api/doxygen/search/functions_15.js
index fd8b30131..bbc21e6f4 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -17,7 +17,7 @@ var searchData=
   ['unknownattributeaccesspathnode',['UnknownAttributeAccessPathNode',['../classtvm_1_1UnknownAttributeAccessPathNode.html#a1882e9e591466a2785acc761dc63d56e',1,'tvm::UnknownAttributeAccessPathNode']]],
   ['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
   ['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
-  ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
+  ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
   ['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
   ['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
   ['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index 3ce5dbded..860ee6399 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -65,7 +65,7 @@ var searchData=
   ['microtvmruntimegetoutput',['MicroTVMRuntimeGetOutput',['../microtvm__runtime_8h.html#a76129be7b6de972791a3f9a1b312acfa',1,'microtvm_runtime.h']]],
   ['microtvmruntimerun',['MicroTVMRuntimeRun',['../microtvm__runtime_8h.html#ac43a544f675dd716e8c279c3e41f6e45',1,'microtvm_runtime.h']]],
   ['microtvmruntimesetinput',['MicroTVMRuntimeSetInput',['../microtvm__runtime_8h.html#aa593edc600f4356f2b560702aa01b113',1,'microtvm_runtime.h']]],
-  ['min',['Min',['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongruentialEngine::min()'],['../namespacetvm.html#aac2abc149c1a47944c37b560181b15c0',1,'tvm::min(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
+  ['min',['min',['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongruentialEngine::min()'],['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../namespacetvm.html#aac2abc149c1a47944c37b560181b15c0',1,'tvm::min(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
   ['min_5fvalue',['min_value',['../namespacetvm.html#a3b37fa55ea93d6868751a2441996b072',1,'tvm']]],
   ['minimum',['minimum',['../namespacetvm_1_1topi.html#a7ac1dc0d99ce93090a4cdf90ab19d4b8',1,'tvm::topi::minimum(const tvm::PrimExpr &amp;a, const tvm::PrimExpr &amp;b)'],['../namespacetvm_1_1topi.html#a0e19dc06a2b1ecbb83b0942fdf836169',1,'tvm::topi::minimum(const tvm::te::Tensor &amp;A, const tvm::te::Tensor &amp;B, std::string name=&quot;T_&quot; &quot;minimum&quot;, std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a28d4ef4b3426bff237215ce356dd5681',1,'tvm::topi::minimum(con [...]
   ['minop',['MinOp',['../namespacetvm_1_1topi.html#aea9a989b0aaa2aef03fe8ee237d8257e',1,'tvm::topi']]],
diff --git a/docs/reference/api/doxygen/search/functions_e.js b/docs/reference/api/doxygen/search/functions_e.js
index 700efa5ff..5a00f421d 100644
--- a/docs/reference/api/doxygen/search/functions_e.js
+++ b/docs/reference/api/doxygen/search/functions_e.js
@@ -1,6 +1,6 @@
 var searchData=
 [
-  ['name',['Name',['../classtvm_1_1script_1_1ir__builder_1_1IRBuilder.html#ace475c7a85ef508d912beba48ef4183a',1,'tvm::script::ir_builder::IRBuilder::Name()'],['../classtvm_1_1script_1_1ir__builder_1_1details_1_1Namer.html#a22da1264beaa8681bab998a5c597369f',1,'tvm::script::ir_builder::details::Namer::Name()'],['../classtvm_1_1runtime_1_1metadata_1_1TensorInfoNode.html#a2b889fc061097f72dcab73f090574c65',1,'tvm::runtime::metadata::TensorInfoNode::name()'],['../classtvm_1_1tir_1_1LayoutAxis. [...]
+  ['name',['name',['../classtvm_1_1runtime_1_1metadata_1_1TensorInfoNode.html#a2b889fc061097f72dcab73f090574c65',1,'tvm::runtime::metadata::TensorInfoNode::name()'],['../classtvm_1_1tir_1_1LayoutAxis.html#a0e1b9f9e05162787ccc40a7daa54ac2e',1,'tvm::tir::LayoutAxis::name()'],['../classtvm_1_1tir_1_1Layout.html#a8beb5a8b6259d9c0e916185e9e5eee52',1,'tvm::tir::Layout::name()'],['../classtvm_1_1script_1_1ir__builder_1_1IRBuilder.html#ace475c7a85ef508d912beba48ef4183a',1,'tvm::script::ir_builde [...]
   ['name_5fhint',['name_hint',['../classtvm_1_1relay_1_1VarPatternNode.html#aa2e698d6bb7d29f6db7aa07070029d42',1,'tvm::relay::VarPatternNode::name_hint()'],['../classtvm_1_1relay_1_1VarNode.html#a8e10dd556c96138aa5320df2fe947199',1,'tvm::relay::VarNode::name_hint()'],['../classtvm_1_1runtime_1_1metadata_1_1ConstantInfoMetadataNode.html#aae9679a8d5d63547239addeb13ba9c17',1,'tvm::runtime::metadata::ConstantInfoMetadataNode::name_hint()']]],
   ['namesupply',['NameSupply',['../classtvm_1_1NameSupply.html#ad6c6c3d3a4698ee50ab2fd2062566820',1,'tvm::NameSupply']]],
   ['namesupplynode',['NameSupplyNode',['../classtvm_1_1NameSupplyNode.html#aba5bb3284648f9f8740eb76500499a12',1,'tvm::NameSupplyNode::NameSupplyNode()=default'],['../classtvm_1_1NameSupplyNode.html#a06784e30bad359af91cb7cd65ec79ca7',1,'tvm::NameSupplyNode::NameSupplyNode(const String &amp;prefix, std::unordered_map&lt; std::string, int &gt; name_map)']]],
diff --git a/docs/reference/api/doxygen/search/typedefs_e.js b/docs/reference/api/doxygen/search/typedefs_e.js
index d02f81c99..1fc2ccb05 100644
--- a/docs/reference/api/doxygen/search/typedefs_e.js
+++ b/docs/reference/api/doxygen/search/typedefs_e.js
@@ -42,7 +42,7 @@ var searchData=
   ['tvmretvalue',['TVMRetValue',['../classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb',1,'tvm::BaseAttrsNode']]],
   ['tvmretvaluehandle',['TVMRetValueHandle',['../c__runtime__api_8h.html#a6cd1076476117e74454f67931c2da1d4',1,'c_runtime_api.h']]],
   ['tvmstreamhandle',['TVMStreamHandle',['../c__runtime__api_8h.html#ab1d5f6b7945e1410602a8a057fda5757',1,'c_runtime_api.h']]],
-  ['type',['type',['../structtvm_1_1detail_1_1is__specialized.html#a3ea7783c457d7ddc82100674292724f4',1,'tvm::detail::is_specialized::type()'],['../structtvm_1_1detail_1_1is__specialized_3_01Container_3_01Args_8_8_8_01_4_00_01Container_01_4.html#a8dee3a1604498d6bc64948f1c0d19dc2',1,'tvm::detail::is_specialized&lt; Container&lt; Args... &gt;, Container &gt;::type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tv [...]
+  ['type',['Type',['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tvm::detail::TracedObjectWrapperSelector&lt; T, false &gt;::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01true_01_4.html#ab1da2c0d7b63a70812c5f27f60aeb695',1,'tvm::detail::TracedObjectWrapperSelector&lt; T, true &gt;::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01Map_3_01K_00_01V_01_4_00_01true_01_4 [...]
   ['typecall',['TypeCall',['../namespacetvm_1_1relay.html#ab406a37acee11226e3e2e119beee439e',1,'tvm::relay']]],
   ['typecallnode',['TypeCallNode',['../namespacetvm_1_1relay.html#af4dccabc877b8fd7db47cb73fb93883e',1,'tvm::relay']]],
   ['typeconstraint',['TypeConstraint',['../namespacetvm_1_1relay.html#a64e2e93fe04716efd8334ab4e39c92ce',1,'tvm::relay']]],
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index aed7b48f1..31e186e65 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
 <dd><p>The search policy that searches in a hierarchical search space defined by sketches.
 The policy randomly samples programs from the space defined by sketches and use evolutionary
 search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
 
