You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/09/09 04:21:48 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@89ce171b8697d223032f53b5e14c459332316da8)
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 7f1cb2c4c deploying docs (apache/tvm@89ce171b8697d223032f53b5e14c459332316da8)
7f1cb2c4c is described below
commit 7f1cb2c4cdbe6bd3c0e18a7043564087158599dd
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Sep 9 04:21:41 2022 +0000
deploying docs (apache/tvm@89ce171b8697d223032f53b5e14c459332316da8)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 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 | 855 +++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 87 +--
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../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 | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
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 | 14 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
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 | 19 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 854 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 87 +--
.../tune_with_autotvm/sg_execution_times.html | 14 +-
.../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/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 | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
121 files changed, 2208 insertions(+), 1271 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 ca8f9c75b..f0a65cd2d 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 3.814 seconds)
+ **Total running time of the script:** ( 1 minutes 3.512 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 057b57521..e757e317d 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.zip17743ad1-f46e-4ab0-839d-28517721a0e3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc40ac1ba-5ca7-490f-8d71-9be239be4132 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 0ec003c4d..4455cd390 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 55.9MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 49.5MB/s]
46%|####6 | 19.1M/41.5M [00:00<00:00, 46.5MB/s]
57%|#####6 | 23.6M/41.5M [00:00<00:00, 43.2MB/s]
67%|######6 | 27.7M/41.5M [00:00<00:00, 41.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.8MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 47.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 45.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 53.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 49.6MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 50.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.0MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 55.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 55.6MB/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 4df5d1c56..dc4a908a6 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]
46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
92%|#########1| 41.0M/44.7M [00:00<00:00, 201MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 203MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
25%|##4 | 11.0M/44.7M [00:00<00:00, 115MB/s]
49%|####9 | 22.0M/44.7M [00:00<00:00, 105MB/s]
72%|#######1 | 32.1M/44.7M [00:00<00:00, 86.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 101MB/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 a609d79da..75553cb40 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 1.582 seconds)
+ **Total running time of the script:** ( 1 minutes 5.541 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 8c651d1c1..c3d795e0f 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
=================
-**05:03.669** total execution time for **how_to_compile_models** files:
+**05:12.775** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.541 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.582 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.512 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.641 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:41.025 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.992 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.911 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.038 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.335 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.770 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.831 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.901 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.976 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.596 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.462 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.489 | 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 63674937c..c2947c8d1 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)
- 15.7863 15.7302 16.1000 15.6958 0.1203
+ 17.2846 16.1849 22.1064 16.0653 2.2413
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 150d1db48..69f526003 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 15.4M/170M [00:00<00:01, 162MB/s]
22%|##1 | 36.9M/170M [00:00<00:00, 199MB/s]
34%|###3 | 57.5M/170M [00:00<00:00, 207MB/s]
47%|####6 | 79.5M/170M [00:00<00:00, 216MB/s]
62%|######1 | 105M/170M [00:00<00:00, 233MB/s]
75%|#######4 | 127M/170M [00:00<00:00, 218MB/s]
88%|########8 | 150M/170M [00:00<00:00, 223MB/s]
100%|##########| 170M/170M [00:00<00:00, 212MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
12%|#1 | 19.6M/170M [00:00<00:00, 206MB/s]
23%|##3 | 39.3M/170M [00:00<00:00, 192MB/s]
34%|###3 | 57.7M/170M [00:00<00:00, 183MB/s]
47%|####7 | 80.2M/170M [00:00<00:00, 203MB/s]
59%|#####8 | 99.7M/170M [00:00<00:00, 197MB/s]
73%|#######3 | 124M/170M [00:00<00:00, 214MB/s]
85%|########5 | 145M/170M [00:00<00:00, 209MB/s]
98%|#########8| 167M/170M [00:00<00:00, 215MB/s]
100%|##########| 170M/170M [00:00<00:00, 205MB/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 55.015 seconds)
+ **Total running time of the script:** ( 2 minutes 57.821 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 e6b72fb0d..da63d65cf 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, 169MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
12%|#2 | 1.69M/13.6M [00:00<00:00, 17.4MB/s]
40%|#### | 5.44M/13.6M [00:00<00:00, 29.9MB/s]
61%|######1 | 8.30M/13.6M [00:00<00:00, 24.1MB/s]
82%|########2 | 11.1M/13.6M [00:00<00:00, 25.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 27.0MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3492 90.0470 97.2694 89.9033 1.0359
+ 90.2042 90.1217 91.2816 89.9329 0.2415
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.675 seconds)
+ **Total running time of the script:** ( 1 minutes 10.561 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 e401b9fe9..95a00b14b 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)
- 120.4961 120.4841 126.6318 118.7601 0.8529
+ 120.1075 120.1307 127.1741 118.1002 1.0104
@@ -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 58.396 seconds)
+ **Total running time of the script:** ( 1 minutes 53.512 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 71b4811d4..38d6047c5 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 36.324 seconds)
+ **Total running time of the script:** ( 1 minutes 22.808 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 56b73d213..d0083266b 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%|4 | 5769/132723 [00:00<00:02, 57684.55KB/s]
11%|# | 14049/132723 [00:00<00:01, 72455.17KB/s]
17%|#6 | 22314/132723 [00:00<00:01, 77100.37KB/s]
23%|##3 | 30556/132723 [00:00<00:01, 79196.89KB/s]
29%|##9 | 38721/132723 [00:00<00:01, 80073.25KB/s]
35%|###5 | 46968/132723 [00:00<00:01, 80886.37KB/s]
42%|####1 | 55113/132723 [00:00<00:00, 81069.63KB/s]
48%|####7 | 63301/132723 [00:00<00:00, 81323.73KB/s]
54%|#####3 | 71480/132723 [00:00<00:00, 81466.22KB/s]
60%|###### | 79720/132723 [00:01<00:00, 81751.85KB/s]
66%|######6 | 88000/132723 [00:01<00:00, 82067.07KB/s]
73%|#######2 | 96261/132723 [00:01<00:00, 82228.66KB/s]
79%|#######8 | 104518/132723 [00:01<00:00, 82328.69KB/s]
85%|########4 | 112796/132723 [00:01<00:00, 82462.46KB/s]
91%|#########1| 121043/132723 [00:01<00:00, 55543.77KB/s]
97%|########
#7| 129159/132723 [00:01<00:00, 61301.29KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73497.80KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6683/132723 [00:00<00:01, 66822.26KB/s]
11%|#1 | 15064/132723 [00:00<00:01, 76811.70KB/s]
17%|#7 | 22746/132723 [00:00<00:01, 64884.27KB/s]
23%|##3 | 31142/132723 [00:00<00:01, 71658.74KB/s]
30%|##9 | 39558/132723 [00:00<00:01, 75865.41KB/s]
36%|###6 | 48034/132723 [00:00<00:01, 78750.71KB/s]
43%|####2 | 56525/132723 [00:00<00:00, 80699.25KB/s]
49%|####8 | 64974/132723 [00:00<00:00, 81878.71KB/s]
55%|#####5 | 73319/132723 [00:00<00:00, 82359.84KB/s]
61%|######1 | 81621/132723 [00:01<00:00, 82558.35KB/s]
68%|######7 | 90095/132723 [00:01<00:00, 83218.05KB/s]
74%|#######4 | 98596/132723 [00:01<00:00, 83754.74KB/s]
81%|######## | 107076/132723 [00:01<00:00, 84062.61KB/s]
87%|########7 | 115493/132723 [00:01<00:00, 83975.73KB/s]
93%|#########3| 123945/132723 [00:01<00:00, 84136.11KB/s]
100%|########
#9| 132504/132723 [00:01<00:00, 84570.11KB/s]
100%|##########| 132723/132723 [00:01<00:00, 80639.96KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.106 seconds)
+ **Total running time of the script:** ( 2 minutes 36.854 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 1ac90bde2..a32b35c49 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:28.273** total execution time for **how_to_deploy_models** files:
+**11:16.270** 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``) | 02:55.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:57.821 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:35.106 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:36.854 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:58.396 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.512 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.324 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.808 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.675 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.453 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.983 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.730 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.776 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.949 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index f94aa1034..a85b439e6 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.zip208d4ed0-abb9-40e6-b534-4faa8be2f36e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf5ca2fa9-0548-475b-afce-1579086a2b8f 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 0cb1abbd5..a1fd381ce 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
=================
-**00:40.720** total execution time for **how_to_extend_tvm** files:
+**00:43.642** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:40.321 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.340 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.909 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.972 | 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 2d1d59332..2e9a3fb19 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: 6768us [6768us] (46.60%; 46.60%)
- FoldScaleAxis: 7756us [6us] (53.40%; 53.40%)
- FoldConstant: 7749us [1584us] (53.36%; 99.92%)
- InferType: 6166us [6166us] (42.45%; 79.56%)
+ InferType: 6972us [6972us] (46.65%; 46.65%)
+ FoldScaleAxis: 7974us [6us] (53.35%; 53.35%)
+ FoldConstant: 7968us [1555us] (53.31%; 99.92%)
+ InferType: 6413us [6413us] (42.91%; 80.49%)
@@ -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: 6231us [6231us] (44.59%; 44.59%)
- FoldScaleAxis: 7742us [5us] (55.41%; 55.41%)
- FoldConstant: 7738us [1568us] (55.37%; 99.94%)
- InferType: 6170us [6170us] (44.15%; 79.73%)
+ InferType: 6403us [6403us] (44.81%; 44.81%)
+ FoldScaleAxis: 7887us [5us] (55.19%; 55.19%)
+ FoldConstant: 7882us [1587us] (55.16%; 99.94%)
+ InferType: 6294us [6294us] (44.05%; 79.86%)
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 3b5b9e192..175ef1668 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: 54.168631 ms
+ Convolution: 34.731199 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 a2ae219c8..503eac569 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.767923 ms
+ conv2d with tensor core: 13.180346 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 a6986af31..a83cec7f4 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: 0.018024
- Baseline: 3.435788
+ Numpy running time: 0.018496
+ Baseline: 3.381006
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296037
+ Opt1: 0.305973
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.334691
+ Opt2: 0.336033
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116833
+ Opt3: 0.121890
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111166
+ Opt4: 0.112389
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110955
+ Opt5: 0.111781
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146793
+ Opt6: 0.147590
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 cb9447441..42ca92cae 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.595** total execution time for **how_to_optimize_operators** files:
+**00:34.967** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.215 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.402 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.298 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.414 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.082 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.151 | 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 12c4ea2c2..3a499150e 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
=================
-**06:21.840** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:25.786** 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``) | 03:36.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:36.847 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.366 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.769 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.689 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.522 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.814 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.756 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.102 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.581 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.969 | 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 cbf265548..044574cb9 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
@@ -240,105 +240,392 @@ 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" = 8;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- for (ff.outer.inner.init: int32, 0, 2) {
- let cse_var_1: int32 = (ff.outer.inner.init*7)
- {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [196], [], scope="local", align=32)[cse_var_1] = 0f32
- conv2d_nchw_1[(cse_var_1 + 14)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 1)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 15)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 2)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 16)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 3)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 17)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 4)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 18)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 5)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 19)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 6)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 20)] = 0f32
- }
- }
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 16)) < 8), dtype=bool) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 36) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4032) + (threadIdx.x_2*36)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[((((((blockIdx.x*294912) + (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*258048)) + (floordiv(threadIdx.x_2, 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)]
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*3136)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 686), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 735), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 833), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 931), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1078), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1127), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1274), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1519), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1617), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1715), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1813), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2009), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2058), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2107), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1707)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2254), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2303), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2401), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2450), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2499), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2597), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2050)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2695), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2793), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2842), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2891), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2989), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3038), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3185), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3234), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3283), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3381), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3430), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3479), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3577), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3626), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3675), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3773), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3822), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3871), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 3079)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 4018), 63)*49)) + rx.outer.outer) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*32)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 1), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 2), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 3)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 4), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 5), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 6)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 7), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 8), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 9)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 27)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 10), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 11), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 12)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 36)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 13), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 14), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 15)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 45)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 16), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 17), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 18)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 54)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 19), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 20), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 21)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 63)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 22), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 23), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 24)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 72)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 25)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 25), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 26)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 26), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 27)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 81)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 28)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 28), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 29)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 29), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 30)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 90)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 31)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 31), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
}
}
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 2) {
- let cse_var_16: int32 = (ff.outer.inner*7)
- let cse_var_15: int32 = (cse_var_16 + 6)
- let cse_var_14: int32 = (cse_var_16 + 5)
- let cse_var_13: int32 = (cse_var_16 + 4)
- let cse_var_12: int32 = (cse_var_16 + 3)
- let cse_var_11: int32 = (cse_var_16 + 20)
- let cse_var_10: int32 = (cse_var_16 + 2)
- let cse_var_9: int32 = (cse_var_16 + 19)
- let cse_var_8: int32 = (cse_var_16 + 18)
- let cse_var_7: int32 = (cse_var_16 + 17)
- let cse_var_6: int32 = (cse_var_16 + 16)
- let cse_var_5: int32 = (cse_var_16 + 15)
- let cse_var_4: int32 = (cse_var_16 + 14)
- let cse_var_3: int32 = (cse_var_16 + 1)
- {
- conv2d_nchw_1[cse_var_16] = (conv2d_nchw_1[cse_var_16] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_12] = (conv2d_nchw_1[cse_var_12] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_13] = (conv2d_nchw_1[cse_var_13] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_14] = (conv2d_nchw_1[cse_var_14] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_15] = (conv2d_nchw_1[cse_var_15] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- }
- }
- }
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.inner*24)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[cse_var_2]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 384)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 387)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 393)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 396)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 399)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 402)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 405)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 192)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 576)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 195)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 579)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 198)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 582)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 201)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 585)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 204)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 588)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 207)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 591)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 210)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 594)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 213)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 385)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 388)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 391)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 394)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 397)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 400)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 403)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 406)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 193)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 577)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 196)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 580)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 199)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 583)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 202)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 586)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 205)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 589)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 208)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 592)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 211)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 595)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 214)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 386)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 389)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 392)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 395)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 398)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 401)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 404)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 407)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 194)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 578)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 197)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 581)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 200)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 584)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 203)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 587)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 206)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 590)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 209)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 593)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 212)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 596)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 215)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 599)]))
}
}
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- let cse_var_17: int32 = ((i1.inner*7) + i3.inner)
- {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[cse_var_17] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[((((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner) + 1568)] = max((conv2d_nchw_1[(cse_var_17 + 14)] + bias[((((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 32)]), 0f32)
- }
- }
+ compute[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*4) + i1.inner)]), 0f32)
+ compute[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
}
}
}
@@ -393,7 +680,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.420 ms
+ Execution time of this operator: 0.414 ms
@@ -443,34 +730,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=16)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=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=7)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=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=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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=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)
@@ -488,16 +775,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=36)
+ 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=32)
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=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -515,74 +802,302 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
- for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
- conv2d_nchw[(ff_outer_inner_init * 7)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 14)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 1)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 15)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 2)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 16)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 3)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 17)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 4)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 18)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 5)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 19)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 6)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 20)] = 0.000000e+00f;
- }
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++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 * 392) + ((((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) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 4)) < 8) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 36; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4032) + (((int)threadIdx.x) * 36)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((int)blockIdx.x) * 294912) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 258048)) + ((((int)threadIdx.x) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)];
- }
+ extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[768];
+ conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 14)] = (conv2d_nchw[((ff_outer_inner * 7) + 14)] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 15)] = (conv2d_nchw[((ff_outer_inner * 7) + 15)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 16)] = (conv2d_nchw[((ff_outer_inner * 7) + 16)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 17)] = (conv2d_nchw[((ff_outer_inner * 7) + 17)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 18)] = (conv2d_nchw[((ff_outer_inner * 7) + 18)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 19)] = (conv2d_nchw[((ff_outer_inner * 7) + 19)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 20)] = (conv2d_nchw[((ff_outer_inner * 7) + 20)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- }
- }
- }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) * 32)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 3)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 9)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 6)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 18)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 8) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 9)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 27)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 10) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 11) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 12)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 36)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 13) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 14) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 15)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 45)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 16) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 17) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 18)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 54)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 19) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 20) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 21)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 63)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 22) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 23) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 24)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 72)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 25)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 25) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 26)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 26) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 27)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 81)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 28)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 28) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 29)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 29) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 30)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 90)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 31)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 31) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 384)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 387)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 393)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 396)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 399)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 402)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 405)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 192)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 576)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 195)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 579)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 198)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 582)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 201)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 585)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 204)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 588)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 207)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 591)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 210)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 594)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 213)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 385)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 388)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 391)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 394)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 397)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 400)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 403)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 406)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 193)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 577)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 196)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 580)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 199)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 583)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 202)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 586)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 205)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 589)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 208)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 592)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 211)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 595)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 214)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 386)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 389)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 392)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 395)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 398)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 401)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 404)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 407)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 194)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 578)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 197)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 581)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 200)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 584)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 203)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 587)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 206)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 590)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 209)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 593)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 212)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 596)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 215)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 599)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner) + 1568)] = max((conv2d_nchw[(((i1_inner * 7) + i3_inner) + 14)] + bias[((((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 32)]), 0.000000e+00f);
- }
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
}
}
@@ -636,7 +1151,7 @@ In the example below we resume the status and do more 5 trials.
