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 2022/12/05 19:50:26 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@2b110367d1e1df12a3e784b7cdcc1d769c97132c)
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 0bbc92b9fe deploying docs (apache/tvm@2b110367d1e1df12a3e784b7cdcc1d769c97132c)
0bbc92b9fe is described below
commit 0bbc92b9fe1e4671b935cd30851535e6d15f4034
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Dec 5 19:50:19 2022 +0000
deploying docs (apache/tvm@2b110367d1e1df12a3e784b7cdcc1d769c97132c)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 298784 -> 314727 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22856 -> 23008 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 12 +-
.../tune_conv2d_layer_cuda.rst.txt | 621 +++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 80 ++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 198 ++-----
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 38 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 10 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 43 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 12 +-
.../tune_conv2d_layer_cuda.html | 621 +++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 80 ++-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 198 ++-----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 268 ++++-----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 38 +-
130 files changed, 1633 insertions(+), 1762 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index fb3c2850a3..44d42e7073 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 86defffe09..979e8de9bd 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index fe199538a9..0141ec1e27 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.503 seconds)
+ **Total running time of the script:** ( 1 minutes 11.802 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 99e2109221..717a534f2f 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 947ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 916ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 0db4dfc1a8..8313ad46fc 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.zipc846ba90-e948-4683-8f07-de7816ac08de from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip86a9eb93-877a-40bb-90f7-7f4b06067c16 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 60c295becc..77fb85b276 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 49.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 49.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 48.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 56.0MB/s]
91%|######### | 37.6M/41.5M [00:00<00:00, 55.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 52.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 54.7MB/s]
28%|##7 | 11.5M/41.5M [00:00<00:00, 47.5MB/s]
39%|###8 | 16.1M/41.5M [00:00<00:01, 24.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 31.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 38.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 37.5MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index bd8bba6af1..e02601b8d4 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
19%|#9 | 8.53M/44.7M [00:00<00:00, 89.3MB/s]
38%|###8 | 17.1M/44.7M [00:00<00:00, 50.1MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 52.6MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 52.6MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 58.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 55.1MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.1M/44.7M [00:00<00:00, 126MB/s]
54%|#####4 | 24.2M/44.7M [00:00<00:00, 107MB/s]
77%|#######7 | 34.6M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 c04d9bfa9d..76bb392e97 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.885 seconds)
+ **Total running time of the script:** ( 1 minutes 11.770 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 57e91c4a5d..617af06cbe 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
=================
-**05:48.151** total execution time for **how_to_compile_models** files:
+**05:45.562** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.885 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.802 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.770 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.958 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.947 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.180 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.124 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.412 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.586 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.799 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.152 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.308 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.532 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.764 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.744 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.430 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.425 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index bcb2d49ed8..04b21494ee 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2756.9797 2756.6301 2770.5540 2752.3762 4.9003
+ 2755.3249 2754.3682 2760.1316 2752.3538 2.8188
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 485536a161..dbf46ae530 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7295 15.6921 15.9503 15.6139 0.1134
+ 16.2046 16.2437 16.8214 15.5189 0.4584
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 9fafddb98e..2619ec1bff 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 65.7MB/s]
8%|8 | 14.3M/170M [00:00<00:02, 59.7MB/s]
12%|#1 | 20.0M/170M [00:00<00:02, 54.0MB/s]
15%|#4 | 25.1M/170M [00:00<00:03, 42.8MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 43.3MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 48.0MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 56.6MB/s]
33%|###2 | 56.0M/170M [00:01<00:01, 59.9MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 60.7MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 56.3MB/s]
46%|####6 | 78.3M/170M [00:01<00:01, 53.6MB/s]
49%|####9 | 83.5M/170M [00:01<00:01, 53.5MB/s]
52%|#####2 | 88.7M/170M [00:01<00:01, 49.8MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 49.5MB/s]
61%|######1 | 104M/170M [00:02<00:01, 56.6MB/s]
66%|######5 | 112M/170M [00:02<00:01, 60.3MB/s]
71%|####### | 120M/170M [00:02<00:00, 65.8MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 60.8MB/s]
78%|#######8 | 133M/170M [00:02<00:00, 62.1MB/s]
82%|########1 | 139M/170M [00:02<00:00, 55.8MB/s]
85%|########4 | 144M/170M [00:02<00:00, 54.1MB/s]
89%|########9 | 152M/170M [00:02<00:00, 60.2MB/s]
94%|#########4| 160M/170M [00:02<00:00, 61.9MB/s]
98%|#########7| 166M/170M [00:03<00:00, 56.3MB/s]
100%|##########| 170M/170M [00:03<00:00, 56.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|8 | 14.3M/170M [00:00<00:01, 150MB/s]
17%|#6 | 28.6M/170M [00:00<00:01, 116MB/s]
24%|##3 | 40.1M/170M [00:00<00:01, 107MB/s]
30%|##9 | 50.6M/170M [00:00<00:01, 105MB/s]
36%|###5 | 60.7M/170M [00:00<00:01, 105MB/s]
42%|####1 | 70.8M/170M [00:00<00:01, 103MB/s]
47%|####7 | 80.6M/170M [00:00<00:00, 101MB/s]
53%|#####3 | 90.3M/170M [00:00<00:00, 101MB/s]
59%|#####8 | 100M/170M [00:00<00:00, 101MB/s]
65%|######4 | 110M/170M [00:01<00:00, 101MB/s]
70%|####### | 119M/170M [00:01<00:00, 91.1MB/s]
78%|#######7 | 132M/170M [00:01<00:00, 102MB/s]
84%|########3 | 142M/170M [00:01<00:00, 97.5MB/s]
90%|######### | 153M/170M [00:01<00:00, 103MB/s]
96%|#########6| 163M/170M [00:01<00:00, 102MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 14.308 seconds)
+ **Total running time of the script:** ( 3 minutes 12.207 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 121abe0340..ad65ae9523 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
52%|#####2 | 7.07M/13.6M [00:00<00:00, 74.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 48.4MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
47%|####6 | 6.30M/13.6M [00:00<00:00, 54.9MB/s]
85%|########5 | 11.5M/13.6M [00:00<00:00, 42.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 37.2MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2946 90.1412 93.7926 90.0108 0.4229
+ 90.3132 90.1718 94.5714 90.0174 0.5161
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.606 seconds)
+ **Total running time of the script:** ( 1 minutes 5.880 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 c64fa17d88..73762a1035 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.6050 121.5894 122.4635 120.9472 0.3133
+ 120.5405 120.4831 125.9646 119.5523 0.6634
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.482 seconds)
+ **Total running time of the script:** ( 2 minutes 31.074 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 647ec93206..1f726df661 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 41.256 seconds)
+ **Total running time of the script:** ( 1 minutes 36.946 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 b07f36bd84..3fe8b7fbd3 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6278/132723 [00:00<00:02, 62775.12KB/s]
11%|#1 | 14985/132723 [00:00<00:01, 77062.03KB/s]
17%|#7 | 22692/132723 [00:00<00:01, 56035.37KB/s]
24%|##3 | 31394/132723 [00:00<00:01, 66001.64KB/s]
29%|##9 | 38533/132723 [00:00<00:01, 52888.53KB/s]
36%|###5 | 47279/132723 [00:00<00:01, 61876.31KB/s]
41%|#### | 54165/132723 [00:00<00:01, 60514.67KB/s]
47%|####7 | 62990/132723 [00:00<00:01, 67962.21KB/s]
53%|#####2 | 70239/132723 [00:01<00:01, 61044.67KB/s]
60%|#####9 | 79027/132723 [00:01<00:00, 67991.23KB/s]
65%|######4 | 86241/132723 [00:01<00:00, 55315.35KB/s]
71%|#######1 | 94815/132723 [00:01<00:00, 62490.53KB/s]
78%|#######7 | 103420/132723 [00:01<00:00, 68427.61KB/s]
84%|########4 | 112135/132723 [00:01<00:00, 73381.91KB/s]
90%|######### | 119939/132723 [00:01<00:00, 66747.80KB/s]
97%|########
#6| 128665/132723 [00:01<00:00, 72069.62KB/s]
100%|##########| 132723/132723 [00:02<00:00, 65614.51KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4195/132723 [00:00<00:03, 41945.44KB/s]
9%|8 | 11921/132723 [00:00<00:01, 62712.01KB/s]
15%|#5 | 20533/132723 [00:00<00:01, 73397.11KB/s]
22%|##1 | 29078/132723 [00:00<00:01, 78151.49KB/s]
28%|##8 | 37773/132723 [00:00<00:01, 81322.21KB/s]
35%|###5 | 46467/132723 [00:00<00:01, 83230.28KB/s]
41%|####1 | 54791/132723 [00:00<00:00, 79984.50KB/s]
48%|####7 | 63434/132723 [00:00<00:00, 81977.96KB/s]
54%|#####3 | 71654/132723 [00:00<00:00, 76070.52KB/s]
61%|###### | 80343/132723 [00:01<00:00, 79195.03KB/s]
67%|######6 | 88346/132723 [00:01<00:00, 67189.24KB/s]
73%|#######3 | 97029/132723 [00:01<00:00, 72311.44KB/s]
79%|#######8 | 104584/132723 [00:01<00:00, 62968.01KB/s]
85%|########5 | 113317/132723 [00:01<00:00, 69061.66KB/s]
91%|######### | 120630/132723 [00:01<00:00, 48572.11KB/s]
97%|########
#7| 129090/132723 [00:01<00:00, 56017.31KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67301.84KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 5.888 seconds)
+ **Total running time of the script:** ( 3 minutes 5.268 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 503a8de33a..61b5daf131 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:00.389** total execution time for **how_to_deploy_models** files:
+**13:51.128** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:14.308 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:12.207 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:05.888 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:05.268 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:33.482 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:31.074 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:41.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.946 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.606 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.880 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.858 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.836 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.527 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.159 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.427 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.641 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.111 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 d78f8dc543..9e110bf8c2 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip3282c536-3eb6-4a23-956e-6b4cea09f0f6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip55ad295b-352b-481d-9b31-d841311bae48 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 de66c66d37..843d9b1860 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
=================
-**00:47.856** total execution time for **how_to_extend_tvm** files:
+**00:47.465** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.395 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.043 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.428 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.394 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.025 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.021 | 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 |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 83755e5f47..1d174e2598 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: 7179us [7179us] (46.33%; 46.33%)
- FoldScaleAxis: 8315us [7us] (53.67%; 53.67%)
- FoldConstant: 8308us [1703us] (53.62%; 99.92%)
- InferType: 6606us [6606us] (42.63%; 79.51%)
+ InferType: 7036us [7036us] (46.21%; 46.21%)
+ FoldScaleAxis: 8192us [6us] (53.79%; 53.79%)
+ FoldConstant: 8186us [1668us] (53.75%; 99.92%)
+ InferType: 6518us [6518us] (42.80%; 79.63%)
@@ -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: 6650us [6650us] (44.86%; 44.86%)
- FoldScaleAxis: 8174us [5us] (55.14%; 55.14%)
- FoldConstant: 8170us [1691us] (55.11%; 99.94%)
- InferType: 6479us [6479us] (43.70%; 79.30%)
+ InferType: 6559us [6559us] (44.89%; 44.89%)
+ FoldScaleAxis: 8054us [5us] (55.11%; 55.11%)
+ FoldConstant: 8049us [1645us] (55.08%; 99.94%)
+ InferType: 6404us [6404us] (43.83%; 79.57%)
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 500b28563b..609432d4ee 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: 34.128063 ms
+ Convolution: 42.333793 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 4a6d9ac40b..15fe6a0567 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.357945 ms
+ conv2d with tensor core: 13.383095 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 ba161945c2..f8904ea354 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: 0.018523
- Baseline: 3.227987
+ Numpy running time: 0.018589
+ Baseline: 3.243079
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.293666
+ Opt1: 0.292523
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.338604
+ Opt2: 0.333028
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116201
+ Opt3: 0.116131
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109497
+ Opt4: 0.109405
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111549
+ Opt5: 0.111996
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146519
+ Opt6: 0.150647
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 b542f99363..76f66f70f6 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
=================
-**00:34.268** total execution time for **how_to_optimize_operators** files:
+**00:34.729** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.668 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.871 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.520 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.659 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.080 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.199 | 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 7d94979eee..2c43d3eb10 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:05.700** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:57.761** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:39.146 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:33.110 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.992 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.763 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.405 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.978 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.378 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.942 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.993 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.112 | 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 1ba504b435..f6ff0b075d 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
@@ -240,175 +240,197 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 16) {
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*24)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod((threadIdx.x_1*24), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod((threadIdx.x_ [...]