 <dl class="py function">
 <dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
 <dd><p>THIS API IS DEPRECATED.</p>
 <p>Run auto scheduling search for a task.</p>
 <dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 3281cce13..8e4801a65 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/534412896/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 4e726fbed..aba402067 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/534412896/web/src/memory.ts#L223">memory.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L208">memory.ts:208</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L312">memory.ts:312</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L284">memory.ts:284</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L388">memory.ts:388</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L376">memory.ts:376</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L267">memory.ts:267</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L243">memory.ts:243</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L321">memory.ts:321</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L252">memory.ts:252</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L359">memory.ts:359</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L342">memory.ts:342</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L350">memory.ts:350</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L326">memory.ts:326</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L363">memory.ts:363</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L346">memory.ts:346</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L334">memory.ts:334</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 4a16530c1..ab99fb184 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/534412896/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 51903c10f..2be7901b5 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/534412896/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 2fab0f7f5..5bebc0a69 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/534412896/web/src/environment.ts#L86">environment.ts:86</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L70">environment.ts:70</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L69">environment.ts:69</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L78">environment.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L84">environment.ts:84</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L105">environment.ts:105</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 949d76430..0ad58fc51 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/534412896/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 5968d8fd6..99d2e3a0d 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/534412896/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 714d2be7c..bbf7df432 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/534412896/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/534412896/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 336a520a4..1aa26e1a1 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/534412896/web/src/memory.ts#L40">memory.ts:40</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L32">memory.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L33">memory.ts:33</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L154">memory.ts:154</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L90">memory.ts:90</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L97">memory.ts:97</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L74">memory.ts:74</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L81">memory.ts:81</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L104">memory.ts:104</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L132">memory.ts:132</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L145">memory.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L60">memory.ts:60</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L67">memory.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L53">memory.ts:53</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L114">memory.ts:114</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L124">memory.ts:124</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/memory.ts#L175">memory.ts:175</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 14af91313..cdc3a9ad5 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/534412896/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 2be1eb030..85bee12ed 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/534412896/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 41252d4c4..4aff73fef 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/534412896/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 cc7f88d8d..b6627258a 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/534412896/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 0acecfabd..332f54a4a 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/534412896/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 a3c9f44c3..18d681008 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/534412896/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 fe1e080cd..b299a4464 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/534412896/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 212c20736..246c2ef1b 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/534412896/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 4bd58d5c4..342367ab2 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/534412896/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 a31474794..1fdbe7ddc 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/534412896/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 6be553c28..e4fa7c7f4 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/534412896/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 8828fef30..0215a366b 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/534412896/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/support.ts#L25">support.ts:25</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/support.ts#L39">support.ts:39</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/support.ts#L52">support.ts:52</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/compact.ts#L38">compact.ts:38</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/environment.ts#L32">environment.ts:32</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/compact.ts#L24">compact.ts:24</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
 								</ul>
 							</aside>
 							<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
 						<li class="tsd-description">
 							<aside class="tsd-sources">
 								<ul>
-									<li>Defined in <a href="https://github.com/apache/tvm/blob/534412896/web/src/support.ts#L62">support.ts:62</a></li>
+									<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+								<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 1fc21ff4b..2aa44c79b 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/534412896/web/src/types.ts#L52">types.ts:52</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 684dceaaf..8beade396 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/534412896/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 8bd76ee3b..8d7ed3d75 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/534412896/web/src/types.ts#L34">types.ts:34</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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/534412896/web/src/types.ts#L39">types.ts:39</a></li>
+							<li>Defined in <a href="https://github.com/apache/tvm/blob/648a29a53/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 afb999779..8468bcf16 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 93b887012..a5a09f6f0 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.566</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.348</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -336,11 +336,11 @@
 </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>00:20.560</p></td>
+<td><p>00:22.342</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>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index aa570ce3a..5bfe42db1 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   DeprecationWarning,
 /workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the  new recommended usage.
   relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.04s!
+resnet18_v1 inference graph built in 24.50s!
 </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 d0b446f67..dfd51244f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
   &quot;target_host parameter is going to be deprecated. &quot;
 /workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
   DeprecationWarning,
-yolov3-tiny inference graph built in 15.66s!
+yolov3-tiny inference graph built in 16.94s!
 </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 134518c0f..cd0c8207b 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:30.263</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:34.723</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.235</p></td>
+<td><p>00:49.828</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>00:42.028</p></td>
+<td><p>00:44.895</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 50b59d5ab..5d0f642d2 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.259</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.271</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 84%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.850</p></td>
+<td><p>00:02.869</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>00:00.410</p></td>
+<td><p>00:00.402</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 d5a2b91f8..b8252ef61 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.764</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.734</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 81%" />
@@ -336,11 +336,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.409</p></td>
+<td><p>00:00.397</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>00:00.355</p></td>
+<td><p>00:00.337</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 b7f84fe0f..b4b369096 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -478,7 +478,7 @@ 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*E
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
 </pre></div>
 </div>
 </div>
@@ -568,7 +568,7 @@ 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: 92.236 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.119 ms
 </pre></div>
 </div>
 </div>
@@ -642,7 +642,6 @@ 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  11.696 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 43517a4b5..a5a833e6e 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
 device available
 Get devices for measurement successfully!
-No: 1   GFLOPS: 9.11/9.11       result: MeasureResult(costs=(0.029471841,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6021461486816406, timestamp=1661724946.3576689)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
-No: 2   GFLOPS: 2.14/9.11       result: MeasureResult(costs=(0.1256582872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1445271968841553, timestamp=1661724948.5297232)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
-No: 3   GFLOPS: 11.94/11.94     result: MeasureResult(costs=(0.022489702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5632054805755615, timestamp=1661724949.5852482)        [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
-No: 4   GFLOPS: 1.42/11.94      result: MeasureResult(costs=(0.18853694780000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.137359142303467, timestamp=1661724953.2856922) [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
-No: 5   GFLOPS: 3.68/11.94      result: MeasureResult(costs=(0.0728464974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.299680471420288, timestamp=1661724954.7127228)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
-No: 6   GFLOPS: 1.63/11.94      result: MeasureResult(costs=(0.1644681828,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7887916564941406, timestamp=1661724957.546864)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
-No: 7   GFLOPS: 0.82/11.94      result: MeasureResult(costs=(0.3256161328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.327296495437622, timestamp=1661724963.4324474)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
-No: 8   GFLOPS: 10.49/11.94     result: MeasureResult(costs=(0.0256009084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5486633777618408, timestamp=1661724964.0033681)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
-No: 9   GFLOPS: 1.47/11.94      result: MeasureResult(costs=(0.1830801916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.016674757003784, timestamp=1661724967.1381662)        [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
-No: 10  GFLOPS: 2.42/11.94      result: MeasureResult(costs=(0.11074119619999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8749973773956299, timestamp=1661724969.0716505)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 4])],None,22
+No: 1   GFLOPS: 9.25/9.25       result: MeasureResult(costs=(0.029018732199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6023972034454346, timestamp=1661761578.8374166)       [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 256])],None,80
+No: 2   GFLOPS: 2.70/9.25       result: MeasureResult(costs=(0.099548106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7477777004241943, timestamp=1661761580.5970793)        [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 8])],None,32
+No: 3   GFLOPS: 11.76/11.76     result: MeasureResult(costs=(0.0228182416,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5506212711334229, timestamp=1661761581.684402)        [(&#39;tile_y&#39;, [-1, 64]), (&#39;tile_x&#39;, [-1, 32])],None,56
+No: 4   GFLOPS: 1.83/11.76      result: MeasureResult(costs=(0.1464734124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.466071367263794, timestamp=1661761584.7498503)        [(&#39;tile_y&#39;, [-1, 1]), (&#39;tile_x&#39;, [-1, 4])],None,20
+No: 5   GFLOPS: 3.60/11.76      result: MeasureResult(costs=(0.0745418648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3305764198303223, timestamp=1661761586.211585)        [(&#39;tile_y&#39;, [-1, 256]), (&#39;tile_x&#39;, [-1, 16])],None,48
+No: 6   GFLOPS: 1.74/11.76      result: MeasureResult(costs=(0.154379631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6465063095092773, timestamp=1661761588.8973215)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 4])],None,29
+No: 7   GFLOPS: 0.82/11.76      result: MeasureResult(costs=(0.3268341212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.347292423248291, timestamp=1661761594.8402455)        [(&#39;tile_y&#39;, [-1, 512]), (&#39;tile_x&#39;, [-1, 2])],None,19
+No: 8   GFLOPS: 9.68/11.76      result: MeasureResult(costs=(0.027718719599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5896084308624268, timestamp=1661761595.4487858)       [(&#39;tile_y&#39;, [-1, 4]), (&#39;tile_x&#39;, [-1, 64])],None,62
+No: 9   GFLOPS: 1.53/11.76      result: MeasureResult(costs=(0.1759445694,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9178578853607178, timestamp=1661761598.4879167)       [(&#39;tile_y&#39;, [-1, 2]), (&#39;tile_x&#39;, [-1, 2])],None,11
+No: 10  GFLOPS: 2.48/11.76      result: MeasureResult(costs=(0.108381803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.846768856048584, timestamp=1661761600.391835)  [(&#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 0296c971b..88afce522 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
 <span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 495.8759032300077, &#39;median&#39;: 499.2053312498683, &#39;std&#39;: 7.764164250480838}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;mean&#39;: 498.4301331699976, &#39;median&#39;: 498.51982829999884, &#39;std&#39;: 0.4806910936114738}
 </pre></div>
 </div>
 </div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
   &quot;target_host parameter is going to be deprecated. &quot;
 