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
-
+ .T
@@ -644,7 +1159,7 @@ 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 36.818 seconds)
+ **Total running time of the script:** ( 3 minutes 36.847 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 f713149a7..272fb9ac8 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)
- 9.8302 9.8440 9.8669 9.7798 0.0369
+ 9.8576 9.8545 9.8738 9.8446 0.0121
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 5c104b5a5..b15457f78 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)
- 756.2388 755.9175 757.5815 755.2175 0.9915
+ 759.7310 760.0380 760.9991 758.1561 1.1808
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.393 seconds)
+ **Total running time of the script:** ( 1 minutes 23.366 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 644ebc2c9..52110b666 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
@@ -397,79 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), 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, 32) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*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 (i.outer.inner: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
- let cse_var_20: int32 = (elem_idx*16)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 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, 4) {
+ 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.outer.inner*128) + (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)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 8) {
- let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
- let cse_var_22: int32 = (((i0.inner*512) + cse_var_23) + i1.inner)
- compute[cse_var_22] = max((compute_5[((((i0.inner*16) + cse_var_23) + i1.inner) - (floordiv(i0.outer.i1.outer.fused, 2)*16))] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -525,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.502 ms
+ Execution time of this operator: 1.454 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 59aa144ab..78813700e 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:47.214** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.636** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:47.177 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.604 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.023 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.006 | 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 |
+| :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_mobile_gpu.py` (``tune_relay_mobile_gpu.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 2e6558ce8..410a63e74 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: 128.67/128.67 result: MeasureResult(costs=(0.0017991688214285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8581395149230957, timestamp=1662680461.6663718) [('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: 0.00/128.67 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 199.78/199.78 result: MeasureResult(costs=(0.0011588081222222222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.055111885070801, timestamp=1662692627.9308276) [('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: 0.00/199.78 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: 261.01/261.01 result: MeasureResult(costs=(0.0008869559944751382,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.78175687789917, timestamp=1662680462.586266) [('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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.39/260.39 result: MeasureResult(costs=(0.0008890501049723757,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5887291431427002, timestamp=1662692628.8349879) [('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: 0.00/260.39 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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.39 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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.27/261.01 result: MeasureResult(costs=(0.04395225775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.882185459136963, timestamp=1662680467.2203062) [('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: 3.36/261.01 result: MeasureResult(costs=(0.06892849250000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.590003728866577, timestamp=1662680468.4531302) [('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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.27/260.39 result: MeasureResult(costs=(0.043887591749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8433284759521484, timestamp=1662692633.4025228) [('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: 3.34/260.39 result: MeasureResult(costs=(0.069245952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5606677532196045, timestamp=1662692634.639085) [('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: 0.00/260.39 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: 27.98/261.01 result: MeasureResult(costs=(0.008274430642857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.275554895401001, timestamp=1662680479.462969) [('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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.03/260.39 result: MeasureResult(costs=(0.0082589655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2980327606201172, timestamp=1662692645.7013125) [('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: 0.00/260.39 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: 0.00/261.01 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.39 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: 0.001219
+ Time cost of this operator: 0.001270
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 32cd475ad..7312eb987 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 310.3 98.729 (1, 2, 10, 10, 3) 2 1 [310.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.96 (1, 6, 10, 10) 1 1 [3.017]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.311 (1, 1, 10, 10, 3) 1 1 [0.978]
- Total_time - 314.295 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.6 98.727 (1, 2, 10, 10, 3) 2 1 [308.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.965 (1, 6, 10, 10) 1 1 [3.017]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.308 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 312.58 - - - - -
@@ -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 195.3 98.499 (1, 6, 10, 10, 1) 2 1 [195.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.027 1.022 (1, 6, 10, 10) 1 1 [2.027]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.949 0.478 (1, 3, 10, 10, 1) 1 1 [0.949]
- Total_time - 198.275 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 87.75 96.911 (1, 6, 10, 10, 1) 2 1 [87.75]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.83 2.021 (1, 6, 10, 10) 1 1 [1.83]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.068 (1, 1, 10, 10, 3) 1 1 [0.967]
+ Total_time - 90.547 - - - - -
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 ae1bbbc5c..3016cb488 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/tmpvv32kj0l/images/random'
+ '/tmp/tmp4qrceu5i/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpvv32kj0l/images/target contains 8144 images
- /tmp/tmpvv32kj0l/images/random contains 5000 images
+ /tmp/tmp4qrceu5i/images/target contains 8144 images
+ /tmp/tmp4qrceu5i/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2202 - accuracy: 0.9226 - val_loss: 0.1345 - val_accuracy: 0.9630
+ 328/328 - 56s - loss: 0.2353 - accuracy: 0.9230 - val_loss: 0.1403 - val_accuracy: 0.9588
Epoch 2/3
- 328/328 - 52s - loss: 0.0926 - accuracy: 0.9648 - val_loss: 0.1574 - val_accuracy: 0.9513
+ 328/328 - 53s - loss: 0.1084 - accuracy: 0.9600 - val_loss: 0.1259 - val_accuracy: 0.9551
Epoch 3/3
- 328/328 - 52s - loss: 0.0646 - accuracy: 0.9745 - val_loss: 0.1738 - val_accuracy: 0.9471
+ 328/328 - 52s - loss: 0.0667 - accuracy: 0.9751 - val_loss: 0.1312 - val_accuracy: 0.9562
- <keras.callbacks.History object at 0x7fe594f1ab90>
+ <keras.callbacks.History object at 0x7f3691a79650>
@@ -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 57.371 seconds)
+ **Total running time of the script:** ( 5 minutes 3.101 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 af347870c..28934ce99 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
=================
-**05:51.117** total execution time for **how_to_work_with_microtvm** files:
+**05:58.885** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:57.371 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:03.101 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.232 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.902 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.208 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.415 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.303 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.466 | 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 a8719f4d2..57b12d2b3 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
=================
-**00:42.813** total execution time for **how_to_work_with_relay** files:
+**00:43.390** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.055 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.858 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.849 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.394 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.479 | 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 a417cedad..dbb4347cd 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 0x7fe520748200>
+ <function my_cuda_math_rule at 0x7f36160534d0>
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 94a06f27d..7fc321945 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
=================
-**00:04.302** total execution time for **how_to_work_with_schedules** files:
+**00:04.274** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.961 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.001 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.070 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.987 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.567 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.098 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 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``) | 00:00.028 | 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_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 f8202f849..a29117269 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/tmp1smf4fmp/input0.cc'\nsource_filename = \"/tmp/tmp1smf4fmp/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/tmp6vbs7_sz/input0.cc'\nsource_filename = \"/tmp/tmp6vbs7_sz/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 fe967dfd5..b60ca14c0 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
=================
-**00:21.166** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.436** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.160 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.430 | 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 00b04ea55..3c6b83a84 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 22.72s!
+ resnet18_v1 inference graph built in 24.39s!
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 09d26c332..1284d9623 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 15.95s!
+ yolov3-tiny inference graph built in 17.05s!
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 17c4d24f2..323e4cf43 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
=================
-**01:31.523** total execution time for **topic_vta_tutorials_frontend** files:
+**01:34.844** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.459 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.972 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.063 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.872 | 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 e778c6ba0..2791146e8 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
=================
-**00:03.342** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.299** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.924 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.862 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.418 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.437 | 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 cb28b9d67..a0d516193 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
=================
-**00:00.769** total execution time for **topic_vta_tutorials** files:
+**00:00.795** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.412 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.421 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.357 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.373 | 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 ed9106a34..1d671ed26 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.485 ms
+ Execution time of this operator: 93.501 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 194316719..4d8c38222 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.49/10.49 result: MeasureResult(costs=(0.0255935978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5469872951507568, timestamp=1662679248.870281) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.67/10.49 result: MeasureResult(costs=(0.1006344324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7545621395111084, timestamp=1662679250.6463335) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022692057600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5711381435394287, timestamp=1662679251.7169244) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.83 result: MeasureResult(costs=(0.1450325686,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4517223834991455, timestamp=1662679254.751538) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.69/11.83 result: MeasureResult(costs=(0.0727773378,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.30503249168396, timestamp=1662679256.1901448) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.72/11.83 result: MeasureResult(costs=(0.1556953856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.614009380340576, timestamp=1662679259.3955157) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.86/11.83 result: MeasureResult(costs=(0.3133077082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.1336164474487305, timestamp=1662679264.5750794) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.55/11.83 result: MeasureResult(costs=(0.025448856599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5543022155761719, timestamp=1662679265.1476328) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.65/11.83 result: MeasureResult(costs=(0.16238124660000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6933515071868896, timestamp=1662679267.960986) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.46/11.83 result: MeasureResult(costs=(0.10907074480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8524575233459473, timestamp=1662679269.8713691) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.025981204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.546959638595581, timestamp=1662691410.4482334) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.92/10.33 result: MeasureResult(costs=(0.0917891412,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.608830451965332, timestamp=1662691412.6035182) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.70/11.70 result: MeasureResult(costs=(0.0229481582,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5848186016082764, timestamp=1662691413.1747024) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.39/11.70 result: MeasureResult(costs=(0.19307266979999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.212522506713867, timestamp=1662691416.9687262) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.69/11.70 result: MeasureResult(costs=(0.0726816568,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2991490364074707, timestamp=1662691418.400518) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.78/11.70 result: MeasureResult(costs=(0.1505677104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5663702487945557, timestamp=1662691421.0122435) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.70 result: MeasureResult(costs=(0.30855539239999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.057368278503418, timestamp=1662691426.6476173) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.61/11.70 result: MeasureResult(costs=(0.0252996838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5468590259552002, timestamp=1662691427.21572) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.76/11.70 result: MeasureResult(costs=(0.152836349,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5458760261535645, timestamp=1662691429.8814402) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.65/11.70 result: MeasureResult(costs=(0.10143048480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7285714149475098, timestamp=1662691431.665993) [('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 6742bc11f..4e3728acd 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': 495.29929663003713, 'median': 495.0232297499497, 'std': 0.5934874365415119}
+ {'mean': 497.83906563998244, 'median': 498.26264240000455, 'std': 1.5189290095920485}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (4/20) | 6.40 s
[Task 1/25] Current/Best: 6.16/ 17.60 GFLOPS | Progress: (8/20) | 9.45 s
[Task 1/25] Current/Best: 11.52/ 22.72 GFLOPS | Progress: (12/20) | 11.94 s
[Task 1/25] Current/Best: 16.54/ 22.72 GFLOPS | Progress: (16/20) | 13.63 s
[Task 1/25] Current/Best: 11.63/ 23.85 GFLOPS | Progress: (20/20) | 15.38 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.13/ 12.68 GFLOPS | Progress: (4/20) | 3.76 s
[Task 2/25] Current/Best: 14.05/ 18.79 GFLOPS | Progress: (8/20) | 5.06 s
[Task 2/25] Current/Best: 21.15/ 21.15 GFLOPS | Progress: (12/20) | 6.39 s
[Task 2/25] Current/Best: 12.75/ 21.15 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 19.33/ 21.15 GFLOPS | Progress: (20/20) | 9.27 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/ 10.84 GFLOPS | Progress: (4/20) | 5.88 s
[Task 3/25] Current/Best: 15.35/ 16.84 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 15.03/ 16.84 GFLOPS | Progress: (12/20) | 9.55 s
[Task 3/25] Current/Best: 7.22/ 23.84 GFLOPS | Progress: (16/20) | 11.47 s
[Task 3/25] Current/Best: 12.38/ 23.84 GFLOPS | Progress: (20/20) | 16.04 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.52/ 20.34 GFLOPS | Progress: (4/20) | 2.43 s
[Task 4/25] Current/Best: 6.72/ 20.34 GFLOPS | Progress: (8/20) | 7.12 s
[Task 4/25] Current/Best: 22.57/ 22.57 GFLOPS | Progress: (12/20) | 12.08 s
[Task 4/25] Current/Best: 17.00/ 22.57 GFLOPS | Progress: (16/20) | 14.45 s
[Task 4/25] Current/Best: 13.48/ 22.57 GFLOPS | Progress: (20/20) | 16.41 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.52/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.70/ 12.69 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.68/ 17.99 GFLOPS | Progress: (12/20) | 7.90 s
[Task 5/25] Current/Best: 11.54/ 22.50 GFLOPS | Progress: (16/20) | 9.31 s
[Task 5/25] Current/Best: 12.04/ 22.50 GFLOPS | Progress: (20/20) | 11.25 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.12/ 20.07 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 18.94/ 20.07 GFLOPS | Progress: (8/20) | 5.91 s
[Task 6/25] Current/Best: 13.15/ 20.07 GFLOPS | Progress: (12/20) | 7.88 s
[Task 6/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (16/20) | 10.14 s
[Task 6/25] Current/Best: 3.72/ 20.09 GFLOPS | Progress: (20/20) | 12.68 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.08/ 12.98 GFLOPS | Progress: (4/20) | 3.58 s
[Task 7/25] Current/Best: 20.30/ 21.03 GFLOPS | Progress: (8/20) | 5.10 s
[Task 7/25] Current/Best: 16.13/ 21.03 GFLOPS | Progress: (12/20) | 7.01 s
[Task 7/25] Current/Best: 12.18/ 21.03 GFLOPS | Progress: (16/20) | 9.06 s
[Task 7/25] Current/Best: 6.31/ 21.83 GFLOPS | Progress: (20/20) | 11.53 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.69/ 13.76 GFLOPS | Progress: (4/20) | 2.99 s
[Task 8/25] Current/Best: 9.20/ 13.76 GFLOPS | Progress: (8/20) | 8.13 s
[Task 8/25] Current/Best: 12.72/ 13.76 GFLOPS | Progress: (12/20) | 14.62 s
[Task 8/25] Current/Best: 18.98/ 18.98 GFLOPS | Progress: (16/20) | 16.73 s
[Task 8/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (20/20) | 23.79 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.38/ 15.66 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 23.42/ 23.42 GFLOPS | Progress: (8/20) | 13.79 s
[Task 9/25] Current/Best: 8.23/ 23.42 GFLOPS | Progress: (12/20) | 16.29 s
[Task 9/25] Current/Best: 17.98/ 23.42 GFLOPS | Progress: (16/20) | 19.02 s
[Task 9/25] Current/Best: 9.18/ 23.42 GFLOPS | Progress: (20/20) | 27.38 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (4/20) | 2.61 s
[Task 10/25] Current/Best: 15.60/ 18.06 GFLOPS | Progress: (8/20) | 4.24 s
[Task 10/25] Current/Best: 12.51/ 19.03 GFLOPS | Progress: (12/20) | 5.80 s
[Task 10/25] Current/Best: 19.11/ 20.23 GFLOPS | Progress: (16/20) | 6.91 s
[Task 10/25] Current/Best: 8.84/ 20.23 GFLOPS | Progress: (20/20
) | 8.49 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.58/ 18.19 GFLOPS | Progress: (4/20) | 3.40 s
[Task 11/25] Current/Best: 16.94/ 18.19 GFLOPS | Progress: (8/20) | 6.22 s
[Task 11/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (12/20) | 8.33 s
[Task 11/25] Current/Best: 13.46/ 20.89 GFLOPS | Progress: (16/20) | 11.25 s
[Task 11/25] Current/Best: 19.32/ 21.59 GFLOPS | Progress: (20/20) | 13.38 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.73/ 17.92 GFLOPS | Progress: (4/20) | 5.73 s
[Task 12/25] Current/Best: 5.16/ 17.92 GFLOPS | Progress: (8/20) | 9.62 s
[Task 12/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (12/20) | 11.64 s
[Task 12/25] Current/Best: 15.23/ 18.94 GFLOPS | Progress: (16/20) | 14.59 s
[Task 12/25] Current/Best: 15.15/ 18.94 GFLOPS | Progress: (20/20) | 16.50 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.60/ 17.38 GFLOPS | Progress: (4/20) | 3.78 s
[Task 13/25] Current/Best: 15.81/ 20.92 GFLOPS | Progress: (8/20) | 6.40 s
[Task 13/25] Current/Best: 19.68/ 22.04 GFLOPS | Progress: (12/20) | 9.52 s
[Task 13/25] Current/Best: 12.28/ 22.04 GFLOPS | Progress: (16/20) | 12.99 s
[Task 13/25] Current/Best: 18.73/ 22.04 GFLOPS | Progress: (20/20) | 15.38 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.80/ 13.80 GFLOPS | Progress: (4/20) | 3.47 s
[Task 14/25] Current/Best: 6.12/ 13.80 GFLOPS | Progress: (8/20) | 5.69 s
[Task 14/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (12/20) | 8.37 s
[Task 14/25] Current/Best: 17.66/ 20.98 GFLOPS | Progress: (16/20) | 10.02 s Done.