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) - 8)], 0f32 [...]
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) - 6)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 21)*49 [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + (f [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + (f [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 2), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 504)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 384)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 505)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 385)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 506)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 386)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 6), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1008)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 776)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1009)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 777)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1010)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 778)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 8), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 9), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1512)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1168)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1513)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1169)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1514)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1170)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 11), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 21)* [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[(((((cse_var_2 + ( [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 12), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 14), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 15), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 17), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 18), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 20), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 21), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 23), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 100), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 69)]))
- }
+ for (rc.outer.inner: int32, 0, 32) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*63) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute_3[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias_3[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
}
}
}
@@ -463,7 +485,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.299 ms
+ Execution time of this operator: 0.277 ms
@@ -512,32 +534,32 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=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=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ 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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -560,12 +582,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+ 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=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
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=196)
+ 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=56)
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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -585,148 +607,143 @@ 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__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && (((((int)threadIdx.x) * 24) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 2) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 6) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 8) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 9) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 11) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 12) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 14) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 15) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 17) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 18) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 20) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 21) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 23) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 104) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 116) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 140) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 152) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 164) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 176) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 100) {
- kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 3)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 6)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 9)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 12)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 15)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 18)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 21)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 24)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 27)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 30)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 33)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 36)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 39)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 42)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 45)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 48)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 51)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 54)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 57)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 60)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 63)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 66)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 69)]));
- }
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 3)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 21) * 49)) + (((((((int)threadIdx.x) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 21) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 21) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 2 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 504)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 505)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 385)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 506)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 386)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 2 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1008)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 776)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1009)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 777)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1010)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 778)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 2 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1512)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1513)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1169)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1514)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1170)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 21) * 49)) + (((((((int)threadIdx.x) [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 2 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 2 [...]
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 216)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 63) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
}
}
@@ -788,7 +805,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 39.146 seconds)
+ **Total running time of the script:** ( 5 minutes 33.110 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 f4dee159ce..bc6412fcf0 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8901 7.8855 7.9012 7.8836 0.0079
+ 7.8684 7.8647 7.8782 7.8624 0.0070
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.531 seconds)
+ **Total running time of the script:** ( 1 minutes 1.405 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index d83898b1cf..d393097d6c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 752.0942 752.2007 753.3887 750.6932 1.1030
+ 751.3310 750.5699 754.0186 749.4045 1.9591
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.992 seconds)
+ **Total running time of the script:** ( 1 minutes 31.763 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 f2fa200e11..87eefb311f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,29 +386,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [1024], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256))
+ let cse_var_17: int32 = (cse_var_19 + 9)
+ let cse_var_16: int32 = (cse_var_19 + 8)
+ let cse_var_15: int32 = (cse_var_19 + 7)
+ let cse_var_14: int32 = (cse_var_19 + 6)
+ let cse_var_13: int32 = (cse_var_19 + 5)
+ let cse_var_12: int32 = (cse_var_19 + 4)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 2)
+ let cse_var_9: int32 = (cse_var_19 + 15)
+ let cse_var_8: int32 = (cse_var_19 + 14)
+ let cse_var_7: int32 = (cse_var_19 + 13)
+ let cse_var_6: int32 = (cse_var_19 + 12)
+ let cse_var_5: int32 = (cse_var_19 + 11)
+ let cse_var_4: int32 = (cse_var_19 + 10)
+ let cse_var_3: int32 = (cse_var_19 + 1)
+ {
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 64) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -464,7 +512,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.527 ms
+ Execution time of this operator: 1.719 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 159a704303..eea1597f14 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:23.639** total execution time for **how_to_tune_with_autotvm** files:
+**00:29.010** 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``) | 00:23.603 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:28.976 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 7ff316be1e..bc4155fe3e 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
@@ -387,8 +387,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2609914
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7643089
+ No: 2 GFLOPS: 2.95/2.95 result: MeasureResult(costs=(0.07855564875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4236485958099365, timestamp=1670264421.0360904) [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5237095
+ No: 3 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -510,8 +511,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10324054
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3162019
+ No: 4 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -633,8 +634,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2646176
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6028914
+ No: 5 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -756,8 +757,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8666779
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4248507
+ No: 6 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -879,8 +880,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3044117
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4484268
+ No: 7 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1002,8 +1003,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9837561
- No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9250124
+ No: 8 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1125,8 +1126,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2037688
- No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10120135
+ No: 9 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1248,8 +1249,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7348723
- No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1054530
+ No: 10 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1371,8 +1372,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2259094
- No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10449984
+ No: 11 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1494,8 +1495,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5183001
- No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10303218
+ No: 12 GFLOPS: 12.31/12.31 result: MeasureResult(costs=(0.01881265,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7861850261688232, timestamp=1670264425.4484458) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1264888
+ No: 13 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1617,8 +1619,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6640650
- No: 12 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6454795
+ No: 14 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1740,8 +1742,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5756847
- No: 13 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9287958
+ No: 15 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1863,8 +1865,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6145789
- No: 14 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10176749
+ No: 16 GFLOPS: 44.41/44.41 result: MeasureResult(costs=(0.00521224325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7851200103759766, timestamp=1670264427.5048223) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4879305
+ No: 17 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1986,10 +1989,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9921774
- No: 15 GFLOPS: 112.94/112.94 result: MeasureResult(costs=(0.002049716857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.603456735610962, timestamp=1670243486.0512342) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9115316
- No: 16 GFLOPS: 60.10/112.94 result: MeasureResult(costs=(0.0038519826923076924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4401683807373047, timestamp=1670243486.6821911) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2944210
- No: 17 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5104018
+ No: 18 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2111,8 +2112,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3180903
- No: 18 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6658574
+ No: 19 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2234,8 +2235,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9024384
- No: 19 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3213109
+ No: 20 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2357,130 +2358,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2281132
- No: 20 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8483145
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3320564
@@ -2535,9 +2413,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9115316
+ [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4879305
Finish loading 20 records
- Time cost of this operator: 0.001138
+ Time cost of this operator: 0.005502
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 3f9b80f347..bcb62f34ab 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 311.9 98.702 (1, 2, 10, 10, 3) 2 1 [311.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.118 0.987 (1, 6, 10, 10) 1 1 [3.118]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.311 (1, 1, 10, 10, 3) 1 1 [0.983]
- Total_time - 316.001 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.7 98.731 (1, 2, 10, 10, 3) 2 1 [311.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 0.962 (1, 6, 10, 10) 1 1 [3.036]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 315.705 - - - - -
@@ -397,10 +397,10 @@ 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 100.9 97.33 (1, 6, 10, 10, 1) 2 1 [100.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.798 1.734 (1, 6, 10, 10) 1 1 [1.798]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.936 (1, 1, 10, 10, 3) 1 1 [0.97]
- Total_time - 103.668 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.486 (1, 6, 10, 10, 1) 2 1 [102.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.802 1.711 (1, 6, 10, 10) 1 1 [1.802]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.846 0.803 (1, 3, 10, 10, 1) 1 1 [0.846]
+ Total_time - 105.348 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 1ec21f05d1..461693c7d1 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 82.5MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 128MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.069 seconds)
+ **Total running time of the script:** ( 1 minutes 2.670 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index f549cb933b..93170d318f 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/tmpoycl8ht0/images/random'
+ '/tmp/tmpaxdwl7ka/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpoycl8ht0/images/target contains 8144 images
- /tmp/tmpoycl8ht0/images/random contains 5000 images
+ /tmp/tmpaxdwl7ka/images/target contains 8144 images
+ /tmp/tmpaxdwl7ka/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2297 - accuracy: 0.9197 - val_loss: 0.2806 - val_accuracy: 0.9026 - 47s/epoch - 143ms/step
+ 328/328 - 46s - loss: 0.2294 - accuracy: 0.9219 - val_loss: 0.1288 - val_accuracy: 0.9634 - 46s/epoch - 141ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1028 - accuracy: 0.9608 - val_loss: 0.0841 - val_accuracy: 0.9698 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0955 - accuracy: 0.9634 - val_loss: 0.1393 - val_accuracy: 0.9585 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0750 - accuracy: 0.9713 - val_loss: 0.0956 - val_accuracy: 0.9683 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0727 - accuracy: 0.9735 - val_loss: 0.1438 - val_accuracy: 0.9494 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f9d34f6d9d0>
+ <keras.callbacks.History object at 0x7fc024b07b50>
@@ -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 35.306 seconds)
+ **Total running time of the script:** ( 4 minutes 45.040 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 f495065df3..00326404ef 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:40.038** total execution time for **how_to_work_with_microtvm** files:
+**06:49.346** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:45.040 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:03.069 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.670 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.025 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.906 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.782 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.827 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 0f3f8282cc..729e9098e7 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.237** total execution time for **how_to_work_with_relay** files:
+**00:44.801** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.811 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.299 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.266 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.715 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.717 | 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 a812ee9d17..b6b7fb4e3d 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 0x7f9d2f4fe7a0>
+ <function my_cuda_math_rule at 0x7fbfca7cc710>
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 0f82554624..45faf31ef7 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:07.312** total execution time for **how_to_work_with_schedules** files:
+**00:05.147** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.503 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.159 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.232 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.607 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.552 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.589 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 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 407937849b..9cf2189e6f 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjc0x3aj0/input0.cc'\nsource_filename = \"/tmp/tmpjc0x3aj0/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/tmpsqdsmili/input0.cc'\nsource_filename = \"/tmp/tmpsqdsmili/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 a2d39a110f..b30e85dd82 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
=================
-**00:26.609** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.221** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.602 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.214 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 6bdf26d1d4..f657291ba8 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 28.98s!