 [Task  1/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  1/25]  Current/Best:   19.41/  19.41 GFLOPS | Progress: (4/20) | 6.22 s
-[Task  1/25]  Current/Best:    6.27/  19.41 GFLOPS | Progress: (8/20) | 9.14 s
-[Task  1/25]  Current/Best:   11.64/  23.19 GFLOPS | Progress: (12/20) | 11.51 s
-[Task  1/25]  Current/Best:   18.54/  23.23 GFLOPS | Progress: (16/20) | 13.14 s
-[Task  1/25]  Current/Best:   11.80/  24.23 GFLOPS | Progress: (20/20) | 14.87 s Done.
+[Task  1/25]  Current/Best:   17.21/  17.21 GFLOPS | Progress: (4/20) | 6.49 s
+[Task  1/25]  Current/Best:    6.15/  17.21 GFLOPS | Progress: (8/20) | 9.56 s
+[Task  1/25]  Current/Best:   11.52/  22.59 GFLOPS | Progress: (12/20) | 12.01 s
+[Task  1/25]  Current/Best:   16.42/  22.73 GFLOPS | Progress: (16/20) | 13.71 s
+[Task  1/25]  Current/Best:   11.58/  23.79 GFLOPS | Progress: (20/20) | 15.46 s Done.
 
 [Task  2/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  2/25]  Current/Best:   12.45/  13.27 GFLOPS | Progress: (4/20) | 3.73 s
-[Task  2/25]  Current/Best:   14.46/  18.89 GFLOPS | Progress: (8/20) | 5.03 s
-[Task  2/25]  Current/Best:   21.24/  21.24 GFLOPS | Progress: (12/20) | 6.32 s
-[Task  2/25]  Current/Best:   12.87/  21.24 GFLOPS | Progress: (16/20) | 7.55 s
-[Task  2/25]  Current/Best:   19.75/  21.24 GFLOPS | Progress: (20/20) | 9.12 s Done.
+[Task  2/25]  Current/Best:   12.25/  13.16 GFLOPS | Progress: (4/20) | 3.85 s
+[Task  2/25]  Current/Best:   14.25/  18.70 GFLOPS | Progress: (8/20) | 5.15 s
+[Task  2/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (12/20) | 6.48 s
+[Task  2/25]  Current/Best:   12.74/  20.82 GFLOPS | Progress: (16/20) | 7.76 s
+[Task  2/25]  Current/Best:   19.49/  20.82 GFLOPS | Progress: (20/20) | 9.37 s Done.
 