-
[Task 14/25] Current/Best: 16.97/ 20.98 GFLOPS | Progress: (20/20) | 11.86 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.20/ 17.62 GFLOPS | Progress: (4/20) | 2.77 s
[Task 15/25] Current/Best: 14.24/ 18.02 GFLOPS | Progress: (8/20) | 4.07 s
[Task 15/25] Current/Best: 10.39/ 22.42 GFLOPS | Progress: (12/20) | 6.30 s
[Task 15/25] Current/Best: 20.42/ 22.42 GFLOPS | Progress: (16/20) | 9.69 s
[Task 15/25] Current/Best: 9.70/ 22.42 GFLOPS | Progress: (20/20) | 10.71 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.23/ 20.23 GFLOPS | Progress: (4/20) | 3.03 s
[Task 16/25] Current/Best: 3.04/ 20.23 GFLOPS | Progress: (8/20) | 4.64 s
[Task 16/25] Current/Best: 19.52/ 20.23 GFLOPS | Progress: (12/20) | 5.87 s
[Task 16/25] Current/Best: 17.46/ 20.23 GFLOPS | Progress: (16/20) |
7.23 s
[Task 16/25] Current/Best: 9.98/ 21.99 GFLOPS | Progress: (20/20) | 9.40 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.10/ 18.22 GFLOPS | Progress: (4/20) | 4.84 s
[Task 17/25] Current/Best: 14.45/ 22.81 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 17.69/ 22.81 GFLOPS | Progress: (12/20) | 9.69 s
[Task 17/25] Current/Best: 16.54/ 22.81 GFLOPS | Progress: (16/20) | 11.89 s
[Task 17/25] Current/Best: 10.06/ 22.81 GFLOPS | Progress: (20/20) | 14.05 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.31/ 17.96 GFLOPS | Progress: (4/20) | 3.84 s
[Task 18/25] Current/Best: 10.55/ 19.61 GFLOPS | Progress: (8/20) | 7.49 s
[Task 18/25] Current/Best: 19.53/ 19.61 GFLOPS | Progress: (12/20) | 9.43 s
[Task 18/25] Current/Best: 10.03/ 19.61 GFLOPS | Progress: (16/20) | 13.30 s
[Task 18/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (20/20) | 14.81 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.41 GFLOPS | Progress: (4/20) | 6.11 s
[Task 19/25] Current/Best: 2.70/ 20.41 GFLOPS | Progress: (8/20) | 9.42 s
[Task 19/25] Current/Best: 19.93/ 21.61 GFLOPS | Progress: (12/20) | 12.42 s
[Task 19/25] Current/Best: 14.21/ 22.54 GFLOPS | Progress: (16/20) | 15.36 s
[Task 19/25] Current/Best: 2.70/ 23.20 GFLOPS | Progress: (20/20) | 18.22 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.66/ 14.87 GFLOPS | Progress: (4/20) | 3.40 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.50/ 17.50 GFLOPS | Progress: (4/20) | 6.47 s
[Task 1/25] Current/Best: 6.16/ 17.50 GFLOPS | Progress: (8/20) | 9.53 s
[Task 1/25] Current/Best: 11.52/ 22.73 GFLOPS | Progress: (12/20) | 11.96 s
[Task 1/25] Current/Best: 16.39/ 22.73 GFLOPS | Progress: (16/20) | 13.65 s
[Task 1/25] Current/Best: 11.57/ 23.81 GFLOPS | Progress: (20/20) | 15.41 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.24/ 12.87 GFLOPS | Progress: (4/20) | 3.90 s
[Task 2/25] Current/Best: 14.03/ 17.42 GFLOPS | Progress: (8/20) | 5.20 s
[Task 2/25] Current/Best: 20.91/ 20.91 GFLOPS | Progress: (12/20) | 6.55 s
[Task 2/25] Current/Best: 12.10/ 20.91 GFLOPS | Progress: (16/20) | 7.85 s
[Task 2/25] Current/Best: 19.65/ 20.91 GFLOPS | Progress: (20/20) | 9.46 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/ 10.74 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.25/ 16.76 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 14.84/ 16.76 GFLOPS | Progress: (12/20) | 9.58 s
[Task 3/25] Current/Best: 7.13/ 23.65 GFLOPS | Progress: (16/20) | 11.56 s
[Task 3/25] Current/Best: 12.30/ 23.65 GFLOPS | Progress: (20/20) | 16.15 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.52/ 20.24 GFLOPS | Progress: (4/20) | 2.47 s
[Task 4/25] Current/Best: 6.77/ 20.24 GFLOPS | Progress: (8/20) | 6.90 s
[Task 4/25] Current/Best: 22.15/ 22.15 GFLOPS | Progress: (12/20) | 11.52 s
[Task 4/25] Current/Best: 17.02/ 22.15 GFLOPS | Progress: (16/20) | 13.78 s
[Task 4/25] Current/Best: 12.96/ 22.15 GFLOPS | Progress: (20/20) | 15.73 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.69/ 10.25 GFLOPS | Progress: (4/20) | 2.72 s
[Task 5/25] Current/Best: 10.80/ 12.77 GFLOPS | Progress: (8/20) | 4.85 s
[Task 5/25] Current/Best: 9.74/ 17.57 GFLOPS | Progress: (12/20) | 7.90 s
[Task 5/25] Current/Best: 11.10/ 22.21 GFLOPS | Progress: (16/20) | 9.34 s
[Task 5/25] Current/Best: 11.86/ 22.21 GFLOPS | Progress: (20/20) | 11.29 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.11/ 19.92 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 18.76/ 19.92 GFLOPS | Progress: (8/20) | 5.94 s
[Task 6/25] Current/Best: 12.80/ 19.92 GFLOPS | Progress: (12/20) | 7.89 s
[Task 6/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (16/20) | 10.22 s
[Task 6/25] Current/Best: 3.76/ 19.96 GFLOPS | Progress: (20/20) | 12.74 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.08/ 12.75 GFLOPS | Progress: (4/20) | 3.67 s
[Task 7/25] Current/Best: 20.11/ 21.10 GFLOPS | Progress: (8/20) | 5.21 s
[Task 7/25] Current/Best: 16.00/ 21.10 GFLOPS | Progress: (12/20) | 7.14 s
[Task 7/25] Current/Best: 12.14/ 21.10 GFLOPS | Progress: (16/20) | 9.21 s
[Task 7/25] Current/Best: 6.23/ 21.54 GFLOPS | Progress: (20/20) | 11.73 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.05/ 13.78 GFLOPS | Progress: (4/20) | 3.03 s
[Task 8/25] Current/Best: 9.88/ 13.78 GFLOPS | Progress: (8/20) | 7.88 s
[Task 8/25] Current/Best: 13.02/ 13.78 GFLOPS | Progress: (12/20) | 14.22 s
[Task 8/25] Current/Best: 19.11/ 19.11 GFLOPS | Progress: (16/20) | 16.32 s
[Task 8/25] Current/Best: 18.91/ 19.11 GFLOPS | Progress: (20/20) | 22.95 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.17/ 15.56 GFLOPS | Progress: (4/20) | 12.06 s
[Task 9/25] Current/Best: 23.19/ 23.19 GFLOPS | Progress: (8/20) | 13.98 s
[Task 9/25] Current/Best: 8.25/ 23.19 GFLOPS | Progress: (12/20) | 16.43 s
[Task 9/25] Current/Best: 17.92/ 23.19 GFLOPS | Progress: (16/20) | 19.16 s
[Task 9/25] Current/Best: 9.02/ 23.19 GFLOPS | Progress: (20/20) | 27.20 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.61 s
[Task 10/25] Current/Best: 15.58/ 18.15 GFLOPS | Progress: (8/20) | 4.21 s
[Task 10/25] Current/Best: 12.27/ 18.74 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 18.93/ 20.38 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.75/ 20.38 GFLOPS | Progress: (20/20
) | 8.42 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.28/ 18.21 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 16.88/ 18.21 GFLOPS | Progress: (8/20) | 6.11 s
[Task 11/25] Current/Best: 18.08/ 18.21 GFLOPS | Progress: (12/20) | 8.18 s
[Task 11/25] Current/Best: 12.95/ 20.83 GFLOPS | Progress: (16/20) | 11.01 s
[Task 11/25] Current/Best: 19.47/ 21.20 GFLOPS | Progress: (20/20) | 13.03 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.80/ 17.94 GFLOPS | Progress: (4/20) | 5.53 s
[Task 12/25] Current/Best: 5.18/ 17.94 GFLOPS | Progress: (8/20) | 9.27 s
[Task 12/25] Current/Best: 18.76/ 18.81 GFLOPS | Progress: (12/20) | 11.28 s
[Task 12/25] Current/Best: 15.28/ 18.81 GFLOPS | Progress: (16/20) | 14.09 s
[Task 12/25] Current/Best: 15.13/ 18.81 GFLOPS | Progress: (20/20) | 16.01 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.58/ 17.27 GFLOPS | Progress: (4/20) | 3.78 s
[Task 13/25] Current/Best: 15.54/ 20.94 GFLOPS | Progress: (8/20) | 6.23 s
[Task 13/25] Current/Best: 19.78/ 22.03 GFLOPS | Progress: (12/20) | 9.14 s
[Task 13/25] Current/Best: 12.31/ 22.03 GFLOPS | Progress: (16/20) | 12.54 s
[Task 13/25] Current/Best: 18.73/ 22.03 GFLOPS | Progress: (20/20) | 14.78 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) | 3.34 s
[Task 14/25] Current/Best: 6.10/ 13.67 GFLOPS | Progress: (8/20) | 5.53 s
[Task 14/25] Current/Best: 20.13/ 20.13 GFLOPS | Progress: (12/20) | 8.06 s
[Task 14/25] Current/Best: 16.28/ 20.13 GFLOPS | Progress: (16/20) | 9.71 s Done.