+ resnet18_v1 inference graph built in 28.55s!
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 baa1ac2cb3..23543372e8 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 19.60s!
+ yolov3-tiny inference graph built in 19.35s!
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 9a971949d3..a2db757ca4 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
=================
-**01:40.353** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.083** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.507 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.587 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.846 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.495 | 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 c838efc9d6..6e96569a61 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.203** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.275** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.739 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.773 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.464 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.502 | 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 7a6bd26f44..0e157a8d85 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
=================
-**00:00.820** total execution time for **topic_vta_tutorials** files:
+**00:00.887** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.440 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.471 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.380 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.416 | 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 261c91b35a..6c20c6de28 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 98.105 ms
+ Execution time of this operator: 98.507 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.241 seconds)
+ **Total running time of the script:** ( 1 minutes 19.892 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index a537b21c96..56be5633a8 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 1.54/1.54 result: MeasureResult(costs=(0.17421450440000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9419920444488525, timestamp=1670242029.2260752) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 2 GFLOPS: 0.50/1.54 result: MeasureResult(costs=(0.5390976992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.774592876434326, timestamp=1670242038.762536) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 3 GFLOPS: 3.68/3.68 result: MeasureResult(costs=(0.07290719279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.316204309463501, timestamp=1670242040.8460305) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
- No: 4 GFLOPS: 2.13/3.68 result: MeasureResult(costs=(0.12614115320000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.139291763305664, timestamp=1670242043.0274477) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 5 GFLOPS: 1.30/3.68 result: MeasureResult(costs=(0.207265825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.44674015045166, timestamp=1670242046.7015278) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
- No: 6 GFLOPS: 12.93/12.93 result: MeasureResult(costs=(0.020757763399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.581312894821167, timestamp=1670242047.2026014) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
- No: 7 GFLOPS: 1.85/12.93 result: MeasureResult(costs=(0.1451806354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.462167263031006, timestamp=1670242050.435471) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 8 GFLOPS: 2.12/12.93 result: MeasureResult(costs=(0.1268626322,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.222801685333252, timestamp=1670242052.6698747) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 9 GFLOPS: 4.18/12.93 result: MeasureResult(costs=(0.0641592044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1838116645812988, timestamp=1670242053.9685485) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
- No: 10 GFLOPS: 0.51/12.93 result: MeasureResult(costs=(0.5291263476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.605321168899536, timestamp=1670242062.5988066) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+ No: 1 GFLOPS: 2.23/2.23 result: MeasureResult(costs=(0.12029255000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0748164653778076, timestamp=1670263001.7466872) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 2 GFLOPS: 11.62/11.62 result: MeasureResult(costs=(0.0231057826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6172356605529785, timestamp=1670263002.3245099) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 3 GFLOPS: 7.16/11.62 result: MeasureResult(costs=(0.037492918400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.730154275894165, timestamp=1670263003.8298085) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 4 GFLOPS: 13.06/13.06 result: MeasureResult(costs=(0.0205578244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.491940975189209, timestamp=1670263004.3282335) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+ No: 5 GFLOPS: 1.21/13.06 result: MeasureResult(costs=(0.2222937174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.688504695892334, timestamp=1670263008.3134856) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 6 GFLOPS: 3.32/13.06 result: MeasureResult(costs=(0.08076983979999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4589121341705322, timestamp=1670263010.5136514) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+ No: 7 GFLOPS: 3.64/13.06 result: MeasureResult(costs=(0.073786626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.343045949935913, timestamp=1670263012.6057835) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 8 GFLOPS: 8.69/13.06 result: MeasureResult(costs=(0.0308980176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8301124572753906, timestamp=1670263013.3047175) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+ No: 9 GFLOPS: 9.91/13.06 result: MeasureResult(costs=(0.0270800922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5659821033477783, timestamp=1670263013.9851444) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 10 GFLOPS: 13.06/13.06 result: MeasureResult(costs=(0.020546659000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.45844483375549316, timestamp=1670263014.4817972) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 0a42558fe0..b188a30999 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 516.4432707599997, 'median': 516.3726706499972, 'std': 1.4022422790593192}
+ {'mean': 513.3368666399474, 'median': 513.5566341999947, 'std': 1.7051907359419172}
@@ -554,29 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.45/ 14.45 GFLOPS | Progress: (4/20) | 8.60 s
[Task 1/25] Current/Best: 8.62/ 23.26 GFLOPS | Progress: (8/20) | 12.58 s
[Task 1/25] Current/Best: 9.37/ 23.26 GFLOPS | Progress: (12/20) | 16.05 s
[Task 1/25] Current/Best: 7.91/ 23.26 GFLOPS | Progress: (16/20) | 19.22 s
[Task 1/25] Current/Best: 18.08/ 23.26 GFLOPS | Progress: (20/20) | 20.93 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.06/ 17.23 GFLOPS | Progress: (4/20) | 2.65 s
[Task 2/25] Current/Best: 5.73/ 19.13 GFLOPS | Progress: (8/20) | 3.74 s
[Task 2/25] Current/Best: 18.31/ 19.13 GFLOPS | Progress: (12/20) | 5.07 s
[Task 2/25] Current/Best: 9.96/ 19.13 GFLOPS | Progress: (16/20) | 6.62 s