 [Task  3/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  3/25]  Current/Best:    1.65/  11.02 GFLOPS | Progress: (4/20) | 5.76 s
-[Task  3/25]  Current/Best:   17.22/  18.81 GFLOPS | Progress: (8/20) | 7.64 s
-[Task  3/25]  Current/Best:   16.84/  18.81 GFLOPS | Progress: (12/20) | 9.28 s
-[Task  3/25]  Current/Best:    7.33/  24.22 GFLOPS | Progress: (16/20) | 11.16 s
-[Task  3/25]  Current/Best:   12.44/  24.22 GFLOPS | Progress: (20/20) | 15.62 s Done.
+[Task  3/25]  Current/Best:    1.63/  10.73 GFLOPS | Progress: (4/20) | 5.95 s
+[Task  3/25]  Current/Best:   15.23/  16.81 GFLOPS | Progress: (8/20) | 7.90 s
+[Task  3/25]  Current/Best:   14.92/  16.81 GFLOPS | Progress: (12/20) | 9.65 s
+[Task  3/25]  Current/Best:    7.21/  23.64 GFLOPS | Progress: (16/20) | 11.61 s
+[Task  3/25]  Current/Best:   11.21/  23.64 GFLOPS | Progress: (20/20) | 16.17 s Done.
 
 [Task  4/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  4/25]  Current/Best:    9.61/  20.33 GFLOPS | Progress: (4/20) | 2.36 s
-[Task  4/25]  Current/Best:    6.78/  20.33 GFLOPS | Progress: (8/20) | 6.59 s
-[Task  4/25]  Current/Best:   22.58/  22.58 GFLOPS | Progress: (12/20) | 10.94 s
-[Task  4/25]  Current/Best:   19.32/  22.58 GFLOPS | Progress: (16/20) | 13.16 s
-[Task  4/25]  Current/Best:   13.73/  22.58 GFLOPS | Progress: (20/20) | 15.14 s Done.
+[Task  4/25]  Current/Best:    9.35/  20.20 GFLOPS | Progress: (4/20) | 2.47 s
+[Task  4/25]  Current/Best:    6.82/  20.20 GFLOPS | Progress: (8/20) | 6.85 s
+[Task  4/25]  Current/Best:   21.97/  21.97 GFLOPS | Progress: (12/20) | 11.37 s
+[Task  4/25]  Current/Best:   16.65/  21.97 GFLOPS | Progress: (16/20) | 13.63 s
+[Task  4/25]  Current/Best:   13.27/  21.97 GFLOPS | Progress: (20/20) | 15.66 s Done.
 
 [Task  5/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  5/25]  Current/Best:    9.60/  10.44 GFLOPS | Progress: (4/20) | 2.59 s
-[Task  5/25]  Current/Best:   11.84/  12.88 GFLOPS | Progress: (8/20) | 4.62 s
-[Task  5/25]  Current/Best:   12.01/  18.39 GFLOPS | Progress: (12/20) | 7.51 s
-[Task  5/25]  Current/Best:   11.81/  23.07 GFLOPS | Progress: (16/20) | 8.90 s
-[Task  5/25]  Current/Best:   12.34/  23.07 GFLOPS | Progress: (20/20) | 10.74 s Done.
+[Task  5/25]  Current/Best:    9.75/  10.26 GFLOPS | Progress: (4/20) | 2.66 s
+[Task  5/25]  Current/Best:   11.71/  13.12 GFLOPS | Progress: (8/20) | 4.71 s
+[Task  5/25]  Current/Best:    9.72/  17.90 GFLOPS | Progress: (12/20) | 7.72 s
+[Task  5/25]  Current/Best:   11.73/  22.65 GFLOPS | Progress: (16/20) | 9.15 s
+[Task  5/25]  Current/Best:   11.84/  22.65 GFLOPS | Progress: (20/20) | 11.06 s Done.
 
 [Task  6/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  6/25]  Current/Best:   12.28/  20.34 GFLOPS | Progress: (4/20) | 3.92 s
-[Task  6/25]  Current/Best:   19.29/  20.34 GFLOPS | Progress: (8/20) | 5.67 s
-[Task  6/25]  Current/Best:   13.57/  20.34 GFLOPS | Progress: (12/20) | 7.58 s
-[Task  6/25]  Current/Best:   20.37/  20.37 GFLOPS | Progress: (16/20) | 9.77 s
-[Task  6/25]  Current/Best:    3.76/  20.37 GFLOPS | Progress: (20/20) | 12.27 s Done.
+[Task  6/25]  Current/Best:   12.09/  20.03 GFLOPS | Progress: (4/20) | 4.07 s
+[Task  6/25]  Current/Best:   18.76/  20.03 GFLOPS | Progress: (8/20) | 5.85 s
+[Task  6/25]  Current/Best:   13.21/  20.03 GFLOPS | Progress: (12/20) | 7.79 s
+[Task  6/25]  Current/Best:   19.88/  20.03 GFLOPS | Progress: (16/20) | 10.06 s
+[Task  6/25]  Current/Best:    3.76/  20.03 GFLOPS | Progress: (20/20) | 12.58 s Done.
 
 [Task  7/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  7/25]  Current/Best:   11.37/  12.83 GFLOPS | Progress: (4/20) | 3.59 s
-[Task  7/25]  Current/Best:   20.29/  21.45 GFLOPS | Progress: (8/20) | 5.08 s
-[Task  7/25]  Current/Best:   16.41/  21.45 GFLOPS | Progress: (12/20) | 6.97 s
-[Task  7/25]  Current/Best:   12.43/  21.45 GFLOPS | Progress: (16/20) | 8.99 s
-[Task  7/25]  Current/Best:    6.45/  22.22 GFLOPS | Progress: (20/20) | 11.39 s Done.
+[Task  7/25]  Current/Best:   11.11/  12.16 GFLOPS | Progress: (4/20) | 3.76 s
+[Task  7/25]  Current/Best:   19.77/  21.18 GFLOPS | Progress: (8/20) | 5.29 s
+[Task  7/25]  Current/Best:   15.96/  21.18 GFLOPS | Progress: (12/20) | 7.21 s
+[Task  7/25]  Current/Best:   12.16/  21.18 GFLOPS | Progress: (16/20) | 9.26 s
+[Task  7/25]  Current/Best:    6.41/  21.64 GFLOPS | Progress: (20/20) | 11.75 s Done.
 