+
[Task 14/25] Current/Best: 17.12/ 20.13 GFLOPS | Progress: (20/20) | 11.48 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.06/ 17.64 GFLOPS | Progress: (4/20) | 2.82 s
[Task 15/25] Current/Best: 14.47/ 18.04 GFLOPS | Progress: (8/20) | 4.16 s
[Task 15/25] Current/Best: 10.40/ 22.33 GFLOPS | Progress: (12/20) | 6.24 s
[Task 15/25] Current/Best: 20.40/ 22.33 GFLOPS | Progress: (16/20) | 9.23 s
[Task 15/25] Current/Best: 9.67/ 22.33 GFLOPS | Progress: (20/20) | 10.21 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.42/ 20.42 GFLOPS | Progress: (4/20) | 3.01 s
[Task 16/25] Current/Best: 3.04/ 20.42 GFLOPS | Progress: (8/20) | 4.62 s
[Task 16/25] Current/Best: 19.40/ 20.42 GFLOPS | Progress: (12/20) | 5.84 s
[Task 16/25] Current/Best: 17.62/ 20.42 GFLOPS | Progress: (16/20) |
7.18 s
[Task 16/25] Current/Best: 9.93/ 21.84 GFLOPS | Progress: (20/20) | 9.24 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.16/ 16.31 GFLOPS | Progress: (4/20) | 4.78 s
[Task 17/25] Current/Best: 14.41/ 23.38 GFLOPS | Progress: (8/20) | 7.64 s
[Task 17/25] Current/Best: 18.12/ 23.38 GFLOPS | Progress: (12/20) | 9.68 s
[Task 17/25] Current/Best: 16.53/ 23.38 GFLOPS | Progress: (16/20) | 11.82 s
[Task 17/25] Current/Best: 10.05/ 23.38 GFLOPS | Progress: (20/20) | 13.95 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.38/ 17.81 GFLOPS | Progress: (4/20) | 3.68 s
[Task 18/25] Current/Best: 10.60/ 20.21 GFLOPS | Progress: (8/20) | 7.08 s
[Task 18/25] Current/Best: 19.31/ 20.21 GFLOPS | Progress: (12/20) | 9.01 s
[Task 18/25] Current/Best: 9.98/ 20.21 GFLOPS | Progress: (16/20) | 12.61 s
[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.02/ 20.39 GFLOPS | Progress: (4/20) | 6.02 s
[Task 19/25] Current/Best: 2.69/ 20.39 GFLOPS | Progress: (8/20) | 9.26 s
[Task 19/25] Current/Best: 20.05/ 21.82 GFLOPS | Progress: (12/20) | 12.00 s
[Task 19/25] Current/Best: 14.16/ 22.10 GFLOPS | Progress: (16/20) | 14.87 s
[Task 19/25] Current/Best: 2.70/ 23.10 GFLOPS | Progress: (20/20) | 17.69 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.31/ 15.21 GFLOPS | Progress: (4/20) | 3.34 s Done.
Done.
-
[Task 20/25] Current/Best: 10.05/ 14.87 GFLOPS | Progress: (8/20) | 6.79 s
[Task 20/25] Current/Best: 2.32/ 16.72 GFLOPS | Progress: (12/20) | 10.74 s
[Task 20/25] Current/Best: 11.94/ 16.72 GFLOPS | Progress: (16/20) | 14.49 s
[Task 20/25] Current/Best: 12.25/ 22.14 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: 6.42/ 17.72 GFLOPS | Progress: (4/20) | 3.31 s
[Task 21/25] Current/Best: 14.65/ 17.72 GFLOPS | Progress: (8/20) | 4.94 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.08 s
[Task 21/25] Current/Best: 16.79/ 17.72 GFLOPS | Progress: (16/20) | 10.61 s
[Task 21/25] Current/Best: 4.47/ 17.72 GFLOPS | Progress: (20/20) | 17.89 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20
) | 2.71 s
[Task 22/25] Current/Best: 8.83/ 21.93 GFLOPS | Progress: (8/20) | 4.77 s
[Task 22/25] Current/Best: 20.00/ 21.93 GFLOPS | Progress: (12/20) | 7.18 s
[Task 22/25] Current/Best: 15.32/ 21.93 GFLOPS | Progress: (16/20) | 9.31 s
[Task 22/25] Current/Best: 13.90/ 21.93 GFLOPS | Progress: (20/20) | 11.06 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.63/ 20.75 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 14.39/ 20.75 GFLOPS | Progress: (8/20) | 6.71 s
[Task 23/25] Current/Best: 21.04/ 21.60 GFLOPS | Progress: (12/20) | 8.54 s
[Task 23/25] Current/Best: 6.26/ 21.60 GFLOPS | Progress: (16/20) | 15.53 s
[Task 23/25] Current/Best: 7.88/ 21.60 GFLOPS | Progress: (20/20) | 19.73 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.85 s
[Task 24/25] Current/Best: 3.66/ 8.47 GFLOPS | Progress: (8/20) | 23.11 s
[Task 24/25] Current/Best: 4.19/ 8.47 GFLOPS | Progress: (12/20) | 33.83 s Done.
-
[Task 24/25] Current/Best: 6.78/ 8.89 GFLOPS | Progress: (16/20) | 39.49 s
[Task 24/25] Current/Best: 3.35/ 8.89 GFLOPS | Progress: (20/20) | 45.54 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/ 2.76 GFLOPS | Progress: (4/20) | 11.62 s
[Task 25/25] Current/Best: 5.96/ 7.92 GFLOPS | Progress: (8/20) | 22.93 s
[Task 25/25] Current/Best: 6.11/ 7.92 GFLOPS | Progress: (12/20) | 34.41 s
[Task 25/25] Current/Best: 5.89/ 8.63 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.88/ 9.13 GFLOPS | Progress: (20/20) | 46.82 s
+
[Task 20/25] Current/Best: 10.19/ 15.21 GFLOPS | Progress: (8/20) | 6.63 s
[Task 20/25] Current/Best: 2.32/ 16.68 GFLOPS | Progress: (12/20) | 10.55 s
[Task 20/25] Current/Best: 12.38/ 16.68 GFLOPS | Progress: (16/20) | 14.33 s
[Task 20/25] Current/Best: 12.65/ 21.90 GFLOPS | Progress: (20/20) | 16.42 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.73 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.60/ 17.73 GFLOPS | Progress: (8/20) | 4.83 s
[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 6.96 s
[Task 21/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (16/20) | 10.40 s
[Task 21/25] Current/Best: 4.47/ 18.06 GFLOPS | Progress: (20/20) | 17.57 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 8.75/ 21.84 GFLOPS | Progress: (8/20) | 4.69 s
[Task 22/25] Current/Best: 19.90/ 21.84 GFLOPS | Progress: (12/20) | 7.01 s
[Task 22/25] Current/Best: 15.51/ 21.84 GFLOPS | Progress: (16/20) | 9.05 s
[Task 22/25] Current/Best: 13.74/ 21.84 GFLOPS | Progress: (20/20) | 10.77 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.69/ 20.79 GFLOPS | Progress: (4/20) | 3.26 s
[Task 23/25] Current/Best: 15.27/ 20.79 GFLOPS | Progress: (8/20) | 6.61 s
[Task 23/25] Current/Best: 20.98/ 21.61 GFLOPS | Progress: (12/20) | 8.42 s
[Task 23/25] Current/Best: 6.40/ 21.61 GFLOPS | Progress: (16/20) | 15.40 s
[Task 23/25] Current/Best: 7.72/ 21.61 GFLOPS | Progress: (20/20) | 19.60 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.69/ 8.69 GFLOPS | Progress: (4/20) | 11.83 s
[Task 24/25] Current/Best: 3.50/ 8.69 GFLOPS | Progress: (8/20) | 23.09 s
[Task 24/25] Current/Best: 4.61/ 8.69 GFLOPS | Progress: (12/20) | 33.81 s Done.
+
[Task 24/25] Current/Best: 6.13/ 8.73 GFLOPS | Progress: (16/20) | 39.35 s
[Task 24/25] Current/Best: 3.33/ 8.73 GFLOPS | Progress: (20/20) | 45.24 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.92/ 7.98 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 6.04/ 7.98 GFLOPS | Progress: (12/20) | 34.37 s
[Task 25/25] Current/Best: 5.90/ 8.81 GFLOPS | Progress: (16/20) | 36.22 s
[Task 25/25] Current/Best: 2.88/ 8.81 GFLOPS | Progress: (20/20) | 46.92 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.14941426999576, 'median': 409.1582320499583, 'std': 0.7372720689148065}
- unoptimized: {'mean': 495.29929663003713, 'median': 495.0232297499497, 'std': 0.5934874365415119}
+ optimized: {'mean': 410.80024174003483, 'median': 410.7523118000245, 'std': 1.2238987442422715}
+ unoptimized: {'mean': 497.83906563998244, 'median': 498.26264240000455, 'std': 1.5189290095920485}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 25.921 seconds)
+ **Total running time of the script:** ( 10 minutes 20.410 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 2af943871..f826aca42 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
- 1.23e-07 secs/op
+ 1.29e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index cac4bb96e..8baa3a931 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, 0xe96b680)), stage(b, placeholder(b, 0x21e756d0)), 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, 0x23065af0)), stage(b, placeholder(b, 0x2842eff0)), 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 bf161fa5d..81b83799a 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:13.379** total execution time for **tutorial** files:
+**13:13.521** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:25.921 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:20.410 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.079 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.601 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.733 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.059 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.719 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.151 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.539 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.687 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.703 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.769 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.514 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.691 | 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_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.144 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 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 |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 0bf2fca38..ff34bfdb3 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: 0.000008
+ Numpy running time: 0.000007
naive: 0.000006
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/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. "
- parallel: 0.000008
+ parallel: 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: 0.000025
+ vector: 0.000034
@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 7.823169999028324e-06 1.0
- naive 5.811899999999999e-06 0.7429085652902679
- parallel 7.5448e-06 0.9644172376334786
- vector 2.4551e-05 3.1382419151123333
+ numpy 7.2782999995979485e-06 1.0
+ naive 5.8009e-06 0.7970130388030776
+ parallel 6.0311e-06 0.8286413036468896
+ vector 3.40965e-05 4.684679114887197
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017740
+ Numpy running time: 0.017684
@@ -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: 3.437629
+ none: 3.369353
@@ -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: 0.299352
+ blocking: 0.306064
@@ -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: 0.335210
+ vectorization: 0.344899
@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: 0.113478
+ loop permutation: 0.116972
@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: 0.107497
+ array packing: 0.108005
@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: 0.110857
+ block caching: 0.109518
@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: 0.146027
+ parallelization: 0.146102
@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 3.4376288085 1.0
- blocking 0.2993515676 0.08708082933788923
- vectorization 0.3352102837 0.09751206496499781
- loop permutation 0.1134779515 0.03301053075288713
- array packing 0.1074966189 0.03127057192277425
- block caching 0.1108566097 0.03224798716658765
- parallelization 0.1460270042 0.04247899128577483
+ none 3.3693528731 1.0
+ blocking 0.3060636917 0.09083752970593538
+ vectorization 0.3448987818 0.10236350859940446
+ loop permutation 0.1169717835 0.03471639448449315
+ array packing 0.10800539089999998 0.03205523284969222
+ block caching 0.1095180378 0.03250417570518135
+ parallelization 0.1461015788 0.04336191081867245
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.079 seconds)
+ **Total running time of the script:** ( 1 minutes 0.601 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 1f5532ef9..a6ea72f83 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-64031d56d634a535c8e3832d9231855b688f0648
+89ce171b8697d223032f53b5e14c459332316da8
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index ac98a0353..c93abbba7 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] 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 3.814 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.512 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 0c247327b..ea0571b1a 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">"x"</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.zip17743ad1-f46e-4ab0-839d-28517721a0e3 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.zipc40ac1ba-5ca7-490f-8d71-9be239be4132 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 4d5ec4154..e9033f75c 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +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: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 55.9MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 49.5MB/s]
- 46%|####6 | 19.1M/41.5M [00:00<00:00, 46.5MB/s]
- 57%|#####6 | 23.6M/41.5M [00:00<00:00, 43.2MB/s]
- 67%|######6 | 27.7M/41.5M [00:00<00:00, 41.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.8MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 47.3MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 45.9MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 53.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 49.6MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 50.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.0MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 55.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 55.6MB/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 88293f115..ccd7c4da8 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,10 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
- 92%|#########1| 41.0M/44.7M [00:00<00:00, 201MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 203MB/s]
+ 25%|##4 | 11.0M/44.7M [00:00<00:00, 115MB/s]
+ 49%|####9 | 22.0M/44.7M [00:00<00:00, 105MB/s]
+ 72%|#######1 | 32.1M/44.7M [00:00<00:00, 86.6MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 101MB/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 9a68b9494..da6b0595c 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 1.582 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.541 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 ac75aae24..881f5aec7 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>05:03.669</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:12.775</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_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>01:03.814</p></td>
+<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>01:05.541</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:01.582</p></td>
+<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>01:03.512</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:39.641</p></td>
+<td><p>00:41.025</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>00:27.847</p></td>
+<td><p>00:28.992</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>00:26.077</p></td>
+<td><p>00:25.911</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.103</p></td>
+<td><p>00:25.038</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>00:21.335</p></td>
+<td><p>00:22.770</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.831</p></td>
+<td><p>00:19.901</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>00:15.976</p></td>
+<td><p>00:17.596</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>00:02.462</p></td>
+<td><p>00:02.489</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 d7c87efb4..a92c8945f 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)
- 15.7863 15.7302 16.1000 15.6958 0.1203
+ 17.2846 16.1849 22.1064 16.0653 2.2413
</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 56cbe37c8..04999928d 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 +436,15 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 9%|9 | 15.4M/170M [00:00<00:01, 162MB/s]
- 22%|##1 | 36.9M/170M [00:00<00:00, 199MB/s]
- 34%|###3 | 57.5M/170M [00:00<00:00, 207MB/s]
- 47%|####6 | 79.5M/170M [00:00<00:00, 216MB/s]
- 62%|######1 | 105M/170M [00:00<00:00, 233MB/s]
- 75%|#######4 | 127M/170M [00:00<00:00, 218MB/s]
- 88%|########8 | 150M/170M [00:00<00:00, 223MB/s]
-100%|##########| 170M/170M [00:00<00:00, 212MB/s]
+ 12%|#1 | 19.6M/170M [00:00<00:00, 206MB/s]
+ 23%|##3 | 39.3M/170M [00:00<00:00, 192MB/s]
+ 34%|###3 | 57.7M/170M [00:00<00:00, 183MB/s]
+ 47%|####7 | 80.2M/170M [00:00<00:00, 203MB/s]
+ 59%|#####8 | 99.7M/170M [00:00<00:00, 197MB/s]
+ 73%|#######3 | 124M/170M [00:00<00:00, 214MB/s]
+ 85%|########5 | 145M/170M [00:00<00:00, 209MB/s]
+ 98%|#########8| 167M/170M [00:00<00:00, 215MB/s]
+100%|##########| 170M/170M [00:00<00:00, 205MB/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').