[Task 2/25] Current/Best: 4.55/ 21.95 GFLOPS | Progress: (20/20) | 7.97 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.69/ 18.12 GFLOPS | Progress: (4/20) | 4.01 s
[Task 3/25] Current/Best: 9.25/ 18.12 GFLOPS | Progress: (8/20) | 7.04 s
[Task 3/25] Current/Best: 6.80/ 23.61 GFLOPS | Progress: (12/20) | 9.78 s
[Task 3/25] Current/Best: 14.56/ 23.61 GFLOPS | Progress: (16/20) | 11.83 s
[Task 3/25] Current/Best: 19.23/ 23.61 GFLOPS | Progress: (20/20) | 13.76 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.70/ 19.58 GFLOPS | Progress: (4/20) | 4.19 s
[Task 4/25] Current/Best: 13.79/ 19.58 GFLOPS | Progress: (8/20) | 8.70 s
[Task 4/25] Current/Best: 15.85/ 19.58 GFLOPS | Progress: (12/20) | 11.85 s
[Task 4/25] Current/Best: 8.44/ 19.58 GFLOPS | Progress: (16/20) | 14.62 s
[Task 4/25] Current/Best: 14.85/ 19.58 GFLOPS | Progress: (20/20) | 18.94 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.17/ 13.76 GFLOPS | Progress: (4/20) | 3.51 s
[Task 5/25] Current/Best: 14.60/ 16.14 GFLOPS | Progress: (8/20) | 5.56 s
[Task 5/25] Current/Best: 16.72/ 16.72 GFLOPS | Progress: (12/20) | 7.19 s
[Task 5/25] Current/Best: 11.17/ 16.72 GFLOPS | Progress: (16/20) | 9.13 s
[Task 5/25] Current/Best: 14.26/ 16.81 GFLOPS | Progress: (20/20) | 10.91 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.09/ 14.64 GFLOPS | Progress: (4/20) | 4.09 s
[Task 6/25] Current/Best: 13.34/ 14.64 GFLOPS | Progress: (8/20) | 6.75 s
[Task 6/25] Current/Best: 14.81/ 14.81 GFLOPS | Progress: (12/20) | 10.53 s
[Task 6/25] Current/Best: 14.01/ 18.25 GFLOPS | Progress: (16/20) | 12.71 s
[Task 6/25] Current/Best: 10.03/ 18.25 GFLOPS | Progress: (20/20) | 16.18 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.83/ 16.83 GFLOPS | Progress: (4/20) | 4.08 s
[Task 7/25] Current/Best: 11.72/ 16.83 GFLOPS | Progress: (8/20) | 6.02 s
[Task 7/25] Current/Best: 6.16/ 16.83 GFLOPS | Progress: (12/20) | 8.47 s
[Task 7/25] Current/Best: 7.19/ 16.83 GFLOPS | Progress: (16/20) | 11.99 s
[Task 7/25] Current/Best: 6.81/ 16.83 GFLOPS | Progress: (20/20) | 14.36 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.12/ 15.12 GFLOPS | Progress: (4/20) | 4.88 s
[Task 8/25] Current/Best: 18.32/ 18.51 GFLOPS | Progress: (8/20) | 6.96 s
[Task 8/25] Current/Best: 5.65/ 18.51 GFLOPS | Progress: (12/20) | 8.96 s
[Task 8/25] Current/Best: 13.40/ 18.51 GFLOPS | Progress: (16/20) | 12.20 s
[Task 8/25] Current/Best: 4.62/ 18.51 GFLOPS | Progress: (20/20) | 16.99 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.42/ 20.93 GFLOPS | Progress: (4/20) | 2.89 s
[Task 9/25] Current/Best: 5.77/ 20.93 GFLOPS | Progress: (8/20) | 12.31 s
[Task 9/25] Current/Best: 13.54/ 20.93 GFLOPS | Progress: (12/20) | 15.45 s
[Task 9/25] Current/Best: 20.74/ 20.93 GFLOPS | Progress: (16/20) | 23.97 s
[Task 9/25] Current/Best: 9.94/ 20.93 GFLOPS | Progress: (20/20) | 26.98 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.85/ 17.63 GFLOPS | Progress: (4/20) | 2.96 s
[Task 10/25] Current/Best: 5.74/ 17.63 GFLOPS | Progress: (8/20) | 5.42 s
[Task 10/25] Current/Best: 10.85/ 17.63 GFLOPS | Progress: (12/20) | 8.11 s
[Task 10/25] Current/Best: 8.07/ 18.11 GFLOPS | Progress: (16/20) | 9.72 s
[Task 10/25] Current/Best: 14.31/ 18.11 GFLOPS | Progress: (20/20) | 11.66 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.42/ 19.29 GFLOPS | Progress: (4/20) | 3.64 s
[Task 11/25] Current/Best: 11.68/ 19.29 GFLOPS | Progress: (8/20) | 6.20 s
[Task 11/25] Current/Best: 11.71/ 19.29 GFLOPS | Progress: (12/20) | 8.65 s
[Task 11/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (16/20) | 11.39 s
[Task 11/25] Current/Best: 6.03/ 21.85 GFLOPS | Progress: (20/20) | 13.65 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.63/ 19.93 GFLOPS | Progress: (4/20) | 5.63 s
[Task 12/25] Current/Best: 14.06/ 19.93 GFLOPS | Progress: (8/20) | 11.97 s
[Task 12/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (12/20) | 19.17 s
[Task 12/25] Current/Best: 17.95/ 22.13 GFLOPS | Progress: (16/20) | 21.57 s
[Task 12/25] Current/Best: 13.33/ 22.13 GFLOPS | Progress: (20/20) | 24.66 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.53/ 20.67 GFLOPS | Progress: (4/20) | 5.23 s
[Task 13/25] Current/Best: 18.60/ 20.67 GFLOPS | Progress: (8/20) | 7.62 s
[Task 13/25] Current/Best: 7.09/ 20.67 GFLOPS | Progress: (12/20) | 10.83 s
[Task 13/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (16/20) | 13.50 s
[Task 13/25] Current/Best: 6.43/ 22.13 GFLOPS | Progress: (20/20) | 17.41 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 3.40/ 12.90 GFLOPS | Progress: (4/20) | 4.22 s
[Task 14/25] Current/Best: 12.66/ 15.98 GFLOPS | Progress: (8/20) | 7.88 s
[Task 14/25] Current/Best: 4.22/ 15.98 GFLOPS | Progress: (12/20) | 12.01 s
[Task 14/25] Current/Best: 13.68/ 15.99 GFLOPS | Progress: (16/20) | 13.62 s
[Task 14/25] Current/Best: 11.17/ 15.99 GFLOPS | Progress: (20/20) | 17.84 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 18.33/ 19.54 GFLOPS | Progress: (4/20) | 3.00 s
[Task 15/25] Current/Best: 12.44/ 19.54 GFLOPS | Progress: (8/20) | 4.92 s Done.
-
[Task 15/25] Current/Best: 13.66/ 19.80 GFLOPS | Progress: (12/20) | 8.10 s
[Task 15/25] Current/Best: 3.19/ 19.80 GFLOPS | Progress: (16/20) | 12.08 s
[Task 15/25] Current/Best: 15.63/ 19.80 GFLOPS | Progress: (20/20) | 14.04 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.26/ 18.69 GFLOPS | Progress: (4/20) | 3.37 s
[Task 16/25] Current/Best: 7.55/ 18.69 GFLOPS | Progress: (8/20) | 6.55 s
[Task 16/25] Current/Best: 7.50/ 18.69 GFLOPS | Progress: (12/20) | 9.76 s
[Task 16/25] Current/Best: 12.36/ 18.69 GFLOPS | Progress: (16/20) | 12.06 s
[Task 16/25] Current/Best: 10.32/ 19.14 GFLOPS | Progress: (20/20) | 14.00 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (4/20) | 5.27 s
[Task 17/25] Current/Best: 18.99/ 21.38 GFLOPS | Progress: (8/20) | 7.81 s
[Task 17/25] Current/Best: 8.15/ 21.38 GFLOPS | Progress: (12/20) | 10.56 s
[Task 17/25] Current/Best: 6.82/ 21.38 GFLOPS | Progress: (16/20) | 13.91 s
[Task 17/25] Current/Best: 12.24/ 21.38 GFLOPS | Progress: (20/20) | 16.13 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.49/ 16.02 GFLOPS | Progress: (4/20) | 3.42 s
[Task 18/25] Current/Best: 10.02/ 17.60 GFLOPS | Progress: (8/20) | 6.25 s
[Task 18/25] Current/Best: 15.05/ 17.60 GFLOPS | Progress: (12/20) | 8.46 s
[Task 18/25] Current/Best: 5.20/ 17.60 GFLOPS | Progress: (16/20) | 13.46 s
[Task 18/25] Current/Best: 14.23/ 19.42 GFLOPS | Progress: (20/20) | 15.22 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.83/ 20.17 GFLOPS | Progress: (4/20) | 4.44 s
[Task 19/25] Current/Best: 12.91/ 20.17 GFLOPS | Progress: (8/20) | 9.67 s
[Task 19/25] Current/Best: 17.88/ 20.75 GFLOPS | Progress: (12/20) | 12.45 s
[Task 19/25] Current/Best: 17.86/ 22.34 GFLOPS | Progress: (16/20) | 15.67 s
[Task 19/25] Current/Best: 5.35/ 22.34 GFLOPS | Progress: (20/20) | 20.53 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 6.19/ 6.73 GFLOPS | Progress: (4/20) | 4.65 s
[Task 20/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 9.67 s
[Task 20/25] Current/Best: 4.90/ 18.80 GFLOPS | Progress: (12/20) | 13.55 s
[Task 20/25] Current/Best: 10.45/ 18.80 GFLOPS | Progress: (16/20) | 15.79 s
[Task 20/25] Current/Best: 12.72/ 18.80 GFLOPS | Progress: (20/20) | 18.41 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 11.49/ 17.34 GFLOPS | Progress: (4/20) | 2.90 s Done.