 [Task  8/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  8/25]  Current/Best:    9.80/  13.83 GFLOPS | Progress: (4/20) | 2.92 s
-[Task  8/25]  Current/Best:    9.36/  13.83 GFLOPS | Progress: (8/20) | 7.62 s
-[Task  8/25]  Current/Best:   12.93/  13.83 GFLOPS | Progress: (12/20) | 13.61 s
-[Task  8/25]  Current/Best:   19.10/  19.10 GFLOPS | Progress: (16/20) | 15.66 s
-[Task  8/25]  Current/Best:   19.63/  19.63 GFLOPS | Progress: (20/20) | 22.07 s Done.
+[Task  8/25]  Current/Best:   10.30/  14.23 GFLOPS | Progress: (4/20) | 2.98 s
+[Task  8/25]  Current/Best:    9.77/  14.23 GFLOPS | Progress: (8/20) | 7.80 s
+[Task  8/25]  Current/Best:   13.25/  14.23 GFLOPS | Progress: (12/20) | 14.08 s
+[Task  8/25]  Current/Best:   19.02/  19.02 GFLOPS | Progress: (16/20) | 16.17 s
+[Task  8/25]  Current/Best:   19.84/  19.84 GFLOPS | Progress: (20/20) | 22.76 s Done.
 
 [Task  9/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task  9/25]  Current/Best:   14.61/  16.04 GFLOPS | Progress: (4/20) | 11.93 s
-[Task  9/25]  Current/Best:   23.91/  23.91 GFLOPS | Progress: (8/20) | 13.69 s
-[Task  9/25]  Current/Best:    8.37/  23.91 GFLOPS | Progress: (12/20) | 16.02 s
-[Task  9/25]  Current/Best:   18.31/  23.91 GFLOPS | Progress: (16/20) | 18.65 s
-[Task  9/25]  Current/Best:    9.33/  23.91 GFLOPS | Progress: (20/20) | 26.21 s
+[Task  9/25]  Current/Best:   14.16/  15.41 GFLOPS | Progress: (4/20) | 12.05 s
+[Task  9/25]  Current/Best:   23.50/  23.50 GFLOPS | Progress: (8/20) | 13.84 s
+[Task  9/25]  Current/Best:    8.25/  23.50 GFLOPS | Progress: (12/20) | 16.23 s
+[Task  9/25]  Current/Best:   17.87/  23.50 GFLOPS | Progress: (16/20) | 18.92 s
+[Task  9/25]  Current/Best:    9.07/  23.50 GFLOPS | Progress: (20/20) | 26.72 s
 [Task 10/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25]  Current/Best:   18.48/  18.48 GFLOPS | Progress: (4/20) | 2.55 s
-[Task 10/25]  Current/Best:   15.92/  18.48 GFLOPS | Progress: (8/20) | 4.13 s
-[Task 10/25]  Current/Best:   12.63/  19.22 GFLOPS | Progress: (12/20) | 5.64 s
-[Task 10/25]  Current/Best:   19.47/  20.51 GFLOPS | Progress: (16/20) | 6.71 s
-[Task 10/25]  Current/Best:    8.93/  20.51 GFLOPS | Progress: (20/20) | 8.23 s Done.
+[Task 10/25]  Current/Best:   18.51/  18.51 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 10/25]  Current/Best:   15.60/  18.51 GFLOPS | Progress: (8/20) | 4.21 s
+[Task 10/25]  Current/Best:   12.70/  19.09 GFLOPS | Progress: (12/20) | 5.76 s
+[Task 10/25]  Current/Best:   19.08/  20.28 GFLOPS | Progress: (16/20) | 6.87 s
+[Task 10/25]  Current/Best:    8.96/  20.28 GFLOPS | Progress: (20/20) | 8.44 s Done.
 
 [Task 11/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25]  Current/Best:   12.61/  20.38 GFLOPS | Progress: (4/20) | 3.21 s
-[Task 11/25]  Current/Best:   17.12/  20.38 GFLOPS | Progress: (8/20) | 5.90 s
-[Task 11/25]  Current/Best:   18.51/  20.38 GFLOPS | Progress: (12/20) | 7.92 s
-[Task 11/25]  Current/Best:   13.78/  21.22 GFLOPS | Progress: (16/20) | 10.56 s
-[Task 11/25]  Current/Best:   19.77/  21.94 GFLOPS | Progress: (20/20) | 12.54 s Done.
+[Task 11/25]  Current/Best:   11.22/  17.95 GFLOPS | Progress: (4/20) | 3.44 s
+[Task 11/25]  Current/Best:   16.17/  17.95 GFLOPS | Progress: (8/20) | 6.18 s
+[Task 11/25]  Current/Best:   17.92/  17.95 GFLOPS | Progress: (12/20) | 8.26 s
+[Task 11/25]  Current/Best:   13.50/  20.98 GFLOPS | Progress: (16/20) | 11.07 s
+[Task 11/25]  Current/Best:   19.42/  21.58 GFLOPS | Progress: (20/20) | 13.12 s Done.
 
 [Task 12/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25]  Current/Best:    7.97/  18.29 GFLOPS | Progress: (4/20) | 5.30 s
-[Task 12/25]  Current/Best:    5.23/  18.29 GFLOPS | Progress: (8/20) | 8.94 s
-[Task 12/25]  Current/Best:   19.25/  20.92 GFLOPS | Progress: (12/20) | 10.91 s
-[Task 12/25]  Current/Best:   15.70/  20.92 GFLOPS | Progress: (16/20) | 13.62 s
-[Task 12/25]  Current/Best:   15.36/  20.92 GFLOPS | Progress: (20/20) | 15.57 s Done.
+[Task 12/25]  Current/Best:    7.77/  17.99 GFLOPS | Progress: (4/20) | 5.47 s
+[Task 12/25]  Current/Best:    5.24/  17.99 GFLOPS | Progress: (8/20) | 9.20 s
+[Task 12/25]  Current/Best:   18.95/  18.95 GFLOPS | Progress: (12/20) | 11.20 s
+[Task 12/25]  Current/Best:   13.32/  18.95 GFLOPS | Progress: (16/20) | 13.99 s
+[Task 12/25]  Current/Best:   15.13/  18.97 GFLOPS | Progress: (20/20) | 15.89 s Done.
 