@@ -538,7 +539,7 @@ 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 55.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.821 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 1f3e1021f..f07ff7ac8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,11 @@ 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: "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, 169MB/s]
+ 12%|#2 | 1.69M/13.6M [00:00<00:00, 17.4MB/s]
+ 40%|#### | 5.44M/13.6M [00:00<00:00, 29.9MB/s]
+ 61%|######1 | 8.30M/13.6M [00:00<00:00, 24.1MB/s]
+ 82%|########2 | 11.1M/13.6M [00:00<00:00, 25.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 27.0MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +573,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3492 90.0470 97.2694 89.9033 1.0359
+ 90.2042 90.1217 91.2816 89.9329 0.2415
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +612,7 @@ 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 8.675 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.561 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 e0f0eb680..617210543 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)
- 120.4961 120.4841 126.6318 118.7601 0.8529
+ 120.1075 120.1307 127.1741 118.1002 1.0104
</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 58.396 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.512 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 9ff390ee8..b348694a5 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 36.324 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.808 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 c1bed921d..6db4ae4f2 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +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<?, ?KB/s]
- 4%|4 | 5769/132723 [00:00<00:02, 57684.55KB/s]
- 11%|# | 14049/132723 [00:00<00:01, 72455.17KB/s]
- 17%|#6 | 22314/132723 [00:00<00:01, 77100.37KB/s]
- 23%|##3 | 30556/132723 [00:00<00:01, 79196.89KB/s]
- 29%|##9 | 38721/132723 [00:00<00:01, 80073.25KB/s]
- 35%|###5 | 46968/132723 [00:00<00:01, 80886.37KB/s]
- 42%|####1 | 55113/132723 [00:00<00:00, 81069.63KB/s]
- 48%|####7 | 63301/132723 [00:00<00:00, 81323.73KB/s]
- 54%|#####3 | 71480/132723 [00:00<00:00, 81466.22KB/s]
- 60%|###### | 79720/132723 [00:01<00:00, 81751.85KB/s]
- 66%|######6 | 88000/132723 [00:01<00:00, 82067.07KB/s]
- 73%|#######2 | 96261/132723 [00:01<00:00, 82228.66KB/s]
- 79%|#######8 | 104518/132723 [00:01<00:00, 82328.69KB/s]
- 85%|########4 | 112796/132723 [00:01<00:00, 82462.46KB/s]
- 91%|#########1| 121043/132723 [00:01<00:00, 55543.77KB/s]
- 97%|#########7| 129159/132723 [00:01<00:00, 61301.29KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 73497.80KB/s]
+ 5%|5 | 6683/132723 [00:00<00:01, 66822.26KB/s]
+ 11%|#1 | 15064/132723 [00:00<00:01, 76811.70KB/s]
+ 17%|#7 | 22746/132723 [00:00<00:01, 64884.27KB/s]
+ 23%|##3 | 31142/132723 [00:00<00:01, 71658.74KB/s]
+ 30%|##9 | 39558/132723 [00:00<00:01, 75865.41KB/s]
+ 36%|###6 | 48034/132723 [00:00<00:01, 78750.71KB/s]
+ 43%|####2 | 56525/132723 [00:00<00:00, 80699.25KB/s]
+ 49%|####8 | 64974/132723 [00:00<00:00, 81878.71KB/s]
+ 55%|#####5 | 73319/132723 [00:00<00:00, 82359.84KB/s]
+ 61%|######1 | 81621/132723 [00:01<00:00, 82558.35KB/s]
+ 68%|######7 | 90095/132723 [00:01<00:00, 83218.05KB/s]
+ 74%|#######4 | 98596/132723 [00:01<00:00, 83754.74KB/s]
+ 81%|######## | 107076/132723 [00:01<00:00, 84062.61KB/s]
+ 87%|########7 | 115493/132723 [00:01<00:00, 83975.73KB/s]
+ 93%|#########3| 123945/132723 [00:01<00:00, 84136.11KB/s]
+100%|#########9| 132504/132723 [00:01<00:00, 84570.11KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 80639.96KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +500,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.106 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 36.854 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 c1251c5c5..458d8975e 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:28.273</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:16.270</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:55.015</p></td>
+<td><p>02:57.821</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:35.106</p></td>
+<td><p>02:36.854</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>01:58.396</p></td>
+<td><p>01:53.512</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>01:36.324</p></td>
+<td><p>01:22.808</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>01:08.675</p></td>
+<td><p>01:10.561</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.453</p></td>
+<td><p>00:29.983</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.730</p></td>
+<td><p>00:22.776</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.569</p></td>
+<td><p>00:21.949</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index e451cd560..fdba6222e 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.zip208d4ed0-abb9-40e6-b534-4faa8be2f36e 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.zipf5ca2fa9-0548-475b-afce-1579086a2b8f 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 234985887..327c2078e 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>00:40.720</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:43.642</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>00:37.632</p></td>
+<td><p>00:40.321</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>00:02.170</p></td>
+<td><p>00:02.340</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>00:00.909</p></td>
+<td><p>00:00.972</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 d051a59d5..fe573ad48 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: 6768us [6768us] (46.60%; 46.60%)
-FoldScaleAxis: 7756us [6us] (53.40%; 53.40%)
- FoldConstant: 7749us [1584us] (53.36%; 99.92%)
- InferType: 6166us [6166us] (42.45%; 79.56%)
+InferType: 6972us [6972us] (46.65%; 46.65%)
+FoldScaleAxis: 7974us [6us] (53.35%; 53.35%)
+ FoldConstant: 7968us [1555us] (53.31%; 99.92%)
+ InferType: 6413us [6413us] (42.91%; 80.49%)
</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: 6231us [6231us] (44.59%; 44.59%)
-FoldScaleAxis: 7742us [5us] (55.41%; 55.41%)
- FoldConstant: 7738us [1568us] (55.37%; 99.94%)
- InferType: 6170us [6170us] (44.15%; 79.73%)
+InferType: 6403us [6403us] (44.81%; 44.81%)
+FoldScaleAxis: 7887us [5us] (55.19%; 55.19%)
+ FoldConstant: 7882us [1587us] (55.16%; 99.94%)
+ InferType: 6294us [6294us] (44.05%; 79.86%)
</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 71cda81b5..45657a6c0 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">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</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: 54.168631 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.731199 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 ff6bd1f1c..d092d6537 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">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.767923 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.180346 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 7961901d4..1b61d1e4a 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">"Baseline: </span><span class="si">%f</span><span class="s2">"</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: 0.018024
-Baseline: 3.435788
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018496
+Baseline: 3.381006
</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">"Opt1: </span><span class="si">%f</span><span class="s2">"</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: 0.296037
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.305973
</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">"Opt2: </span><span class="si">%f</span><span class="s2">"</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: 0.334691
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336033
</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">"Opt3: </span><span class="si">%f</span><span class="s2">"</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: 0.116833
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121890
</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">"Opt4: </span><span class="si">%f</span><span class="s2">"</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: 0.111166
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112389
</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">"Opt5: </span><span class="si">%f</span><span class="s2">"</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: 0.110955
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111781
</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">"Opt6: </span><span class="si">%f</span><span class="s2">"</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: 0.146793
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147590
</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 79c8a5c04..e54f13d2e 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.595</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.967</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.215</p></td>
+<td><p>00:32.402</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>00:01.298</p></td>
+<td><p>00:01.414</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>00:01.082</p></td>
+<td><p>00:01.151</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 132cc1218..cc98147b5 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>06:21.840</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:25.786</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>03:36.818</p></td>
+<td><p>03:36.847</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:22.393</p></td>
+<td><p>01:23.366</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.769</p></td>
+<td><p>00:47.689</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>00:18.522</p></td>
+<td><p>00:19.814</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>00:08.756</p></td>
+<td><p>00:09.102</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>00:08.581</p></td>
+<td><p>00:08.969</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 5cf17a876..a3297cc19 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
@@ -491,105 +491,392 @@ 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), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- for (ff.outer.inner.init: int32, 0, 2) {
- let cse_var_1: int32 = (ff.outer.inner.init*7)
- {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [196], [], scope="local", align=32)[cse_var_1] = 0f32
- conv2d_nchw_1[(cse_var_1 + 14)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 1)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 15)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 2)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 16)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 3)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 17)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 4)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 18)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 5)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 19)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 6)] = 0f32
- conv2d_nchw_1[(cse_var_1 + 20)] = 0f32
- }
- }
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 16)) < 8), dtype=bool) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 36) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4032) + (threadIdx.x_2*36)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[((((((blockIdx.x*294912) + (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*258048)) + (floordiv(threadIdx.x_2, 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)]
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*3136)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 686), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 735), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 833), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 931), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1078), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1127), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1274), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1519), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1617), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1715), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1813), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2009), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2058), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2107), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 1707)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2254), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2303), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2401), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2450), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2499), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2597), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2050)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2695), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2793), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2842), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2891), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 2989), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3038), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3185), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3234), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3283), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3381), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3430), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3479), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3577), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3626), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3675), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3773), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3822), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3871), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_1 + threadIdx.x_1) + rx.outer.outer) + 3079)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 4018), 63)*49)) + rx.outer.outer) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*32)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 1), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 2), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 3)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 4), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 5), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 6)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 7), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 8), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 9)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 27)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 10), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 11), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 12)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 36)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 13), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 14), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 15)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 45)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 16), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 17), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 18)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 54)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 19), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 20), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 21)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 63)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 22), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 23), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 24)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 72)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 25)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 25), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 26)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 26), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 27)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 81)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 28)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 28), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 29)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 29), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + rx.outer.outer)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 30)] = kernel[(((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv((floormod(threadIdx.x_2, 6)*32), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + rx.outer.outer) + 90)]
+ }
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 31)] = kernel[((((((blockIdx.x*18432) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*576)) + (floordiv(((floormod(threadIdx.x_2, 6)*32) + 31), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + rx.outer.outer)]
}
}
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 2) {
- let cse_var_16: int32 = (ff.outer.inner*7)
- let cse_var_15: int32 = (cse_var_16 + 6)
- let cse_var_14: int32 = (cse_var_16 + 5)
- let cse_var_13: int32 = (cse_var_16 + 4)
- let cse_var_12: int32 = (cse_var_16 + 3)
- let cse_var_11: int32 = (cse_var_16 + 20)
- let cse_var_10: int32 = (cse_var_16 + 2)
- let cse_var_9: int32 = (cse_var_16 + 19)
- let cse_var_8: int32 = (cse_var_16 + 18)
- let cse_var_7: int32 = (cse_var_16 + 17)
- let cse_var_6: int32 = (cse_var_16 + 16)
- let cse_var_5: int32 = (cse_var_16 + 15)
- let cse_var_4: int32 = (cse_var_16 + 14)
- let cse_var_3: int32 = (cse_var_16 + 1)
- {
- conv2d_nchw_1[cse_var_16] = (conv2d_nchw_1[cse_var_16] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_12] = (conv2d_nchw_1[cse_var_12] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_13] = (conv2d_nchw_1[cse_var_13] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_14] = (conv2d_nchw_1[cse_var_14] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- conv2d_nchw_1[cse_var_15] = (conv2d_nchw_1[cse_var_15] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((((((floordiv(threadIdx.x, 7)*144) + (ff.outer.inner*72)) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 2304)]))
- }
- }
- }
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.inner*24)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[cse_var_2]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 384)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 387)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 393)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 396)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 399)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 402)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 405)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 192)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*504) + threadIdx.x)]*kernel.shared_1[(cse_var_2 + 576)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 195)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_2 + 579)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 198)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_2 + 582)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 201)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_2 + 585)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 204)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_2 + 588)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 207)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_2 + 591)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 210)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_2 + 594)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 213)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_2 + 597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 385)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 388)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 391)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 394)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 397)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 400)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 403)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 406)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 193)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_2 + 577)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 196)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_2 + 580)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 199)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_2 + 583)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 202)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_2 + 586)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 205)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_2 + 589)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 208)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_2 + 592)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 211)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_2 + 595)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 214)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_2 + 598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 386)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 389)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 392)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 395)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 398)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 401)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 404)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 407)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 194)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_2 + 578)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 197)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_2 + 581)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 200)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_2 + 584)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 203)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_2 + 587)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 206)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_2 + 590)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 209)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_2 + 593)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 212)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_2 + 596)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 215)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_2 + 599)]))
}
}
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- let cse_var_17: int32 = ((i1.inner*7) + i3.inner)
- {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[cse_var_17] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[((((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner) + 1568)] = max((conv2d_nchw_1[(cse_var_17 + 14)] + bias[((((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 32)]), 0f32)
- }
- }
+ compute[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*4) + i1.inner)]), 0f32)
+ compute[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
}
}
}
@@ -626,7 +913,7 @@ 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: 0.420 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.414 ms
</pre></div>
</div>
</div>
@@ -657,34 +944,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=16)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=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=7)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=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=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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=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)
@@ -702,16 +989,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=36)
+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=32)
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=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -729,74 +1016,302 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
- for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
- conv2d_nchw[(ff_outer_inner_init * 7)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 14)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 1)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 15)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 2)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 16)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 3)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 17)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 4)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 18)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 5)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 19)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 6)] = 0.000000e+00f;
- conv2d_nchw[((ff_outer_inner_init * 7) + 20)] = 0.000000e+00f;
- }
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++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 * 392) + ((((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) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 4)) < 8) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 36; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4032) + (((int)threadIdx.x) * 36)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((int)blockIdx.x) * 294912) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 258048)) + ((((int)threadIdx.x) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)];
- }
+extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[768];
+ conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 14)] = (conv2d_nchw[((ff_outer_inner * 7) + 14)] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 15)] = (conv2d_nchw[((ff_outer_inner * 7) + 15)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 16)] = (conv2d_nchw[((ff_outer_inner * 7) + 16)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 17)] = (conv2d_nchw[((ff_outer_inner * 7) + 17)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 18)] = (conv2d_nchw[((ff_outer_inner * 7) + 18)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 19)] = (conv2d_nchw[((ff_outer_inner * 7) + 19)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + 20)] = (conv2d_nchw[((ff_outer_inner * 7) + 20)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((((((int)threadIdx.x) / 7) * 144) + (ff_outer_inner * 72)) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 2304)]));
- }
- }
- }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) * 32)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 3)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 9)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 6)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 18)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 8) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 9)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 27)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 10) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 11) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 12)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 36)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 13) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 14) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 15)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 45)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 16) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 17) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 18)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 54)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 19) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 20) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 21)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 63)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 22) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 23) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 24)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 72)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 25)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 25) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 26)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 26) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 27)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 81)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 28)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 28) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 29)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 29) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + rx_outer_outer)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 30)] = kernel[(((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 6) * 32) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + rx_outer_outer) + 90)];
+ }