-
[Task 21/25] Current/Best: 8.23/ 17.34 GFLOPS | Progress: (8/20) | 4.87 s
[Task 21/25] Current/Best: 2.31/ 17.95 GFLOPS | Progress: (12/20) | 7.19 s
[Task 21/25] Current/Best: 18.75/ 18.75 GFLOPS | Progress: (16/20) | 8.78 s
[Task 21/25] Current/Best: 16.85/ 18.75 GFLOPS | Progress: (20/20) | 11.09 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (4/20) | 5.73 s
[Task 22/25] Current/Best: 16.59/ 20.43 GFLOPS | Progress: (8/20) | 7.00 s
[Task 22/25] Current/Best: 3.08/ 20.43 GFLOPS | Progress: (12/20) | 8.68 s
[Task 22/25] Current/Best: 14.64/ 20.43 GFLOPS | Progress: (16/20) | 11.89 s
[Task 22/25] Current/Best: 18.34/ 20.43 GFLOPS | Progress: (20/20) | 13.21 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.07/ 20.15 GFLOPS | Progress: (4/20) | 5.96 s
[Task 23/25] Current/Best: 18.09/ 20.15 GFLOPS | Progress: (8/20) | 8.59 s
[Task 23/25] Current/Best: 5.21/ 20.15 GFLOPS | Progress: (12/20) | 11.22 s
[Task 23/25] Current/Best: 8.24/ 22.79 GFLOPS | Progress: (16/20) | 15.09 s
[Task 23/25] Current/Best: 17.73/ 22.79 GFLOPS | Progress: (20/20) | 17.48 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.98/ 9.50 GFLOPS | Progress: (4/20) | 5.37 s
[Task 24/25] Current/Best: 1.69/ 9.50 GFLOPS | Progress: (8/20) | 16.09 s
[Task 24/25] Current/Best: 1.83/ 9.50 GFLOPS | Progress: (12/20) | 27.59 s
[Task 24/25] Current/Best: 1.69/ 9.50 GFLOPS | Progress: (16/20) | 39.10 s
[Task 24/25] Current/Best: 3.64/ 9.59 GFLOPS | Progress: (20/20) | 44.87 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.55/ 8.36 GFLOPS | Progress: (4/20) | 3.03 s
[Task 25/25] Current/Best: 7.16/ 8.36 GFLOPS | Progress: (8/20) | 4.14 s
[Task 25/25] Current/Best: 6.17/ 8.61 GFLOPS | Progress: (12/20) | 14.86 s
[Task 25/25] Current/Best: 6.37/ 8.90 GFLOPS | Progress: (16/20) | 23.74 s
[Task 25/25] Current/Best: 3.12/ 9.01 GFLOPS | Progress: (20/20) | 28.67 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 21.50/ 21.50 GFLOPS | Progress: (4/20) | 7.24 s
[Task 1/25] Current/Best: 16.87/ 21.50 GFLOPS | Progress: (8/20) | 11.30 s
[Task 1/25] Current/Best: 18.97/ 21.50 GFLOPS | Progress: (12/20) | 16.20 s
[Task 1/25] Current/Best: 8.86/ 21.50 GFLOPS | Progress: (16/20) | 19.51 s
[Task 1/25] Current/Best: 12.40/ 22.71 GFLOPS | Progress: (20/20) | 21.60 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 16.73/ 18.35 GFLOPS | Progress: (4/20) | 2.84 s
[Task 2/25] Current/Best: 14.25/ 18.35 GFLOPS | Progress: (8/20) | 4.28 s
[Task 2/25] Current/Best: 10.98/ 18.35 GFLOPS | Progress: (12/20) | 6.14 s
[Task 2/25] Current/Best: 16.08/ 19.88 GFLOPS | Progress: (16/20) | 7.19 s
[Task 2/25] Current/Best: 15.23/ 19.88 GFLOPS | Progress: (20/20) | 8.65 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 18.54/ 20.06 GFLOPS | Progress: (4/20) | 3.31 s
[Task 3/25] Current/Best: 9.03/ 20.06 GFLOPS | Progress: (8/20) | 5.76 s
[Task 3/25] Current/Best: 17.19/ 20.06 GFLOPS | Progress: (12/20) | 8.10 s
[Task 3/25] Current/Best: 11.12/ 20.06 GFLOPS | Progress: (16/20) | 10.01 s
[Task 3/25] Current/Best: 12.89/ 24.07 GFLOPS | Progress: (20/20) | 12.81 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.36/ 12.36 GFLOPS | Progress: (4/20) | 12.44 s
[Task 4/25] Current/Best: 15.65/ 16.41 GFLOPS | Progress: (8/20) | 14.56 s
[Task 4/25] Current/Best: 16.08/ 16.41 GFLOPS | Progress: (12/20) | 19.63 s
[Task 4/25] Current/Best: 12.39/ 17.16 GFLOPS | Progress: (16/20) | 21.55 s
[Task 4/25] Current/Best: 20.41/ 20.41 GFLOPS | Progress: (20/20) | 26.37 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.81/ 14.50 GFLOPS | Progress: (4/20) | 3.83 s
[Task 5/25] Current/Best: 20.95/ 22.61 GFLOPS | Progress: (8/20) | 4.98 s
[Task 5/25] Current/Best: 18.19/ 22.61 GFLOPS | Progress: (12/20) | 6.94 s
[Task 5/25] Current/Best: 17.70/ 22.61 GFLOPS | Progress: (16/20) | 8.22 s
[Task 5/25] Current/Best: 8.80/ 22.61 GFLOPS | Progress: (20/20) | 10.21 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 5.60/ 13.63 GFLOPS | Progress: (4/20) | 4.49 s
[Task 6/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (8/20) | 6.31 s
[Task 6/25] Current/Best: 8.61/ 18.21 GFLOPS | Progress: (12/20) | 8.87 s
[Task 6/25] Current/Best: 10.71/ 18.21 GFLOPS | Progress: (16/20) | 11.15 s
[Task 6/25] Current/Best: 12.72/ 18.21 GFLOPS | Progress: (20/20) | 14.73 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.55/ 22.76 GFLOPS | Progress: (4/20) | 3.48 s
[Task 7/25] Current/Best: 19.83/ 22.76 GFLOPS | Progress: (8/20) | 6.28 s
[Task 7/25] Current/Best: 4.84/ 22.76 GFLOPS | Progress: (12/20) | 9.27 s
[Task 7/25] Current/Best: 3.08/ 22.76 GFLOPS | Progress: (16/20) | 12.09 s
[Task 7/25] Current/Best: 11.25/ 22.76 GFLOPS | Progress: (20/20) | 15.57 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.14/ 10.35 GFLOPS | Progress: (4/20) | 9.86 s
[Task 8/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (8/20) | 18.30 s
[Task 8/25] Current/Best: 7.49/ 12.13 GFLOPS | Progress: (12/20) | 25.05 s
[Task 8/25] Current/Best: 9.13/ 14.32 GFLOPS | Progress: (16/20) | 31.43 s
[Task 8/25] Current/Best: 11.41/ 14.32 GFLOPS | Progress: (20/20) | 33.99 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 20.04/ 20.04 GFLOPS | Progress: (4/20) | 2.97 s
[Task 9/25] Current/Best: 8.76/ 20.04 GFLOPS | Progress: (8/20) | 10.77 s
[Task 9/25] Current/Best: 6.16/ 20.04 GFLOPS | Progress: (12/20) | 16.41 s
[Task 9/25] Current/Best: 12.44/ 20.24 GFLOPS | Progress: (16/20) | 19.32 s
[Task 9/25] Current/Best: 3.20/ 20.24 GFLOPS | Progress: (20/20) | 20.84 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 7.88/ 17.82 GFLOPS | Progress: (4/20) | 3.29 s
[Task 10/25] Current/Best: 7.89/ 17.82 GFLOPS | Progress: (8/20) | 4.90 s
[Task 10/25] Current/Best: 4.07/ 17.82 GFLOPS | Progress: (12/20) | 6.75 s
[Task 10/25] Current/Best: 18.23/ 18.60 GFLOPS | Progress: (16/20) | 8.09 s
[Task 10/25] Current/Best: 7.62/ 20.13 GFLOPS | Progress: (20/20) | 9.35 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (4/20) | 3.89 s
[Task 11/25] Current/Best: 12.24/ 22.05 GFLOPS | Progress: (8/20) | 6.43 s
[Task 11/25] Current/Best: 18.43/ 22.05 GFLOPS | Progress: (12/20) | 8.45 s
[Task 11/25] Current/Best: 22.10/ 22.10 GFLOPS | Progress: (16/20) | 10.40 s
[Task 11/25] Current/Best: 10.78/ 22.10 GFLOPS | Progress: (20/20) | 12.69 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.88/ 14.63 GFLOPS | Progress: (4/20) | 5.73 s
[Task 12/25] Current/Best: 15.60/ 15.60 GFLOPS | Progress: (8/20) | 7.81 s
[Task 12/25] Current/Best: 7.99/ 18.72 GFLOPS | Progress: (12/20) | 9.85 s
[Task 12/25] Current/Best: 14.84/ 19.19 GFLOPS | Progress: (16/20) | 11.92 s
[Task 12/25] Current/Best: 2.55/ 19.19 GFLOPS | Progress: (20/20) | 14.75 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 14.03/ 16.41 GFLOPS | Progress: (4/20) | 4.86 s
[Task 13/25] Current/Best: 6.46/ 17.60 GFLOPS | Progress: (8/20) | 7.68 s
[Task 13/25] Current/Best: 16.81/ 21.15 GFLOPS | Progress: (12/20) | 9.33 s
[Task 13/25] Current/Best: 23.24/ 23.24 GFLOPS | Progress: (16/20) | 11.24 s
[Task 13/25] Current/Best: 12.26/ 23.24 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.69/ 14.06 GFLOPS | Progress: (4/20) | 5.22 s
[Task 14/25] Current/Best: 9.73/ 18.45 GFLOPS | Progress: (8/20) | 7.55 s
[Task 14/25] Current/Best: 15.82/ 18.45 GFLOPS | Progress: (12/20) | 9.59 s
[Task 14/25] Current/Best: 5.50/ 18.45 GFLOPS | Progress: (16/20) | 12.48 s
[Task 14/25] Current/Best: 12.54/ 18.45 GFLOPS | Progress: (20/20) | 18.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 23.23/ 23.23 GFLOPS | Progress: (4/20) | 5.06 s
[Task 15/25] Current/Best: 12.14/ 23.23 GFLOPS | Progress: (8/20) | 6.56 s
[Task 15/25] Current/Best: 10.26/ 23.23 GFLOPS | Progress: (12/20) | 13.06 s Done.