 [Task 13/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25]  Current/Best:    8.87/  19.34 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 13/25]  Current/Best:   18.02/  21.32 GFLOPS | Progress: (8/20) | 5.91 s
-[Task 13/25]  Current/Best:   20.00/  22.19 GFLOPS | Progress: (12/20) | 8.74 s
-[Task 13/25]  Current/Best:   12.53/  22.19 GFLOPS | Progress: (16/20) | 12.05 s
-[Task 13/25]  Current/Best:   19.15/  22.19 GFLOPS | Progress: (20/20) | 14.25 s Done.
+[Task 13/25]  Current/Best:    8.93/  17.27 GFLOPS | Progress: (4/20) | 3.72 s
+[Task 13/25]  Current/Best:   16.03/  20.72 GFLOPS | Progress: (8/20) | 6.17 s
+[Task 13/25]  Current/Best:   19.49/  21.62 GFLOPS | Progress: (12/20) | 9.13 s
+[Task 13/25]  Current/Best:   12.21/  21.62 GFLOPS | Progress: (16/20) | 12.57 s
+[Task 13/25]  Current/Best:   18.70/  21.62 GFLOPS | Progress: (20/20) | 14.83 s Done.
 
 [Task 14/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25]  Current/Best:   14.14/  14.14 GFLOPS | Progress: (4/20) | 3.23 s
-[Task 14/25]  Current/Best:    6.22/  15.01 GFLOPS | Progress: (8/20) | 5.37 s
-[Task 14/25]  Current/Best:   21.53/  21.53 GFLOPS | Progress: (12/20) | 7.90 s
-[Task 14/25]  Current/Best:   16.99/  21.53 GFLOPS | Progress: (16/20) | 9.53 s Done.
+[Task 14/25]  Current/Best:   13.67/  13.67 GFLOPS | Progress: (4/20) | 3.43 s
+[Task 14/25]  Current/Best:    6.11/  13.67 GFLOPS | Progress: (8/20) | 5.65 s
+[Task 14/25]  Current/Best:   20.77/  20.77 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 14/25]  Current/Best:   17.16/  20.77 GFLOPS | Progress: (16/20) | 9.91 s Done.
 
-[Task 14/25]  Current/Best:   17.59/  21.53 GFLOPS | Progress: (20/20) | 11.27 s
+[Task 14/25]  Current/Best:   16.93/  20.77 GFLOPS | Progress: (20/20) | 11.71 s
 [Task 15/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25]  Current/Best:   18.14/  18.14 GFLOPS | Progress: (4/20) | 2.67 s
-[Task 15/25]  Current/Best:   14.59/  18.42 GFLOPS | Progress: (8/20) | 4.00 s
-[Task 15/25]  Current/Best:   10.57/  22.64 GFLOPS | Progress: (12/20) | 6.04 s
-[Task 15/25]  Current/Best:   22.80/  22.80 GFLOPS | Progress: (16/20) | 9.00 s
-[Task 15/25]  Current/Best:    9.86/  22.80 GFLOPS | Progress: (20/20) | 9.95 s
+[Task 15/25]  Current/Best:   16.17/  17.51 GFLOPS | Progress: (4/20) | 2.81 s
+[Task 15/25]  Current/Best:   14.10/  17.95 GFLOPS | Progress: (8/20) | 4.17 s
+[Task 15/25]  Current/Best:   10.36/  22.31 GFLOPS | Progress: (12/20) | 6.25 s
+[Task 15/25]  Current/Best:   20.36/  22.31 GFLOPS | Progress: (16/20) | 9.16 s
+[Task 15/25]  Current/Best:    9.37/  22.31 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:   20.60/  20.60 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 16/25]  Current/Best:    3.07/  20.60 GFLOPS | Progress: (8/20) | 4.58 s
-[Task 16/25]  Current/Best:   19.84/  20.60 GFLOPS | Progress: (12/20) | 5.78 s
-[Task 16/25]  Current/Best:   18.15/  20.60 GFLOPS | Progress: (16/20) | 7.10 s
-[Task 16/25]  Current/Best:   10.51/  21.90 GFLOPS | Progress: (20/20) | 9.11 s Done.
+[Task 16/25]  Current/Best:   20.21/  20.21 GFLOPS | Progress: (4/20) | 3.05 s
+[Task 16/25]  Current/Best:    3.03/  20.21 GFLOPS | Progress: (8/20) | 4.68 s
+[Task 16/25]  Current/Best:   19.00/  20.21 GFLOPS | Progress: (12/20) | 5.91 s
+[Task 16/25]  Current/Best:   17.77/  20.21 GFLOPS | Progress: (16/20) | 7.26 s
+[Task 16/25]  Current/Best:    9.98/  21.78 GFLOPS | Progress: (20/20) | 9.32 s Done.
 
 [Task 17/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25]  Current/Best:   12.71/  18.75 GFLOPS | Progress: (4/20) | 4.65 s
-[Task 17/25]  Current/Best:   14.53/  23.80 GFLOPS | Progress: (8/20) | 7.43 s
-[Task 17/25]  Current/Best:   18.78/  23.80 GFLOPS | Progress: (12/20) | 9.42 s
-[Task 17/25]  Current/Best:   18.47/  23.80 GFLOPS | Progress: (16/20) | 11.51 s
-[Task 17/25]  Current/Best:   10.22/  23.80 GFLOPS | Progress: (20/20) | 13.57 s Done.
+[Task 17/25]  Current/Best:   13.93/  18.27 GFLOPS | Progress: (4/20) | 4.79 s
+[Task 17/25]  Current/Best:   14.46/  23.10 GFLOPS | Progress: (8/20) | 7.60 s
+[Task 17/25]  Current/Best:   17.42/  23.10 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 17/25]  Current/Best:   16.67/  23.10 GFLOPS | Progress: (16/20) | 11.76 s
+[Task 17/25]  Current/Best:   10.03/  23.10 GFLOPS | Progress: (20/20) | 13.90 s Done.
 
 [Task 18/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25]  Current/Best:   11.70/  18.73 GFLOPS | Progress: (4/20) | 3.61 s
-[Task 18/25]  Current/Best:   10.78/  18.73 GFLOPS | Progress: (8/20) | 6.98 s
-[Task 18/25]  Current/Best:   19.44/  19.44 GFLOPS | Progress: (12/20) | 8.87 s
-[Task 18/25]  Current/Best:   10.67/  19.44 GFLOPS | Progress: (16/20) | 12.32 s
-[Task 18/25]  Current/Best:   20.82/  20.82 GFLOPS | Progress: (20/20) | 13.80 s Done.
+[Task 18/25]  Current/Best:   11.43/  17.97 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 18/25]  Current/Best:   10.60/  19.15 GFLOPS | Progress: (8/20) | 7.24 s
+[Task 18/25]  Current/Best:   19.25/  19.25 GFLOPS | Progress: (12/20) | 9.20 s
+[Task 18/25]  Current/Best:    9.90/  19.25 GFLOPS | Progress: (16/20) | 12.82 s
+[Task 18/25]  Current/Best:   20.70/  20.70 GFLOPS | Progress: (20/20) | 14.33 s Done.
 