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 31)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 6) * 32) + 31) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 384)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 387)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 393)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 396)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 399)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 402)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 405)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 192)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 504) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 24) + 576)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 195)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 63)] * kernel_shared[((rc_outer_inner * 24) + 579)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 198)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 126)] * kernel_shared[((rc_outer_inner * 24) + 582)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 201)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 189)] * kernel_shared[((rc_outer_inner * 24) + 585)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 204)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 252)] * kernel_shared[((rc_outer_inner * 24) + 588)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 207)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 315)] * kernel_shared[((rc_outer_inner * 24) + 591)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 210)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 378)] * kernel_shared[((rc_outer_inner * 24) + 594)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 213)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 441)] * kernel_shared[((rc_outer_inner * 24) + 597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 385)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 388)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 391)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 394)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 397)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 400)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 403)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 406)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 193)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 7)] * kernel_shared[((rc_outer_inner * 24) + 577)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 196)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 70)] * kernel_shared[((rc_outer_inner * 24) + 580)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 199)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 133)] * kernel_shared[((rc_outer_inner * 24) + 583)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 202)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 196)] * kernel_shared[((rc_outer_inner * 24) + 586)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 205)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 259)] * kernel_shared[((rc_outer_inner * 24) + 589)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 208)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 322)] * kernel_shared[((rc_outer_inner * 24) + 592)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 211)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 385)] * kernel_shared[((rc_outer_inner * 24) + 595)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 214)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 448)] * kernel_shared[((rc_outer_inner * 24) + 598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 386)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 389)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 392)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 395)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 398)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 401)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 404)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 407)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 194)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 14)] * kernel_shared[((rc_outer_inner * 24) + 578)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 197)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 77)] * kernel_shared[((rc_outer_inner * 24) + 581)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 200)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 140)] * kernel_shared[((rc_outer_inner * 24) + 584)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 203)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 203)] * kernel_shared[((rc_outer_inner * 24) + 587)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 206)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 266)] * kernel_shared[((rc_outer_inner * 24) + 590)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 209)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 329)] * kernel_shared[((rc_outer_inner * 24) + 593)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 212)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 392)] * kernel_shared[((rc_outer_inner * 24) + 596)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 215)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((int)threadIdx.x)) + 455)] * kernel_shared[((rc_outer_inner * 24) + 599)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner) + 1568)] = max((conv2d_nchw[(((i1_inner * 7) + i3_inner) + 14)] + bias[((((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 32)]), 0.000000e+00f);
- }
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
}
}
</pre></div>
@@ -831,9 +1346,10 @@ In the example below we resume the status and do more 5 trials.</p>
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
+.T
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 36.818 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 36.847 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 5ff398fdb..da19dddfd 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)
- 9.8302 9.8440 9.8669 9.7798 0.0369
+ 9.8576 9.8545 9.8738 9.8446 0.0121
</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 037fc5ec3..b392a2439 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)
- 756.2388 755.9175 757.5815 755.2175 0.9915
+ 759.7310 760.0380 760.9991 758.1561 1.1808
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.393 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.366 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 c56626153..a15a08a1a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,79 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), 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, 32) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*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 (i.outer.inner: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
- let cse_var_20: int32 = (elem_idx*16)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 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, 4) {
+ 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.outer.inner*128) + (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)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 8) {
- let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
- let cse_var_22: int32 = (((i0.inner*512) + cse_var_23) + i1.inner)
- compute[cse_var_22] = max((compute_5[((((i0.inner*16) + cse_var_23) + i1.inner) - (floordiv(i0.outer.i1.outer.fused, 2)*16))] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -735,7 +686,7 @@ 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: 3.502 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.454 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 7b710f285..6d02eac33 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>00:47.214</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.636</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:47.177</p></td>
+<td><p>00:46.604</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>00:00.023</p></td>
+<td><p>00:00.016</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>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<td><p>00:00.006</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>
-<td><p>00:00.005</p></td>
+<tr class="row-even"><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>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 8930aa4bb..d0659be0d 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
[('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: 128.67/128.67 result: MeasureResult(costs=(0.0017991688214285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8581395149230957, timestamp=1662680461.6663718) [('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: 0.00/128.67 result: Traceback (most recent call last):
+No: 9 GFLOPS: 199.78/199.78 result: MeasureResult(costs=(0.0011588081222222222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.055111885070801, timestamp=1662692627.9308276) [('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: 0.00/199.78 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
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
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: 261.01/261.01 result: MeasureResult(costs=(0.0008869559944751382,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.78175687789917, timestamp=1662680462.586266) [('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: 0.00/261.01 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.39/260.39 result: MeasureResult(costs=(0.0008890501049723757,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5887291431427002, timestamp=1662692628.8349879) [('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: 0.00/260.39 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
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
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: 0.00/261.01 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.39 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
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
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: 0.00/261.01 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.39 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
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.27/261.01 result: MeasureResult(costs=(0.04395225775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.882185459136963, timestamp=1662680467.2203062) [('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: 3.36/261.01 result: MeasureResult(costs=(0.06892849250000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.590003728866577, timestamp=1662680468.4531302) [('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: 0.00/261.01 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.27/260.39 result: MeasureResult(costs=(0.043887591749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8433284759521484, timestamp=1662692633.4025228) [('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: 3.34/260.39 result: MeasureResult(costs=(0.069245952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5606677532196045, timestamp=1662692634.639085) [('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: 0.00/260.39 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
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/261.01 result: Traceback (most recent call last):
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: 27.98/261.01 result: MeasureResult(costs=(0.008274430642857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.275554895401001, timestamp=1662680479.462969) [('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: 0.00/261.01 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.03/260.39 result: MeasureResult(costs=(0.0082589655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2980327606201172, timestamp=1662692645.7013125) [('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: 0.00/260.39 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
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
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: 0.00/261.01 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.39 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
@@ -2237,7 +2237,7 @@ and measure running time.</p>
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: 0.001219
+Time cost of this operator: 0.001270
</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 68c8aa953..3f05280e2 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 310.3 98.729 (1, 2, 10, 10, 3) 2 1 [310.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.96 (1, 6, 10, 10) 1 1 [3.017]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.311 (1, 1, 10, 10, 3) 1 1 [0.978]
-Total_time - 314.295 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.6 98.727 (1, 2, 10, 10, 3) 2 1 [308.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.965 (1, 6, 10, 10) 1 1 [3.017]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.308 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 312.58 - - - - -
</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 195.3 98.499 (1, 6, 10, 10, 1) 2 1 [195.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.027 1.022 (1, 6, 10, 10) 1 1 [2.027]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.949 0.478 (1, 3, 10, 10, 1) 1 1 [0.949]
-Total_time - 198.275 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 87.75 96.911 (1, 6, 10, 10, 1) 2 1 [87.75]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.83 2.021 (1, 6, 10, 10) 1 1 [1.83]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.068 (1, 1, 10, 10, 3) 1 1 [0.967]
+Total_time - 90.547 - - - - -
</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 ff40e8ec0..eb4cdc04e 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">"</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>'/tmp/tmpvv32kj0l/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp4qrceu5i/images/random'
</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">"off"</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/tmpvv32kj0l/images/target contains 8144 images
-/tmp/tmpvv32kj0l/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/tmp4qrceu5i/images/target contains 8144 images
+/tmp/tmp4qrceu5i/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 - 56s - loss: 0.2202 - accuracy: 0.9226 - val_loss: 0.1345 - val_accuracy: 0.9630
+328/328 - 56s - loss: 0.2353 - accuracy: 0.9230 - val_loss: 0.1403 - val_accuracy: 0.9588
Epoch 2/3
-328/328 - 52s - loss: 0.0926 - accuracy: 0.9648 - val_loss: 0.1574 - val_accuracy: 0.9513
+328/328 - 53s - loss: 0.1084 - accuracy: 0.9600 - val_loss: 0.1259 - val_accuracy: 0.9551
Epoch 3/3
-328/328 - 52s - loss: 0.0646 - accuracy: 0.9745 - val_loss: 0.1738 - val_accuracy: 0.9471
+328/328 - 52s - loss: 0.0667 - accuracy: 0.9751 - val_loss: 0.1312 - val_accuracy: 0.9562
-<keras.callbacks.History object at 0x7fe594f1ab90>
+<keras.callbacks.History object at 0x7f3691a79650>
</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 57.371 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 3.101 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 ac48525b4..c5f0c6426 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>05:51.117</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:58.885</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>04:57.371</p></td>
+<td><p>05:03.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.232</p></td>
+<td><p>00:43.902</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>00:08.208</p></td>
+<td><p>00:08.415</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>00:03.303</p></td>
+<td><p>00:03.466</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 ad5fb2651..a967d4662 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>00:42.813</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.390</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.554</p></td>
+<td><p>00:32.055</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.858</p></td>
+<td><p>00:09.849</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>00:01.394</p></td>
+<td><p>00:01.479</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 dfa447ec5..1d60a645e 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">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</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><function my_cuda_math_rule at 0x7fe520748200>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f36160534d0>
</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 8a01beb5d..21fda908d 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>00:04.302</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.274</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</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>00:01.961</p></td>
+<td><p>00:02.001</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>00:01.070</p></td>
+<td><p>00:00.987</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.549</p></td>
+<td><p>00:00.567</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.541</p></td>
+<td><p>00:00.539</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>
@@ -356,11 +356,11 @@
<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>00:00.028</p></td>
+<td><p>00:00.026</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 37a3d15ca..190d9d0f4 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), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1smf4fmp/input0.cc'\nsource_filename = \"/tmp/tmp1smf4fmp/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 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp6vbs7_sz/input0.cc'\nsource_filename = \"/tmp/tmp6vbs7_sz/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 = allo [...]
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/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 58c8c68fe..1eca2e3ea 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 22d0ec416..6b5a8c175 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/64031d56d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 e6345209e..e1e54b332 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/64031d56d/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 6045007a6..96050ca9b 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/64031d56d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 0ec7eee5c..18713048a 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/64031d56d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 a9761fb9f..9c9a6ff83 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/64031d56d/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</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">></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/64031d56d/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 1ea3c1ed3..0eec68e4d 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/64031d56d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</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">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 1a070f410..f83471cab 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/64031d56d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 fd3c54012..f1ac69b56 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/64031d56d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</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">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 26b865fe5..f70568216 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/64031d56d/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 a3c3f293e..35ddec231 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/64031d56d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 b34efccc9..c75984f74 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/64031d56d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 b608cb84c..201a1112a 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/64031d56d/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 e3e1c4d24..14cf71bec 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/64031d56d/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</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/64031d56d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 ed0527513..4a1845e4a 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/64031d56d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 ec4f4eec2..6ac18b1ce 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/64031d56d/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 12504a456..3bc1f5a94 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/64031d56d/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 6bf1daea3..c35f47afe 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/64031d56d/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 9aa7a3a29..3388111ca 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/64031d56d/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 14875ad50..af4035520 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/64031d56d/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 0d5059cd3..eebccd1d3 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/64031d56d/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 04d20d0bd..d01f3052d 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/64031d56d/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 1cc895695..c535f548f 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"> => </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/64031d56d/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 25d300505..778fc668d 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"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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/64031d56d/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 87562d5cb..cea608cb4 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"><</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">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/64031d56d/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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"> => </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/64031d56d/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/89ce171b8/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 49048d51f..e36935387 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 bb85452db..b7579ddad 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>00:21.166</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.436</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>00:21.160</p></td>
+<td><p>00:22.430</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 d4acca4fc..f1db0eef5 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 22.72s!
+resnet18_v1 inference graph built in 24.39s!
</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 7710a8352..01914e039 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>
"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 15.95s!
+yolov3-tiny inference graph built in 17.05s!
</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 4f248e477..280903332 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>01:31.523</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:34.844</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>00:48.459</p></td>
+<td><p>00:49.972</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>00:43.063</p></td>
+<td><p>00:44.872</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 5c312556d..c7c8644c5 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>00:03.342</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.299</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>00:02.924</p></td>
+<td><p>00:02.862</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>00:00.418</p></td>
+<td><p>00:00.437</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 eb3cc111d..ff53922f2 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>00:00.769</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.795</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>00:00.412</p></td>
+<td><p>00:00.421</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>00:00.357</p></td>
+<td><p>00:00.373</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 171eb1d2f..6bdd1c59a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.485 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.501 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 9564ea7d3..f58aa2a45 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.49/10.49 result: MeasureResult(costs=(0.0255935978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5469872951507568, timestamp=1662679248.870281) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.67/10.49 result: MeasureResult(costs=(0.1006344324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7545621395111084, timestamp=1662679250.6463335) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022692057600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5711381435394287, timestamp=1662679251.7169244) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.83 result: MeasureResult(costs=(0.1450325686,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4517223834991455, timestamp=1662679254.751538) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.69/11.83 result: MeasureResult(costs=(0.0727773378,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.30503249168396, timestamp=1662679256.1901448) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.72/11.83 result: MeasureResult(costs=(0.1556953856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.614009380340576, timestamp=1662679259.3955157) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.86/11.83 result: MeasureResult(costs=(0.3133077082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.1336164474487305, timestamp=1662679264.5750794) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.55/11.83 result: MeasureResult(costs=(0.025448856599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5543022155761719, timestamp=1662679265.1476328) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.65/11.83 result: MeasureResult(costs=(0.16238124660000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6933515071868896, timestamp=1662679267.960986) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.46/11.83 result: MeasureResult(costs=(0.10907074480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8524575233459473, timestamp=1662679269.8713691) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.025981204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.546959638595581, timestamp=1662691410.4482334) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.92/10.33 result: MeasureResult(costs=(0.0917891412,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.608830451965332, timestamp=1662691412.6035182) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.70/11.70 result: MeasureResult(costs=(0.0229481582,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5848186016082764, timestamp=1662691413.1747024) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.39/11.70 result: MeasureResult(costs=(0.19307266979999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.212522506713867, timestamp=1662691416.9687262) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.69/11.70 result: MeasureResult(costs=(0.0726816568,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2991490364074707, timestamp=1662691418.400518) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.78/11.70 result: MeasureResult(costs=(0.1505677104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5663702487945557, timestamp=1662691421.0122435) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.70 result: MeasureResult(costs=(0.30855539239999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.057368278503418, timestamp=1662691426.6476173) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.61/11.70 result: MeasureResult(costs=(0.0252996838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5468590259552002, timestamp=1662691427.21572) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.76/11.70 result: MeasureResult(costs=(0.152836349,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5458760261535645, timestamp=1662691429.8814402) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.65/11.70 result: MeasureResult(costs=(0.10143048480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7285714149475098, timestamp=1662691431.665993) [('tile_y', [-1, 4]), ('tile_x', [-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 f7290833b..5552b4fcb 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>{'mean': 495.29929663003713, 'median': 495.0232297499497, 'std': 0.5934874365415119}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 497.83906563998244, 'median': 498.26264240000455, 'std': 1.5189290095920485}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (4/20) | 6.40 s
-[Task 1/25] Current/Best: 6.16/ 17.60 GFLOPS | Progress: (8/20) | 9.45 s
-[Task 1/25] Current/Best: 11.52/ 22.72 GFLOPS | Progress: (12/20) | 11.94 s
-[Task 1/25] Current/Best: 16.54/ 22.72 GFLOPS | Progress: (16/20) | 13.63 s
-[Task 1/25] Current/Best: 11.63/ 23.85 GFLOPS | Progress: (20/20) | 15.38 s Done.