+
[Task 15/25] Current/Best: 6.48/ 23.23 GFLOPS | Progress: (16/20) | 14.50 s
[Task 15/25] Current/Best: 4.87/ 23.23 GFLOPS | Progress: (20/20) | 16.00 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.24/ 15.22 GFLOPS | Progress: (4/20) | 3.59 s
[Task 16/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (8/20) | 7.10 s
[Task 16/25] Current/Best: 17.16/ 18.20 GFLOPS | Progress: (12/20) | 10.02 s
[Task 16/25] Current/Best: 16.10/ 18.20 GFLOPS | Progress: (16/20) | 11.36 s
[Task 16/25] Current/Best: 15.92/ 18.20 GFLOPS | Progress: (20/20) | 12.68 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.22/ 23.08 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 17.63/ 23.08 GFLOPS | Progress: (8/20) | 6.86 s
[Task 17/25] Current/Best: 12.39/ 23.08 GFLOPS | Progress: (12/20) | 10.04 s
[Task 17/25] Current/Best: 11.65/ 23.11 GFLOPS | Progress: (16/20) | 12.17 s
[Task 17/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 14.70 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 14.41/ 14.41 GFLOPS | Progress: (4/20) | 3.73 s
[Task 18/25] Current/Best: 15.57/ 23.12 GFLOPS | Progress: (8/20) | 7.36 s
[Task 18/25] Current/Best: 17.55/ 23.12 GFLOPS | Progress: (12/20) | 10.76 s
[Task 18/25] Current/Best: 14.93/ 23.12 GFLOPS | Progress: (16/20) | 12.30 s
[Task 18/25] Current/Best: 21.27/ 23.12 GFLOPS | Progress: (20/20) | 13.82 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.57/ 23.65 GFLOPS | Progress: (4/20) | 3.76 s
[Task 19/25] Current/Best: 22.27/ 23.65 GFLOPS | Progress: (8/20) | 6.94 s
[Task 19/25] Current/Best: 21.89/ 23.65 GFLOPS | Progress: (12/20) | 8.66 s
[Task 19/25] Current/Best: 1.55/ 23.65 GFLOPS | Progress: (16/20) | 13.20 s
[Task 19/25] Current/Best: 19.10/ 23.65 GFLOPS | Progress: (20/20) | 15.20 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 15.96/ 15.96 GFLOPS | Progress: (4/20) | 3.47 s
[Task 20/25] Current/Best: 9.92/ 18.24 GFLOPS | Progress: (8/20) | 6.06 s
[Task 20/25] Current/Best: 14.04/ 18.24 GFLOPS | Progress: (12/20) | 8.11 s
[Task 20/25] Current/Best: 10.39/ 18.24 GFLOPS | Progress: (16/20) | 10.03 s
[Task 20/25] Current/Best: 13.90/ 18.24 GFLOPS | Progress: (20/20) | 12.59 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 13.98/ 16.98 GFLOPS | Progress: (4/20) | 3.83 s
[Task 21/25] Current/Best: 18.78/ 18.78 GFLOPS | Progress: (8/20) | 5.25 s
[Task 21/25] Current/Best: 10.39/ 18.78 GFLOPS | Progress: (12/20) | 7.57 s
[Task 21/25] Current/Best: 13.33/ 18.78 GFLOPS | Progress: (16/20) | 8.95 s
[Task 21/25] Current/Best: 12.02/ 21.03 GFLOPS | Progress: (20/20) |
10.98 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.12/ 9.96 GFLOPS | Progress: (4/20) | 4.84 s Done.
+ Done.
+
[Task 22/25] Current/Best: 10.29/ 16.33 GFLOPS | Progress: (8/20) | 6.68 s
[Task 22/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (12/20) | 8.16 s
[Task 22/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (16/20) | 9.74 s
[Task 22/25] Current/Best: 1.56/ 19.15 GFLOPS | Progress: (20/20) | 13.52 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 20.02/ 20.02 GFLOPS | Progress: (4/20) | 6.73 s
[Task 23/25] Current/Best: 5.28/ 20.02 GFLOPS | Progress: (8/20) | 9.18 s
[Task 23/25] Current/Best: 9.89/ 20.14 GFLOPS | Progress: (12/20) | 11.83 s
[Task 23/25] Current/Best: 9.82/ 20.14 GFLOPS | Progress: (16/20) | 14.52 s
[Task 23/25] Current/Best: 8.36/ 20.14 GFLOPS | Progress: (20/20) | 17.65 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.23/ 7.72 GFLOPS | Progress: (4/20) | 4.33 s
[Task 24/25] Current/Best: 1.15/ 10.07 GFLOPS | Progress: (8/20) | 14.83 s
[Task 24/25] Current/Best: 9.68/ 10.07 GFLOPS | Progress: (12/20) | 26.06 s
[Task 24/25] Current/Best: 9.85/ 10.07 GFLOPS | Progress: (16/20) | 37.71 s
[Task 24/25] Current/Best: 1.96/ 10.07 GFLOPS | Progress: (20/20) | 48.25 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 10.03/ 10.03 GFLOPS | Progress: (4/20) | 3.36 s
[Task 25/25] Current/Best: 3.02/ 10.03 GFLOPS | Progress: (8/20) | 13.90 s
[Task 25/25] Current/Best: 3.06/ 10.03 GFLOPS | Progress: (12/20) | 25.79 s
[Task 25/25] Current/Best: 5.22/ 10.03 GFLOPS | Progress: (16/20) | 36.46 s
[Task 25/25] Current/Best: 5.20/ 10.03 GFLOPS | Progress: (20/20) | 47.94 s
@@ -673,7 +675,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -730,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 423.5871288499993, 'median': 423.5212795500047, 'std': 1.34763029209712}
- unoptimized: {'mean': 516.4432707599997, 'median': 516.3726706499972, 'std': 1.4022422790593192}
+ optimized: {'mean': 410.3863057700073, 'median': 410.34498144999816, 'std': 3.432853636493948}
+ unoptimized: {'mean': 513.3368666399474, 'median': 513.5566341999947, 'std': 1.7051907359419172}
@@ -754,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 57.960 seconds)
+ **Total running time of the script:** ( 11 minutes 3.960 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 0bb2f489fe..559429e264 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.267e-07 secs/op
+ 1.283e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index db24ce53f9..56adddfb6f 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x9501580)), stage(b, placeholder(b, 0x950a7c0)), 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, 0x1b364a70)), stage(b, placeholder(b, 0xf927d50)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 4718a52cd3..52e9533956 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**14:34.892** total execution time for **tutorial** files:
+**14:16.723** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:57.960 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:03.960 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:21.241 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:19.892 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.749 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.502 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:40.251 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.608 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.139 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.692 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.533 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.021 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.828 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.822 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.181 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.216 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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 3c41b3803a..3e605b55f7 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.963939999626746e-06 1.0
- naive 6.6652e-06 0.8369224278827295
- parallel 6.973e-06 0.8755716392045659
- vector 2.53903e-05 3.1881581228876654
+ numpy 7.840300022508017e-06 1.0
+ naive 6.7042e-06 0.8550948281001379
+ parallel 7.011e-06 0.8942259836833727
+ vector 2.4628699999999997e-05 3.1412956046701863
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019172
+ Numpy running time: 0.018293
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.231683
+ none: 3.205208
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.300975
+ blocking: 0.302485
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.337035
+ vectorization: 0.338956
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116394
+ loop permutation: 0.115099
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108136
+ array packing: 0.108057
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.109992
+ block caching: 0.110390
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146137
+ parallelization: 0.146280
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2316831066 1.0
- blocking 0.30097518700000003 0.09313264236376538
- vectorization 0.3370352539 0.10429093533697034
- loop permutation 0.1163937089 0.036016436346215853
- array packing 0.10813601229999999 0.03346120542548124
- block caching 0.109992387 0.03403563510771363
- parallelization 0.1461374082 0.04522021602351623
+ none 3.2052078806000006 1.0
+ blocking 0.3024845609 0.09437283701030219
+ vectorization 0.3389559137 0.10575161622170633
+ loop permutation 0.11509879910000001 0.03590993264326245
+ array packing 0.10805690429999999 0.03371291608074176
+ block caching 0.1103904456 0.03444096286801073
+ parallelization 0.1462801062 0.0456382586244662
diff --git a/docs/commit_hash b/docs/commit_hash
index 496b609fb8..173665aae3 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-012551ffda830d7992a467fce67cdf0ada3a1826
+2b110367d1e1df12a3e784b7cdcc1d769c97132c
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index d4626d9751..ace0a9e81d 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 11.503 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.802 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index 81fa825535..96ee167651 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 947ms/step
+1/1 [==============================] - 1s 916ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 5b5f2094af..217b2109f2 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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.zipc846ba90-e948-4683-8f07-de7816ac08de 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.zip86a9eb93-877a-40bb-90f7-7f4b06067c16 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 0441483014..051aee757b 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,12 +448,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 49.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 49.9MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 48.0MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 56.0MB/s]
- 91%|######### | 37.6M/41.5M [00:00<00:00, 55.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 52.9MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 54.7MB/s]
+ 28%|##7 | 11.5M/41.5M [00:00<00:00, 47.5MB/s]
+ 39%|###8 | 16.1M/41.5M [00:00<00:01, 24.4MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 31.9MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 38.0MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 37.5MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 427d933fb3..d3665b0c76 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,12 +431,10 @@ be unstable.</p>
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]
- 19%|#9 | 8.53M/44.7M [00:00<00:00, 89.3MB/s]
- 38%|###8 | 17.1M/44.7M [00:00<00:00, 50.1MB/s]
- 58%|#####8 | 26.1M/44.7M [00:00<00:00, 52.6MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 52.6MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 58.1MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 55.1MB/s]
+ 27%|##7 | 12.1M/44.7M [00:00<00:00, 126MB/s]
+ 54%|#####4 | 24.2M/44.7M [00:00<00:00, 107MB/s]
+ 77%|#######7 | 34.6M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 be5c60082d..844e6acf6d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.885 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.770 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 1f8e9c52c1..d5487af896 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:48.151</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:45.562</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:13.885</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:11.802</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:11.503</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:11.770</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:46.844</p></td>
+<td><p>00:46.958</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:31.947</p></td>
+<td><p>00:32.180</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>00:29.124</p></td>
+<td><p>00:28.412</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.547</p></td>
+<td><p>00:26.586</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.799</p></td>
+<td><p>00:25.152</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>00:23.308</p></td>
+<td><p>00:22.532</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>00:16.764</p></td>
+<td><p>00:17.744</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>00:02.430</p></td>
+<td><p>00:02.425</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 65e25c6f91..b9be049a2d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,7 +919,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2756.9797 2756.6301 2770.5540 2752.3762 4.9003