 [Task 19/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25]  Current/Best:    7.47/  22.94 GFLOPS | Progress: (4/20) | 5.82 s
-[Task 19/25]  Current/Best:    2.74/  22.94 GFLOPS | Progress: (8/20) | 9.06 s
-[Task 19/25]  Current/Best:   17.58/  22.94 GFLOPS | Progress: (12/20) | 11.87 s
-[Task 19/25]  Current/Best:   14.23/  22.94 GFLOPS | Progress: (16/20) | 14.70 s
-[Task 19/25]  Current/Best:    2.75/  23.74 GFLOPS | Progress: (20/20) | 17.51 s Done.
+[Task 19/25]  Current/Best:    6.76/  20.18 GFLOPS | Progress: (4/20) | 6.23 s
+[Task 19/25]  Current/Best:    2.69/  20.18 GFLOPS | Progress: (8/20) | 9.50 s
+[Task 19/25]  Current/Best:   19.28/  20.89 GFLOPS | Progress: (12/20) | 12.27 s
+[Task 19/25]  Current/Best:   15.16/  20.89 GFLOPS | Progress: (16/20) | 15.06 s
+[Task 19/25]  Current/Best:    2.69/  22.49 GFLOPS | Progress: (20/20) | 17.87 s Done.
 
 [Task 20/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25]  Current/Best:    9.22/  15.58 GFLOPS | Progress: (4/20) | 3.26 s Done.
+[Task 20/25]  Current/Best:    9.59/  15.09 GFLOPS | Progress: (4/20) | 3.39 s Done.
  Done.
 
-[Task 20/25]  Current/Best:   10.12/  15.58 GFLOPS | Progress: (8/20) | 6.64 s
-[Task 20/25]  Current/Best:    2.36/  16.43 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 20/25]  Current/Best:   12.59/  16.43 GFLOPS | Progress: (16/20) | 14.05 s
-[Task 20/25]  Current/Best:   12.43/  22.65 GFLOPS | Progress: (20/20) | 16.11 s
+[Task 20/25]  Current/Best:   10.29/  15.09 GFLOPS | Progress: (8/20) | 6.89 s
+[Task 20/25]  Current/Best:    2.32/  16.71 GFLOPS | Progress: (12/20) | 10.82 s
+[Task 20/25]  Current/Best:   12.39/  16.71 GFLOPS | Progress: (16/20) | 14.48 s
+[Task 20/25]  Current/Best:   13.48/  21.64 GFLOPS | Progress: (20/20) | 16.61 s
 [Task 21/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25]  Current/Best:    6.53/  19.60 GFLOPS | Progress: (4/20) | 3.15 s
-[Task 21/25]  Current/Best:   14.86/  19.60 GFLOPS | Progress: (8/20) | 4.70 s
-[Task 21/25]  Current/Best:    1.64/  19.60 GFLOPS | Progress: (12/20) | 6.81 s
-[Task 21/25]  Current/Best:   18.46/  19.60 GFLOPS | Progress: (16/20) | 10.18 s
-[Task 21/25]  Current/Best:    4.53/  19.60 GFLOPS | Progress: (20/20) | 17.15 s
+[Task 21/25]  Current/Best:    6.39/  17.69 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 21/25]  Current/Best:   14.40/  17.69 GFLOPS | Progress: (8/20) | 4.89 s
+[Task 21/25]  Current/Best:    1.61/  17.69 GFLOPS | Progress: (12/20) | 7.08 s
+[Task 21/25]  Current/Best:   18.07/  18.07 GFLOPS | Progress: (16/20) | 10.62 s
+[Task 21/25]  Current/Best:    4.46/  18.07 GFLOPS | Progress: (20/20) | 17.86 s
 [Task 22/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25]  Current/Best:    2.75/  18.89 GFLOPS | Progress: (4/20) | 2.63 s
-[Task 22/25]  Current/Best:    8.91/  21.96 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 22/25]  Current/Best:   20.36/  21.96 GFLOPS | Progress: (12/20) | 6.86 s
-[Task 22/25]  Current/Best:   15.67/  21.96 GFLOPS | Progress: (16/20) | 8.88 s
-[Task 22/25]  Current/Best:   14.29/  21.96 GFLOPS | Progress: (20/20) | 10.50 s Done.
+[Task 22/25]  Current/Best:    2.70/  16.98 GFLOPS | Progress: (4/20) | 2.78 s
+[Task 22/25]  Current/Best:    9.16/  21.16 GFLOPS | Progress: (8/20) | 4.78 s
+[Task 22/25]  Current/Best:   19.61/  21.16 GFLOPS | Progress: (12/20) | 7.14 s
+[Task 22/25]  Current/Best:   15.10/  21.16 GFLOPS | Progress: (16/20) | 9.22 s
+[Task 22/25]  Current/Best:   14.80/  21.16 GFLOPS | Progress: (20/20) | 10.99 s Done.
 
 [Task 23/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25]  Current/Best:   18.05/  21.20 GFLOPS | Progress: (4/20) | 3.20 s
-[Task 23/25]  Current/Best:   15.05/  22.03 GFLOPS | Progress: (8/20) | 6.48 s
-[Task 23/25]  Current/Best:   21.34/  22.03 GFLOPS | Progress: (12/20) | 8.25 s
-[Task 23/25]  Current/Best:    6.66/  22.03 GFLOPS | Progress: (16/20) | 15.03 s
-[Task 23/25]  Current/Best:    8.18/  22.03 GFLOPS | Progress: (20/20) | 19.13 s Done.
+[Task 23/25]  Current/Best:   17.32/  20.04 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 23/25]  Current/Best:   16.09/  20.04 GFLOPS | Progress: (8/20) | 6.75 s
+[Task 23/25]  Current/Best:   20.70/  21.11 GFLOPS | Progress: (12/20) | 8.58 s
+[Task 23/25]  Current/Best:    6.20/  21.11 GFLOPS | Progress: (16/20) | 15.80 s
+[Task 23/25]  Current/Best:    7.34/  21.11 GFLOPS | Progress: (20/20) | 20.07 s Done.
 
 [Task 24/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25]  Current/Best:    9.10/   9.10 GFLOPS | Progress: (4/20) | 11.80 s
-[Task 24/25]  Current/Best:    2.13/   9.10 GFLOPS | Progress: (8/20) | 22.84 s
-[Task 24/25]  Current/Best:    4.49/   9.10 GFLOPS | Progress: (12/20) | 34.37 s Done.
+[Task 24/25]  Current/Best:    8.64/   8.64 GFLOPS | Progress: (4/20) | 11.91 s
+[Task 24/25]  Current/Best:    2.13/   8.64 GFLOPS | Progress: (8/20) | 22.99 s
+[Task 24/25]  Current/Best:    3.96/   8.64 GFLOPS | Progress: (12/20) | 34.58 s Done.
 