+[Task 1/25] Current/Best: 17.50/ 17.50 GFLOPS | Progress: (4/20) | 6.47 s
+[Task 1/25] Current/Best: 6.16/ 17.50 GFLOPS | Progress: (8/20) | 9.53 s
+[Task 1/25] Current/Best: 11.52/ 22.73 GFLOPS | Progress: (12/20) | 11.96 s
+[Task 1/25] Current/Best: 16.39/ 22.73 GFLOPS | Progress: (16/20) | 13.65 s
+[Task 1/25] Current/Best: 11.57/ 23.81 GFLOPS | Progress: (20/20) | 15.41 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.13/ 12.68 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 2/25] Current/Best: 14.05/ 18.79 GFLOPS | Progress: (8/20) | 5.06 s
-[Task 2/25] Current/Best: 21.15/ 21.15 GFLOPS | Progress: (12/20) | 6.39 s
-[Task 2/25] Current/Best: 12.75/ 21.15 GFLOPS | Progress: (16/20) | 7.65 s
-[Task 2/25] Current/Best: 19.33/ 21.15 GFLOPS | Progress: (20/20) | 9.27 s Done.
+[Task 2/25] Current/Best: 12.24/ 12.87 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 2/25] Current/Best: 14.03/ 17.42 GFLOPS | Progress: (8/20) | 5.20 s
+[Task 2/25] Current/Best: 20.91/ 20.91 GFLOPS | Progress: (12/20) | 6.55 s
+[Task 2/25] Current/Best: 12.10/ 20.91 GFLOPS | Progress: (16/20) | 7.85 s
+[Task 2/25] Current/Best: 19.65/ 20.91 GFLOPS | Progress: (20/20) | 9.46 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/ 10.84 GFLOPS | Progress: (4/20) | 5.88 s
-[Task 3/25] Current/Best: 15.35/ 16.84 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 3/25] Current/Best: 15.03/ 16.84 GFLOPS | Progress: (12/20) | 9.55 s
-[Task 3/25] Current/Best: 7.22/ 23.84 GFLOPS | Progress: (16/20) | 11.47 s
-[Task 3/25] Current/Best: 12.38/ 23.84 GFLOPS | Progress: (20/20) | 16.04 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.74 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 3/25] Current/Best: 15.25/ 16.76 GFLOPS | Progress: (8/20) | 7.85 s
+[Task 3/25] Current/Best: 14.84/ 16.76 GFLOPS | Progress: (12/20) | 9.58 s
+[Task 3/25] Current/Best: 7.13/ 23.65 GFLOPS | Progress: (16/20) | 11.56 s
+[Task 3/25] Current/Best: 12.30/ 23.65 GFLOPS | Progress: (20/20) | 16.15 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.52/ 20.34 GFLOPS | Progress: (4/20) | 2.43 s
-[Task 4/25] Current/Best: 6.72/ 20.34 GFLOPS | Progress: (8/20) | 7.12 s
-[Task 4/25] Current/Best: 22.57/ 22.57 GFLOPS | Progress: (12/20) | 12.08 s
-[Task 4/25] Current/Best: 17.00/ 22.57 GFLOPS | Progress: (16/20) | 14.45 s
-[Task 4/25] Current/Best: 13.48/ 22.57 GFLOPS | Progress: (20/20) | 16.41 s Done.
+[Task 4/25] Current/Best: 9.52/ 20.24 GFLOPS | Progress: (4/20) | 2.47 s
+[Task 4/25] Current/Best: 6.77/ 20.24 GFLOPS | Progress: (8/20) | 6.90 s
+[Task 4/25] Current/Best: 22.15/ 22.15 GFLOPS | Progress: (12/20) | 11.52 s
+[Task 4/25] Current/Best: 17.02/ 22.15 GFLOPS | Progress: (16/20) | 13.78 s
+[Task 4/25] Current/Best: 12.96/ 22.15 GFLOPS | Progress: (20/20) | 15.73 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.52/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
-[Task 5/25] Current/Best: 11.70/ 12.69 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 5/25] Current/Best: 11.68/ 17.99 GFLOPS | Progress: (12/20) | 7.90 s
-[Task 5/25] Current/Best: 11.54/ 22.50 GFLOPS | Progress: (16/20) | 9.31 s
-[Task 5/25] Current/Best: 12.04/ 22.50 GFLOPS | Progress: (20/20) | 11.25 s Done.
+[Task 5/25] Current/Best: 9.69/ 10.25 GFLOPS | Progress: (4/20) | 2.72 s
+[Task 5/25] Current/Best: 10.80/ 12.77 GFLOPS | Progress: (8/20) | 4.85 s
+[Task 5/25] Current/Best: 9.74/ 17.57 GFLOPS | Progress: (12/20) | 7.90 s
+[Task 5/25] Current/Best: 11.10/ 22.21 GFLOPS | Progress: (16/20) | 9.34 s
+[Task 5/25] Current/Best: 11.86/ 22.21 GFLOPS | Progress: (20/20) | 11.29 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.12/ 20.07 GFLOPS | Progress: (4/20) | 4.13 s
-[Task 6/25] Current/Best: 18.94/ 20.07 GFLOPS | Progress: (8/20) | 5.91 s
-[Task 6/25] Current/Best: 13.15/ 20.07 GFLOPS | Progress: (12/20) | 7.88 s
-[Task 6/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (16/20) | 10.14 s
-[Task 6/25] Current/Best: 3.72/ 20.09 GFLOPS | Progress: (20/20) | 12.68 s Done.
+[Task 6/25] Current/Best: 12.11/ 19.92 GFLOPS | Progress: (4/20) | 4.13 s
+[Task 6/25] Current/Best: 18.76/ 19.92 GFLOPS | Progress: (8/20) | 5.94 s
+[Task 6/25] Current/Best: 12.80/ 19.92 GFLOPS | Progress: (12/20) | 7.89 s
+[Task 6/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (16/20) | 10.22 s
+[Task 6/25] Current/Best: 3.76/ 19.96 GFLOPS | Progress: (20/20) | 12.74 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.08/ 12.98 GFLOPS | Progress: (4/20) | 3.58 s
-[Task 7/25] Current/Best: 20.30/ 21.03 GFLOPS | Progress: (8/20) | 5.10 s
-[Task 7/25] Current/Best: 16.13/ 21.03 GFLOPS | Progress: (12/20) | 7.01 s
-[Task 7/25] Current/Best: 12.18/ 21.03 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 7/25] Current/Best: 6.31/ 21.83 GFLOPS | Progress: (20/20) | 11.53 s Done.
+[Task 7/25] Current/Best: 11.08/ 12.75 GFLOPS | Progress: (4/20) | 3.67 s
+[Task 7/25] Current/Best: 20.11/ 21.10 GFLOPS | Progress: (8/20) | 5.21 s
+[Task 7/25] Current/Best: 16.00/ 21.10 GFLOPS | Progress: (12/20) | 7.14 s
+[Task 7/25] Current/Best: 12.14/ 21.10 GFLOPS | Progress: (16/20) | 9.21 s
+[Task 7/25] Current/Best: 6.23/ 21.54 GFLOPS | Progress: (20/20) | 11.73 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.69/ 13.76 GFLOPS | Progress: (4/20) | 2.99 s
-[Task 8/25] Current/Best: 9.20/ 13.76 GFLOPS | Progress: (8/20) | 8.13 s
-[Task 8/25] Current/Best: 12.72/ 13.76 GFLOPS | Progress: (12/20) | 14.62 s
-[Task 8/25] Current/Best: 18.98/ 18.98 GFLOPS | Progress: (16/20) | 16.73 s
-[Task 8/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (20/20) | 23.79 s Done.
+[Task 8/25] Current/Best: 10.05/ 13.78 GFLOPS | Progress: (4/20) | 3.03 s
+[Task 8/25] Current/Best: 9.88/ 13.78 GFLOPS | Progress: (8/20) | 7.88 s
+[Task 8/25] Current/Best: 13.02/ 13.78 GFLOPS | Progress: (12/20) | 14.22 s
+[Task 8/25] Current/Best: 19.11/ 19.11 GFLOPS | Progress: (16/20) | 16.32 s
+[Task 8/25] Current/Best: 18.91/ 19.11 GFLOPS | Progress: (20/20) | 22.95 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.38/ 15.66 GFLOPS | Progress: (4/20) | 11.99 s
-[Task 9/25] Current/Best: 23.42/ 23.42 GFLOPS | Progress: (8/20) | 13.79 s
-[Task 9/25] Current/Best: 8.23/ 23.42 GFLOPS | Progress: (12/20) | 16.29 s
-[Task 9/25] Current/Best: 17.98/ 23.42 GFLOPS | Progress: (16/20) | 19.02 s
-[Task 9/25] Current/Best: 9.18/ 23.42 GFLOPS | Progress: (20/20) | 27.38 s
+[Task 9/25] Current/Best: 14.17/ 15.56 GFLOPS | Progress: (4/20) | 12.06 s
+[Task 9/25] Current/Best: 23.19/ 23.19 GFLOPS | Progress: (8/20) | 13.98 s
+[Task 9/25] Current/Best: 8.25/ 23.19 GFLOPS | Progress: (12/20) | 16.43 s
+[Task 9/25] Current/Best: 17.92/ 23.19 GFLOPS | Progress: (16/20) | 19.16 s
+[Task 9/25] Current/Best: 9.02/ 23.19 GFLOPS | Progress: (20/20) | 27.20 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 10/25] Current/Best: 15.60/ 18.06 GFLOPS | Progress: (8/20) | 4.24 s
-[Task 10/25] Current/Best: 12.51/ 19.03 GFLOPS | Progress: (12/20) | 5.80 s
-[Task 10/25] Current/Best: 19.11/ 20.23 GFLOPS | Progress: (16/20) | 6.91 s
-[Task 10/25] Current/Best: 8.84/ 20.23 GFLOPS | Progress: (20/20) | 8.49 s Done.
+[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 10/25] Current/Best: 15.58/ 18.15 GFLOPS | Progress: (8/20) | 4.21 s
+[Task 10/25] Current/Best: 12.27/ 18.74 GFLOPS | Progress: (12/20) | 5.75 s
+[Task 10/25] Current/Best: 18.93/ 20.38 GFLOPS | Progress: (16/20) | 6.86 s
+[Task 10/25] Current/Best: 8.75/ 20.38 GFLOPS | Progress: (20/20) | 8.42 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.58/ 18.19 GFLOPS | Progress: (4/20) | 3.40 s
-[Task 11/25] Current/Best: 16.94/ 18.19 GFLOPS | Progress: (8/20) | 6.22 s
-[Task 11/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 11/25] Current/Best: 13.46/ 20.89 GFLOPS | Progress: (16/20) | 11.25 s
-[Task 11/25] Current/Best: 19.32/ 21.59 GFLOPS | Progress: (20/20) | 13.38 s Done.
+[Task 11/25] Current/Best: 12.28/ 18.21 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 11/25] Current/Best: 16.88/ 18.21 GFLOPS | Progress: (8/20) | 6.11 s
+[Task 11/25] Current/Best: 18.08/ 18.21 GFLOPS | Progress: (12/20) | 8.18 s
+[Task 11/25] Current/Best: 12.95/ 20.83 GFLOPS | Progress: (16/20) | 11.01 s
+[Task 11/25] Current/Best: 19.47/ 21.20 GFLOPS | Progress: (20/20) | 13.03 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.73/ 17.92 GFLOPS | Progress: (4/20) | 5.73 s
-[Task 12/25] Current/Best: 5.16/ 17.92 GFLOPS | Progress: (8/20) | 9.62 s
-[Task 12/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (12/20) | 11.64 s
-[Task 12/25] Current/Best: 15.23/ 18.94 GFLOPS | Progress: (16/20) | 14.59 s
-[Task 12/25] Current/Best: 15.15/ 18.94 GFLOPS | Progress: (20/20) | 16.50 s Done.
+[Task 12/25] Current/Best: 7.80/ 17.94 GFLOPS | Progress: (4/20) | 5.53 s
+[Task 12/25] Current/Best: 5.18/ 17.94 GFLOPS | Progress: (8/20) | 9.27 s
+[Task 12/25] Current/Best: 18.76/ 18.81 GFLOPS | Progress: (12/20) | 11.28 s
+[Task 12/25] Current/Best: 15.28/ 18.81 GFLOPS | Progress: (16/20) | 14.09 s
+[Task 12/25] Current/Best: 15.13/ 18.81 GFLOPS | Progress: (20/20) | 16.01 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.60/ 17.38 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 13/25] Current/Best: 15.81/ 20.92 GFLOPS | Progress: (8/20) | 6.40 s
-[Task 13/25] Current/Best: 19.68/ 22.04 GFLOPS | Progress: (12/20) | 9.52 s
-[Task 13/25] Current/Best: 12.28/ 22.04 GFLOPS | Progress: (16/20) | 12.99 s
-[Task 13/25] Current/Best: 18.73/ 22.04 GFLOPS | Progress: (20/20) | 15.38 s Done.
+[Task 13/25] Current/Best: 8.58/ 17.27 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 13/25] Current/Best: 15.54/ 20.94 GFLOPS | Progress: (8/20) | 6.23 s
+[Task 13/25] Current/Best: 19.78/ 22.03 GFLOPS | Progress: (12/20) | 9.14 s
+[Task 13/25] Current/Best: 12.31/ 22.03 GFLOPS | Progress: (16/20) | 12.54 s
+[Task 13/25] Current/Best: 18.73/ 22.03 GFLOPS | Progress: (20/20) | 14.78 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.80/ 13.80 GFLOPS | Progress: (4/20) | 3.47 s
-[Task 14/25] Current/Best: 6.12/ 13.80 GFLOPS | Progress: (8/20) | 5.69 s
-[Task 14/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (12/20) | 8.37 s
-[Task 14/25] Current/Best: 17.66/ 20.98 GFLOPS | Progress: (16/20) | 10.02 s Done.
+[Task 14/25] Current/Best: 13.67/ 13.67 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 14/25] Current/Best: 6.10/ 13.67 GFLOPS | Progress: (8/20) | 5.53 s
+[Task 14/25] Current/Best: 20.13/ 20.13 GFLOPS | Progress: (12/20) | 8.06 s
+[Task 14/25] Current/Best: 16.28/ 20.13 GFLOPS | Progress: (16/20) | 9.71 s Done.
-[Task 14/25] Current/Best: 16.97/ 20.98 GFLOPS | Progress: (20/20) | 11.86 s
+[Task 14/25] Current/Best: 17.12/ 20.13 GFLOPS | Progress: (20/20) | 11.48 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.20/ 17.62 GFLOPS | Progress: (4/20) | 2.77 s
-[Task 15/25] Current/Best: 14.24/ 18.02 GFLOPS | Progress: (8/20) | 4.07 s
-[Task 15/25] Current/Best: 10.39/ 22.42 GFLOPS | Progress: (12/20) | 6.30 s
-[Task 15/25] Current/Best: 20.42/ 22.42 GFLOPS | Progress: (16/20) | 9.69 s
-[Task 15/25] Current/Best: 9.70/ 22.42 GFLOPS | Progress: (20/20) | 10.71 s
+[Task 15/25] Current/Best: 16.06/ 17.64 GFLOPS | Progress: (4/20) | 2.82 s
+[Task 15/25] Current/Best: 14.47/ 18.04 GFLOPS | Progress: (8/20) | 4.16 s
+[Task 15/25] Current/Best: 10.40/ 22.33 GFLOPS | Progress: (12/20) | 6.24 s
+[Task 15/25] Current/Best: 20.40/ 22.33 GFLOPS | Progress: (16/20) | 9.23 s
+[Task 15/25] Current/Best: 9.67/ 22.33 GFLOPS | Progress: (20/20) | 10.21 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.23/ 20.23 GFLOPS | Progress: (4/20) | 3.03 s
-[Task 16/25] Current/Best: 3.04/ 20.23 GFLOPS | Progress: (8/20) | 4.64 s
-[Task 16/25] Current/Best: 19.52/ 20.23 GFLOPS | Progress: (12/20) | 5.87 s
-[Task 16/25] Current/Best: 17.46/ 20.23 GFLOPS | Progress: (16/20) | 7.23 s
-[Task 16/25] Current/Best: 9.98/ 21.99 GFLOPS | Progress: (20/20) | 9.40 s Done.