+ 2755.3249 2754.3682 2760.1316 2752.3538 2.8188
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 2f1dde6554..308b50526a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7295 15.6921 15.9503 15.6139 0.1134
+ 16.2046 16.2437 16.8214 15.5189 0.4584
</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 65adf9d794..48c1611ec9 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,31 +453,22 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.99M/170M [00:00<00:02, 65.7MB/s]
- 8%|8 | 14.3M/170M [00:00<00:02, 59.7MB/s]
- 12%|#1 | 20.0M/170M [00:00<00:02, 54.0MB/s]
- 15%|#4 | 25.1M/170M [00:00<00:03, 42.8MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 43.3MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 48.0MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:02, 56.6MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:01, 59.9MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 60.7MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 56.3MB/s]
- 46%|####6 | 78.3M/170M [00:01<00:01, 53.6MB/s]
- 49%|####9 | 83.5M/170M [00:01<00:01, 53.5MB/s]
- 52%|#####2 | 88.7M/170M [00:01<00:01, 49.8MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 49.5MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 56.6MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 60.3MB/s]
- 71%|####### | 120M/170M [00:02<00:00, 65.8MB/s]
- 74%|#######4 | 126M/170M [00:02<00:00, 60.8MB/s]
- 78%|#######8 | 133M/170M [00:02<00:00, 62.1MB/s]
- 82%|########1 | 139M/170M [00:02<00:00, 55.8MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 54.1MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 60.2MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 61.9MB/s]
- 98%|#########7| 166M/170M [00:03<00:00, 56.3MB/s]
-100%|##########| 170M/170M [00:03<00:00, 56.0MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:01, 150MB/s]
+ 17%|#6 | 28.6M/170M [00:00<00:01, 116MB/s]
+ 24%|##3 | 40.1M/170M [00:00<00:01, 107MB/s]
+ 30%|##9 | 50.6M/170M [00:00<00:01, 105MB/s]
+ 36%|###5 | 60.7M/170M [00:00<00:01, 105MB/s]
+ 42%|####1 | 70.8M/170M [00:00<00:01, 103MB/s]
+ 47%|####7 | 80.6M/170M [00:00<00:00, 101MB/s]
+ 53%|#####3 | 90.3M/170M [00:00<00:00, 101MB/s]
+ 59%|#####8 | 100M/170M [00:00<00:00, 101MB/s]
+ 65%|######4 | 110M/170M [00:01<00:00, 101MB/s]
+ 70%|####### | 119M/170M [00:01<00:00, 91.1MB/s]
+ 78%|#######7 | 132M/170M [00:01<00:00, 102MB/s]
+ 84%|########3 | 142M/170M [00:01<00:00, 97.5MB/s]
+ 90%|######### | 153M/170M [00:01<00:00, 103MB/s]
+ 96%|#########6| 163M/170M [00:01<00:00, 102MB/s]
+100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -575,7 +566,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 14.308 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 12.207 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 ced86a2697..00925c16f4 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,9 @@ training. Other models require a full post training calibration.</p>
Downloading: "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]
- 52%|#####2 | 7.07M/13.6M [00:00<00:00, 74.1MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 48.4MB/s]
+ 47%|####6 | 6.30M/13.6M [00:00<00:00, 54.9MB/s]
+ 85%|########5 | 11.5M/13.6M [00:00<00:00, 42.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 37.2MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +590,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2946 90.1412 93.7926 90.0108 0.4229
+ 90.3132 90.1718 94.5714 90.0174 0.5161
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +629,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.606 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.880 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 abc832f4ad..d1ae18a03f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.6050 121.5894 122.4635 120.9472 0.3133
+ 120.5405 120.4831 125.9646 119.5523 0.6634
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.482 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.074 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 aea426e7b5..58e25f1e6c 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.256 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.946 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 25252da579..a69212fcdb 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,23 @@ 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]
- 5%|4 | 6278/132723 [00:00<00:02, 62775.12KB/s]
- 11%|#1 | 14985/132723 [00:00<00:01, 77062.03KB/s]
- 17%|#7 | 22692/132723 [00:00<00:01, 56035.37KB/s]
- 24%|##3 | 31394/132723 [00:00<00:01, 66001.64KB/s]
- 29%|##9 | 38533/132723 [00:00<00:01, 52888.53KB/s]
- 36%|###5 | 47279/132723 [00:00<00:01, 61876.31KB/s]
- 41%|#### | 54165/132723 [00:00<00:01, 60514.67KB/s]
- 47%|####7 | 62990/132723 [00:00<00:01, 67962.21KB/s]
- 53%|#####2 | 70239/132723 [00:01<00:01, 61044.67KB/s]
- 60%|#####9 | 79027/132723 [00:01<00:00, 67991.23KB/s]
- 65%|######4 | 86241/132723 [00:01<00:00, 55315.35KB/s]
- 71%|#######1 | 94815/132723 [00:01<00:00, 62490.53KB/s]
- 78%|#######7 | 103420/132723 [00:01<00:00, 68427.61KB/s]
- 84%|########4 | 112135/132723 [00:01<00:00, 73381.91KB/s]
- 90%|######### | 119939/132723 [00:01<00:00, 66747.80KB/s]
- 97%|#########6| 128665/132723 [00:01<00:00, 72069.62KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 65614.51KB/s]
+ 3%|3 | 4195/132723 [00:00<00:03, 41945.44KB/s]
+ 9%|8 | 11921/132723 [00:00<00:01, 62712.01KB/s]
+ 15%|#5 | 20533/132723 [00:00<00:01, 73397.11KB/s]
+ 22%|##1 | 29078/132723 [00:00<00:01, 78151.49KB/s]
+ 28%|##8 | 37773/132723 [00:00<00:01, 81322.21KB/s]
+ 35%|###5 | 46467/132723 [00:00<00:01, 83230.28KB/s]
+ 41%|####1 | 54791/132723 [00:00<00:00, 79984.50KB/s]
+ 48%|####7 | 63434/132723 [00:00<00:00, 81977.96KB/s]
+ 54%|#####3 | 71654/132723 [00:00<00:00, 76070.52KB/s]
+ 61%|###### | 80343/132723 [00:01<00:00, 79195.03KB/s]
+ 67%|######6 | 88346/132723 [00:01<00:00, 67189.24KB/s]
+ 73%|#######3 | 97029/132723 [00:01<00:00, 72311.44KB/s]
+ 79%|#######8 | 104584/132723 [00:01<00:00, 62968.01KB/s]
+ 85%|########5 | 113317/132723 [00:01<00:00, 69061.66KB/s]
+ 91%|######### | 120630/132723 [00:01<00:00, 48572.11KB/s]
+ 97%|#########7| 129090/132723 [00:01<00:00, 56017.31KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67301.84KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +517,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.888 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.268 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 480fe0d2bf..65279ed4a8 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:00.389</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:51.128</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:14.308</p></td>
+<td><p>03:12.207</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:05.888</p></td>
+<td><p>03:05.268</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:33.482</p></td>
+<td><p>02:31.074</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>01:41.256</p></td>
+<td><p>01:36.946</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>01:05.606</p></td>
+<td><p>01:05.880</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:53.858</p></td>
+<td><p>00:53.836</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.527</p></td>
+<td><p>00:35.159</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.427</p></td>
+<td><p>00:25.641</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.031</p></td>
+<td><p>00:25.111</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 1008d17a62..a3f1d3d8e9 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip3282c536-3eb6-4a23-956e-6b4cea09f0f6 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.zip55ad295b-352b-481d-9b31-d841311bae48 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 f28921b551..5a5c1a47c0 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.856</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.465</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:44.395</p></td>
+<td><p>00:44.043</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>00:02.428</p></td>
+<td><p>00:02.394</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.025</p></td>
+<td><p>00:01.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index cb82840228..322f1c876d 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7179us [7179us] (46.33%; 46.33%)
-FoldScaleAxis: 8315us [7us] (53.67%; 53.67%)
- FoldConstant: 8308us [1703us] (53.62%; 99.92%)
- InferType: 6606us [6606us] (42.63%; 79.51%)
+InferType: 7036us [7036us] (46.21%; 46.21%)
+FoldScaleAxis: 8192us [6us] (53.79%; 53.79%)
+ FoldConstant: 8186us [1668us] (53.75%; 99.92%)
+ InferType: 6518us [6518us] (42.80%; 79.63%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6650us [6650us] (44.86%; 44.86%)
-FoldScaleAxis: 8174us [5us] (55.14%; 55.14%)
- FoldConstant: 8170us [1691us] (55.11%; 99.94%)
- InferType: 6479us [6479us] (43.70%; 79.30%)
+InferType: 6559us [6559us] (44.89%; 44.89%)
+FoldScaleAxis: 8054us [5us] (55.11%; 55.11%)
+ FoldConstant: 8049us [1645us] (55.08%; 99.94%)
+ InferType: 6404us [6404us] (43.83%; 79.57%)
</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 8a6063397f..9c9c3dd87d 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 34.128063 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 42.333793 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 3b8e70b78a..e6c4ec9de2 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 13.357945 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.383095 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 71b705492b..745c8073fc 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.018523
-Baseline: 3.227987
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018589
+Baseline: 3.243079
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.293666
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.292523
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.338604
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333028
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.116201
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116131
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.109497
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109405
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.111549
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111996
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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: 0.146519
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.150647
</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 2c9de35c68..8a8b0cd2e0 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.268</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.729</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.668</p></td>
+<td><p>00:31.871</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>00:01.520</p></td>
+<td><p>00:01.659</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>00:01.080</p></td>
+<td><p>00:01.199</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 fe0905cd5d..565ff0ab39 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:05.700</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:57.761</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:39.146</p></td>
+<td><p>05:33.110</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>01:31.992</p></td>
+<td><p>01:31.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:01.531</p></td>
+<td><p>01:01.405</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:29.978</p></td>
+<td><p>00:28.378</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:11.942</p></td>
+<td><p>00:11.993</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
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 8731db542e..5e9a024a01 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
@@ -504,175 +504,197 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 16) {
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*24)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod((threadIdx.x_1*24), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_ [...]
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx. [...]