-[Task 24/25]  Current/Best:    5.95/   9.10 GFLOPS | Progress: (16/20) | 39.61 s
-[Task 24/25]  Current/Best:    3.40/   9.10 GFLOPS | Progress: (20/20) | 45.51 s Done.
+[Task 24/25]  Current/Best:    7.02/   8.64 GFLOPS | Progress: (16/20) | 40.04 s
+[Task 24/25]  Current/Best:    3.30/   8.90 GFLOPS | Progress: (20/20) | 46.01 s Done.
 
 [Task 25/25]  Current/Best:    0.00/   0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25]  Current/Best:    1.58/   2.81 GFLOPS | Progress: (4/20) | 11.55 s
-[Task 25/25]  Current/Best:    6.16/   8.47 GFLOPS | Progress: (8/20) | 22.83 s
-[Task 25/25]  Current/Best:    6.12/   8.47 GFLOPS | Progress: (12/20) | 34.27 s
-[Task 25/25]  Current/Best:    6.02/   8.71 GFLOPS | Progress: (16/20) | 35.97 s
-[Task 25/25]  Current/Best:    2.91/   9.48 GFLOPS | Progress: (20/20) | 46.69 s
+[Task 25/25]  Current/Best:    1.55/   2.92 GFLOPS | Progress: (4/20) | 11.66 s
+[Task 25/25]  Current/Best:    5.80/   7.46 GFLOPS | Progress: (8/20) | 22.97 s
+[Task 25/25]  Current/Best:    5.60/   7.46 GFLOPS | Progress: (12/20) | 34.49 s
+[Task 25/25]  Current/Best:    5.69/   9.18 GFLOPS | Progress: (16/20) | 36.45 s
+[Task 25/25]  Current/Best:    2.87/   9.18 GFLOPS | Progress: (20/20) | 47.13 s
 </pre></div>
 </div>
 <p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;unoptimized: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 383.3758860499802, &#39;median&#39;: 383.3882426499258, &#39;std&#39;: 0.31093456828347843}
-unoptimized: {&#39;mean&#39;: 495.8759032300077, &#39;median&#39;: 499.2053312498683, &#39;std&#39;: 7.764164250480838}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {&#39;mean&#39;: 413.2851679700025, &#39;median&#39;: 413.1391143000087, &#39;std&#39;: 0.6314766786546927}
+unoptimized: {&#39;mean&#39;: 498.4301331699976, &#39;median&#39;: 498.51982829999884, &#39;std&#39;: 0.4806910936114738}
 </pre></div>
 </div>
 </div>
@@ -996,7 +996,7 @@ models.</p>
 <p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
 supports many more features including cross-compilation, remote execution and
 profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  7.553 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes  26.466 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 211d1273d..5fc4bc177 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
 <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;</span><span class="si">%g</span><span class="s2"> secs/op&quot;</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.2e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.273e-07 secs/op
 </pre></div>
 </div>
 </div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 9eb294d4f..9d10fb5e3 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xdc50bb0)), stage(b, placeholder(b, 0x1789af20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x20e383a0)), stage(b, placeholder(b, 0x21738130)), 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=[ [...]
 </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 378bb307b..d6e744a7a 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:17.141</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:26.059</strong> total execution time for <strong>tutorial</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 83%" />
@@ -336,35 +336,35 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:07.553</p></td>
+<td><p>10:26.466</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:11.696</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>01:00.701</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.087</p></td>
+<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>00:59.456</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>00:29.983</p></td>
+<td><p>00:31.843</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>00:26.199</p></td>
+<td><p>00:25.207</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>00:00.802</p></td>
+<td><p>00:01.490</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.678</p></td>
+<td><p>00:00.722</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.134</p></td>
+<td><p>00:00.164</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -372,14 +372,14 @@
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
 <td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
 <td><p>00:00.001</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index f2e614ed6..21b8dd7dd 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,7 +542,7 @@ helper function to run a profile of the TVM generated code.</p>
 <span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">&quot;naive&quot;</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
 naive: 0.000006
 </pre></div>
 </div>
@@ -635,7 +635,7 @@ factor to be the number of threads on your CPU.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vector: 0.000024
+vector: 0.000025
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type=&quot;auto&quot;),
@@ -668,10 +668,10 @@ vector: 0.000024
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator                  Timing             Performance
-   numpy    7.400050017167814e-06                    1.0
-   naive    5.8132000000000005e-06    0.7855622578919891
-parallel              5.8428e-06      0.7895622308558649
-  vector             2.37836e-05      3.2139782764742155
+   numpy    8.03192000148556e-06                     1.0
+   naive    5.818700000000001e-06     0.7244469565090029
+parallel              6.0602e-06      0.7545144870565349
+  vector             2.46257e-05      3.0659792422540693
 </pre></div>
 </div>
 <div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
 <span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.015221
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019174
 </pre></div>
 </div>
 <p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-none: 3.425296
+none: 3.330907
 </pre></div>
 </div>
 <p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-blocking: 0.297018
+blocking: 0.332323
 </pre></div>
 </div>
 <p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-vectorization: 0.324939
+vectorization: 0.359443
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-loop permutation: 0.112317
+loop permutation: 0.124312
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-array packing: 0.105738
+array packing: 0.108148
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-block caching: 0.097653
+block caching: 0.110939
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
   &quot;target_host parameter is going to be deprecated. &quot;
-parallelization: 0.130493
+parallelization: 0.146840
 @main = primfn(A_1: handle, B_1: handle, C_1: handle) -&gt; ()
   attr = {&quot;from_legacy_te_schedule&quot;: True, &quot;global_symbol&quot;: &quot;main&quot;, &quot;tir.noalias&quot;: True}
   buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>        Operator                  Timing             Performance
-            none            3.4252957738                     1.0
-        blocking            0.2970183914      0.0867132098990943
-   vectorization            0.3249389654     0.09486449838447525
-loop permutation     0.11231713139999999     0.03279049133774399
-   array packing             0.105737908    0.030869716072050354
-   block caching            0.0976527841    0.028509299794471372
- parallelization            0.1304927843     0.03809679307058269
+            none            3.3309067194                     1.0
+        blocking     0.33232271850000006     0.09976944612842888
+   vectorization     0.35944334840000003     0.10791156243028834
+loop permutation     0.12431189620000001     0.03732073776668007
+   array packing     0.10814778759999999     0.03246797245030049
+   block caching     0.11093876620000001    0.033305876010836934
+ parallelization            0.1468397339     0.04408401263378831
 </pre></div>
 </div>
 <p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,7 @@ is</p>
 you can build generic templates of the matrix multiplication and other
 operations with tunable parameters that allows you to automatically optimize
 the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  0.087 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  0.701 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>