+[Task 16/25] Current/Best: 20.42/ 20.42 GFLOPS | Progress: (4/20) | 3.01 s
+[Task 16/25] Current/Best: 3.04/ 20.42 GFLOPS | Progress: (8/20) | 4.62 s
+[Task 16/25] Current/Best: 19.40/ 20.42 GFLOPS | Progress: (12/20) | 5.84 s
+[Task 16/25] Current/Best: 17.62/ 20.42 GFLOPS | Progress: (16/20) | 7.18 s
+[Task 16/25] Current/Best: 9.93/ 21.84 GFLOPS | Progress: (20/20) | 9.24 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.10/ 18.22 GFLOPS | Progress: (4/20) | 4.84 s
-[Task 17/25] Current/Best: 14.45/ 22.81 GFLOPS | Progress: (8/20) | 7.63 s
-[Task 17/25] Current/Best: 17.69/ 22.81 GFLOPS | Progress: (12/20) | 9.69 s
-[Task 17/25] Current/Best: 16.54/ 22.81 GFLOPS | Progress: (16/20) | 11.89 s
-[Task 17/25] Current/Best: 10.06/ 22.81 GFLOPS | Progress: (20/20) | 14.05 s Done.
+[Task 17/25] Current/Best: 14.16/ 16.31 GFLOPS | Progress: (4/20) | 4.78 s
+[Task 17/25] Current/Best: 14.41/ 23.38 GFLOPS | Progress: (8/20) | 7.64 s
+[Task 17/25] Current/Best: 18.12/ 23.38 GFLOPS | Progress: (12/20) | 9.68 s
+[Task 17/25] Current/Best: 16.53/ 23.38 GFLOPS | Progress: (16/20) | 11.82 s
+[Task 17/25] Current/Best: 10.05/ 23.38 GFLOPS | Progress: (20/20) | 13.95 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.31/ 17.96 GFLOPS | Progress: (4/20) | 3.84 s
-[Task 18/25] Current/Best: 10.55/ 19.61 GFLOPS | Progress: (8/20) | 7.49 s
-[Task 18/25] Current/Best: 19.53/ 19.61 GFLOPS | Progress: (12/20) | 9.43 s
-[Task 18/25] Current/Best: 10.03/ 19.61 GFLOPS | Progress: (16/20) | 13.30 s
-[Task 18/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (20/20) | 14.81 s Done.
+[Task 18/25] Current/Best: 11.38/ 17.81 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 18/25] Current/Best: 10.60/ 20.21 GFLOPS | Progress: (8/20) | 7.08 s
+[Task 18/25] Current/Best: 19.31/ 20.21 GFLOPS | Progress: (12/20) | 9.01 s
+[Task 18/25] Current/Best: 9.98/ 20.21 GFLOPS | Progress: (16/20) | 12.61 s
+[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (20/20) | 14.12 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.16/ 20.41 GFLOPS | Progress: (4/20) | 6.11 s
-[Task 19/25] Current/Best: 2.70/ 20.41 GFLOPS | Progress: (8/20) | 9.42 s
-[Task 19/25] Current/Best: 19.93/ 21.61 GFLOPS | Progress: (12/20) | 12.42 s
-[Task 19/25] Current/Best: 14.21/ 22.54 GFLOPS | Progress: (16/20) | 15.36 s
-[Task 19/25] Current/Best: 2.70/ 23.20 GFLOPS | Progress: (20/20) | 18.22 s Done.
+[Task 19/25] Current/Best: 7.02/ 20.39 GFLOPS | Progress: (4/20) | 6.02 s
+[Task 19/25] Current/Best: 2.69/ 20.39 GFLOPS | Progress: (8/20) | 9.26 s
+[Task 19/25] Current/Best: 20.05/ 21.82 GFLOPS | Progress: (12/20) | 12.00 s
+[Task 19/25] Current/Best: 14.16/ 22.10 GFLOPS | Progress: (16/20) | 14.87 s
+[Task 19/25] Current/Best: 2.70/ 23.10 GFLOPS | Progress: (20/20) | 17.69 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.66/ 14.87 GFLOPS | Progress: (4/20) | 3.40 s Done.
+[Task 20/25] Current/Best: 8.31/ 15.21 GFLOPS | Progress: (4/20) | 3.34 s Done.
Done.
-[Task 20/25] Current/Best: 10.05/ 14.87 GFLOPS | Progress: (8/20) | 6.79 s
-[Task 20/25] Current/Best: 2.32/ 16.72 GFLOPS | Progress: (12/20) | 10.74 s
-[Task 20/25] Current/Best: 11.94/ 16.72 GFLOPS | Progress: (16/20) | 14.49 s
-[Task 20/25] Current/Best: 12.25/ 22.14 GFLOPS | Progress: (20/20) | 16.61 s
+[Task 20/25] Current/Best: 10.19/ 15.21 GFLOPS | Progress: (8/20) | 6.63 s
+[Task 20/25] Current/Best: 2.32/ 16.68 GFLOPS | Progress: (12/20) | 10.55 s
+[Task 20/25] Current/Best: 12.38/ 16.68 GFLOPS | Progress: (16/20) | 14.33 s
+[Task 20/25] Current/Best: 12.65/ 21.90 GFLOPS | Progress: (20/20) | 16.42 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.42/ 17.72 GFLOPS | Progress: (4/20) | 3.31 s
-[Task 21/25] Current/Best: 14.65/ 17.72 GFLOPS | Progress: (8/20) | 4.94 s
-[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.08 s
-[Task 21/25] Current/Best: 16.79/ 17.72 GFLOPS | Progress: (16/20) | 10.61 s
-[Task 21/25] Current/Best: 4.47/ 17.72 GFLOPS | Progress: (20/20) | 17.89 s
+[Task 21/25] Current/Best: 6.42/ 17.73 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 21/25] Current/Best: 14.60/ 17.73 GFLOPS | Progress: (8/20) | 4.83 s
+[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 6.96 s
+[Task 21/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (16/20) | 10.40 s
+[Task 21/25] Current/Best: 4.47/ 18.06 GFLOPS | Progress: (20/20) | 17.57 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20) | 2.71 s
-[Task 22/25] Current/Best: 8.83/ 21.93 GFLOPS | Progress: (8/20) | 4.77 s
-[Task 22/25] Current/Best: 20.00/ 21.93 GFLOPS | Progress: (12/20) | 7.18 s
-[Task 22/25] Current/Best: 15.32/ 21.93 GFLOPS | Progress: (16/20) | 9.31 s
-[Task 22/25] Current/Best: 13.90/ 21.93 GFLOPS | Progress: (20/20) | 11.06 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 22/25] Current/Best: 8.75/ 21.84 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 22/25] Current/Best: 19.90/ 21.84 GFLOPS | Progress: (12/20) | 7.01 s
+[Task 22/25] Current/Best: 15.51/ 21.84 GFLOPS | Progress: (16/20) | 9.05 s
+[Task 22/25] Current/Best: 13.74/ 21.84 GFLOPS | Progress: (20/20) | 10.77 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.63/ 20.75 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 23/25] Current/Best: 14.39/ 20.75 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 23/25] Current/Best: 21.04/ 21.60 GFLOPS | Progress: (12/20) | 8.54 s
-[Task 23/25] Current/Best: 6.26/ 21.60 GFLOPS | Progress: (16/20) | 15.53 s
-[Task 23/25] Current/Best: 7.88/ 21.60 GFLOPS | Progress: (20/20) | 19.73 s Done.
+[Task 23/25] Current/Best: 17.69/ 20.79 GFLOPS | Progress: (4/20) | 3.26 s
+[Task 23/25] Current/Best: 15.27/ 20.79 GFLOPS | Progress: (8/20) | 6.61 s
+[Task 23/25] Current/Best: 20.98/ 21.61 GFLOPS | Progress: (12/20) | 8.42 s
+[Task 23/25] Current/Best: 6.40/ 21.61 GFLOPS | Progress: (16/20) | 15.40 s
+[Task 23/25] Current/Best: 7.72/ 21.61 GFLOPS | Progress: (20/20) | 19.60 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.85 s
-[Task 24/25] Current/Best: 3.66/ 8.47 GFLOPS | Progress: (8/20) | 23.11 s
-[Task 24/25] Current/Best: 4.19/ 8.47 GFLOPS | Progress: (12/20) | 33.83 s Done.
+[Task 24/25] Current/Best: 8.69/ 8.69 GFLOPS | Progress: (4/20) | 11.83 s
+[Task 24/25] Current/Best: 3.50/ 8.69 GFLOPS | Progress: (8/20) | 23.09 s
+[Task 24/25] Current/Best: 4.61/ 8.69 GFLOPS | Progress: (12/20) | 33.81 s Done.
-[Task 24/25] Current/Best: 6.78/ 8.89 GFLOPS | Progress: (16/20) | 39.49 s
-[Task 24/25] Current/Best: 3.35/ 8.89 GFLOPS | Progress: (20/20) | 45.54 s Done.
+[Task 24/25] Current/Best: 6.13/ 8.73 GFLOPS | Progress: (16/20) | 39.35 s
+[Task 24/25] Current/Best: 3.33/ 8.73 GFLOPS | Progress: (20/20) | 45.24 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/ 2.76 GFLOPS | Progress: (4/20) | 11.62 s
-[Task 25/25] Current/Best: 5.96/ 7.92 GFLOPS | Progress: (8/20) | 22.93 s
-[Task 25/25] Current/Best: 6.11/ 7.92 GFLOPS | Progress: (12/20) | 34.41 s
-[Task 25/25] Current/Best: 5.89/ 8.63 GFLOPS | Progress: (16/20) | 36.16 s
-[Task 25/25] Current/Best: 2.88/ 9.13 GFLOPS | Progress: (20/20) | 46.82 s
+[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.63 s
+[Task 25/25] Current/Best: 5.92/ 7.98 GFLOPS | Progress: (8/20) | 22.89 s
+[Task 25/25] Current/Best: 6.04/ 7.98 GFLOPS | Progress: (12/20) | 34.37 s
+[Task 25/25] Current/Best: 5.90/ 8.81 GFLOPS | Progress: (16/20) | 36.22 s
+[Task 25/25] Current/Best: 2.88/ 8.81 GFLOPS | Progress: (20/20) | 46.92 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">"unoptimized: </span><span class="si">%s</span><span class="s2">"</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: {'mean': 409.14941426999576, 'median': 409.1582320499583, 'std': 0.7372720689148065}
-unoptimized: {'mean': 495.29929663003713, 'median': 495.0232297499497, 'std': 0.5934874365415119}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.80024174003483, 'median': 410.7523118000245, 'std': 1.2238987442422715}
+unoptimized: {'mean': 497.83906563998244, 'median': 498.26264240000455, 'std': 1.5189290095920485}
</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 25.921 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 20.410 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 b0794782d..7b6fc1b91 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">"</span><span class="si">%g</span><span class="s2"> secs/op"</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>1.23e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.29e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index dba4f6ab2..f9d5e7db1 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, 0xe96b680)), stage(b, placeholder(b, 0x21e756d0)), 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, 0x23065af0)), stage(b, placeholder(b, 0x2842eff0)), 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 7d2a48a4c..81ffcd569 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>13:13.379</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:13.521</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,39 +336,39 @@
</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>10:25.921</p></td>
+<td><p>10:20.410</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.079</p></td>
+<td><p>01:00.601</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:49.733</p></td>
+<td><p>00:55.059</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:30.719</p></td>
+<td><p>00:31.151</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>00:24.539</p></td>
+<td><p>00:24.687</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.703</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.769</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.514</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.691</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>00:00.164</p></td>
+<td><p>00:00.144</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>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 5a1815b81..1fb6a066d 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">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000006
</pre></div>
</div>
@@ -594,7 +594,7 @@ compile and run this new schedule with the parallel operation applied:</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.
"target_host parameter is going to be deprecated. "
-parallel: 0.000008
+parallel: 0.000006
</pre></div>
</div>
</div>
@@ -635,7 +635,7 @@ factor to be the number of threads on your CPU.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vector: 0.000025
+vector: 0.000034
@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"),
@@ -668,10 +668,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.823169999028324e-06 1.0
- naive 5.811899999999999e-06 0.7429085652902679
-parallel 7.5448e-06 0.9644172376334786
- vector 2.4551e-05 3.1382419151123333
+ numpy 7.2782999995979485e-06 1.0
+ naive 5.8009e-06 0.7970130388030776
+parallel 6.0311e-06 0.8286413036468896
+ vector 3.40965e-05 4.684679114887197
</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: 0.017740
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017684
</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.
"target_host parameter is going to be deprecated. "
-none: 3.437629
+none: 3.369353
</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.
"target_host parameter is going to be deprecated. "
-blocking: 0.299352
+blocking: 0.306064
</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.
"target_host parameter is going to be deprecated. "
-vectorization: 0.335210
+vectorization: 0.344899
@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], []),
@@ -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.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.113478
+loop permutation: 0.116972
@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], []),
@@ -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.
"target_host parameter is going to be deprecated. "
-array packing: 0.107497
+array packing: 0.108005
@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], []),
@@ -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.
"target_host parameter is going to be deprecated. "
-block caching: 0.110857
+block caching: 0.109518
@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], []),
@@ -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.
"target_host parameter is going to be deprecated. "
-parallelization: 0.146027
+parallelization: 0.146102
@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], []),
@@ -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 3.4376288085 1.0
- blocking 0.2993515676 0.08708082933788923
- vectorization 0.3352102837 0.09751206496499781
-loop permutation 0.1134779515 0.03301053075288713
- array packing 0.1074966189 0.03127057192277425
- block caching 0.1108566097 0.03224798716658765
- parallelization 0.1460270042 0.04247899128577483
+ none 3.3693528731 1.0
+ blocking 0.3060636917 0.09083752970593538
+ vectorization 0.3448987818 0.10236350859940446
+loop permutation 0.1169717835 0.03471639448449315
+ array packing 0.10800539089999998 0.03205523284969222
+ block caching 0.1095180378 0.03250417570518135
+ parallelization 0.1461015788 0.04336191081867245
</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 1.079 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.601 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>