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) - 6)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floor [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 56), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 2), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 112), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f3 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 504)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 384)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 505)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 385)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 506)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 386)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 224), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f3 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 280), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 6), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f3 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1008)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 776)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1009)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 777)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1010)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 778)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 392), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 8), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f3 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 448), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 9), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtyp [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1512)] = @tir.if_then_else(((((2 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1168)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1513)] = @tir.if_then_else(((((2 <= floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 19)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1169)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*3) + 1514)] = @tir.if_then_else(((((1 < floormod(threadIdx.x_1, 21)) && (floormod(threadIdx.x_1, 21) < 18)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 21)*49)) + (floormod(threadIdx.x_1, 21)*3)) + rx.outer.outer) + 1170)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 560), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 11), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*3), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*3), 7)) < 8)), data_3[(((((cse_var_2 + (floo [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 1), 7)) < [...]
+ pad_temp.shared_1[(((floordiv((threadIdx.x_1 + 616), 21)*63) + (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*3) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*3) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*3) + 2), 7)) < [...]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 12), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0 [...]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
}
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 14), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 15), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 17), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 18), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dt [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 20), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9 [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 21), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 23), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*1568) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0 [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 100), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*1152) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + rx.outer.inner) + 69)]))
- }
+ for (rc.outer.inner: int32, 0, 32) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*63) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 768)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 769)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*63) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*96) + (rc.outer.inner*3)) + 770)]))
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute_3[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias_3[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
}
}
}
@@ -709,7 +731,7 @@ 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: 0.299 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.277 ms
</pre></div>
</div>
</div>
@@ -739,32 +761,32 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=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=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -787,12 +809,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+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=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
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=196)
+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=56)
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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -812,148 +834,143 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && (((((int)threadIdx.x) * 24) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 2) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 6) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 8) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 9) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 11) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 12) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 14) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 15) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 17) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 18) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 20) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 21) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 108) {
- pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 23) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 104) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 116) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 140) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 152) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 164) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 176) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 100) {
- kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 3)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 6)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 9)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 12)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 15)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 18)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 21)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 24)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 27)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 30)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 33)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 36)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 39)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 42)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 45)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 48)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 51)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 54)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 57)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 60)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 63)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 66)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 1152) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + rx_outer_inner) + 69)]));
- }
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 3)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 21) * 4 [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ( [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 56) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ( [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 112) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 504)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 505)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 385)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 506)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 386)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 224) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 280) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1008)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 776)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1009)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 777)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1010)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 778)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 392) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 448) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1512)] = (((((2 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1513)] = (((((2 <= (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 19)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1169)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 3) + 1514)] = (((((1 < (((int)threadIdx.x) % 21)) && ((((int)threadIdx.x) % 21) < 18)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)threadIdx.x) % 21) * 3)) + rx_outer_outer) + 1170)] : 0.000000e+00f);
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 560) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 3) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 3) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 21) * [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ pad_temp_shared[(((((((int)threadIdx.x) + 616) / 21) * 63) + ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 3) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 3) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + [...]
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 216)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 63) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 768)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 769)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 96) + (rc_outer_inner * 3)) + 770)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
}
}
</pre></div>
@@ -990,7 +1007,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.146 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.110 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 f8974f1350..37a428d489 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8901 7.8855 7.9012 7.8836 0.0079
+ 7.8684 7.8647 7.8782 7.8624 0.0070
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.531 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.405 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index a606bf9d1e..7b7795bbaf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 752.0942 752.2007 753.3887 750.6932 1.1030
+ 751.3310 750.5699 754.0186 749.4045 1.9591
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.992 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.763 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 c82dba760e..9ffc9820d4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,29 +632,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [1024], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256))
+ let cse_var_17: int32 = (cse_var_19 + 9)
+ let cse_var_16: int32 = (cse_var_19 + 8)
+ let cse_var_15: int32 = (cse_var_19 + 7)
+ let cse_var_14: int32 = (cse_var_19 + 6)
+ let cse_var_13: int32 = (cse_var_19 + 5)
+ let cse_var_12: int32 = (cse_var_19 + 4)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 2)
+ let cse_var_9: int32 = (cse_var_19 + 15)
+ let cse_var_8: int32 = (cse_var_19 + 14)
+ let cse_var_7: int32 = (cse_var_19 + 13)
+ let cse_var_6: int32 = (cse_var_19 + 12)
+ let cse_var_5: int32 = (cse_var_19 + 11)
+ let cse_var_4: int32 = (cse_var_19 + 10)
+ let cse_var_3: int32 = (cse_var_19 + 1)
+ {
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_18 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_18 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 64) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -692,7 +740,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.527 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.719 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 6a224ddd69..5a386c28ff 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:23.639</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:29.010</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:23.603</p></td>
+<td><p>00:28.976</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>00:00.022</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index fe6a42e596..0948205606 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,8 +689,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2609914
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7643089
+No: 2 GFLOPS: 2.95/2.95 result: MeasureResult(costs=(0.07855564875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4236485958099365, timestamp=1670264421.0360904) [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5237095
+No: 3 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -812,8 +813,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10324054
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3162019
+No: 4 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -935,8 +936,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2646176
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6028914
+No: 5 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1058,8 +1059,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8666779
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4248507
+No: 6 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1181,8 +1182,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3044117
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4484268
+No: 7 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1304,8 +1305,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9837561
-No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9250124
+No: 8 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1427,8 +1428,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2037688
-No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10120135
+No: 9 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1550,8 +1551,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7348723
-No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1054530
+No: 10 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1673,8 +1674,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2259094
-No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10449984
+No: 11 GFLOPS: 0.00/2.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1796,8 +1797,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5183001
-No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10303218
+No: 12 GFLOPS: 12.31/12.31 result: MeasureResult(costs=(0.01881265,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7861850261688232, timestamp=1670264425.4484458) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1264888
+No: 13 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1919,8 +1921,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6640650
-No: 12 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6454795
+No: 14 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2042,8 +2044,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5756847
-No: 13 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9287958
+No: 15 GFLOPS: 0.00/12.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2165,8 +2167,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6145789
-No: 14 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10176749
+No: 16 GFLOPS: 44.41/44.41 result: MeasureResult(costs=(0.00521224325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7851200103759766, timestamp=1670264427.5048223) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4879305
+No: 17 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2288,10 +2291,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9921774
-No: 15 GFLOPS: 112.94/112.94 result: MeasureResult(costs=(0.002049716857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.603456735610962, timestamp=1670243486.0512342) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9115316
-No: 16 GFLOPS: 60.10/112.94 result: MeasureResult(costs=(0.0038519826923076924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4401683807373047, timestamp=1670243486.6821911) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2944210
-No: 17 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5104018
+No: 18 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2413,8 +2414,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3180903
-No: 18 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6658574
+No: 19 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2536,8 +2537,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9024384
-No: 19 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3213109
+No: 20 GFLOPS: 0.00/44.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2659,130 +2660,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2281132
-No: 20 GFLOPS: 0.00/112.94 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1730
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1749
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1693
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8483145
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3320564
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2821,9 +2699,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9115316
+[('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4879305
Finish loading 20 records
-Time cost of this operator: 0.001138
+Time cost of this operator: 0.005502
</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 593383d7cd..7c0e1fde6f 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.9 98.702 (1, 2, 10, 10, 3) 2 1 [311.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.118 0.987 (1, 6, 10, 10) 1 1 [3.118]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.311 (1, 1, 10, 10, 3) 1 1 [0.983]
-Total_time - 316.001 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.7 98.731 (1, 2, 10, 10, 3) 2 1 [311.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 0.962 (1, 6, 10, 10) 1 1 [3.036]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.307 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 315.705 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.9 97.33 (1, 6, 10, 10, 1) 2 1 [100.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.798 1.734 (1, 6, 10, 10) 1 1 [1.798]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.936 (1, 1, 10, 10, 3) 1 1 [0.97]
-Total_time - 103.668 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.486 (1, 6, 10, 10, 1) 2 1 [102.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.802 1.711 (1, 6, 10, 10) 1 1 [1.802]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.846 0.803 (1, 3, 10, 10, 1) 1 1 [0.846]
+Total_time - 105.348 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 660623ac94..9e1c8b399a 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 82.5MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 128MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -564,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.069 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.670 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index b8dba4b6e7..959ea3b048 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</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/tmpoycl8ht0/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpaxdwl7ka/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"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="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpoycl8ht0/images/target contains 8144 images
-/tmp/tmpoycl8ht0/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpaxdwl7ka/images/target contains 8144 images
+/tmp/tmpaxdwl7ka/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2297 - accuracy: 0.9197 - val_loss: 0.2806 - val_accuracy: 0.9026 - 47s/epoch - 143ms/step
+328/328 - 46s - loss: 0.2294 - accuracy: 0.9219 - val_loss: 0.1288 - val_accuracy: 0.9634 - 46s/epoch - 141ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1028 - accuracy: 0.9608 - val_loss: 0.0841 - val_accuracy: 0.9698 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0955 - accuracy: 0.9634 - val_loss: 0.1393 - val_accuracy: 0.9585 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0750 - accuracy: 0.9713 - val_loss: 0.0956 - val_accuracy: 0.9683 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0727 - accuracy: 0.9735 - val_loss: 0.1438 - val_accuracy: 0.9494 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f9d34f6d9d0>
+<keras.callbacks.History object at 0x7fc024b07b50>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.306 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 45.040 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 c21d4c2f24..b3b5a544ee 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:40.038</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:49.346</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:35.306</p></td>
+<td><p>04:45.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:03.069</p></td>
+<td><p>01:02.670</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:50.036</p></td>
+<td><p>00:50.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.906</p></td>
+<td><p>00:07.782</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.720</p></td>
+<td><p>00:03.827</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.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 569f5f7683..3e693a9285 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.237</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.801</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.217</p></td>
+<td><p>00:32.811</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.299</p></td>
+<td><p>00:10.266</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>00:01.715</p></td>
+<td><p>00:01.717</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 9af46bdae9..80b21d3266 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"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 0x7f9d2f4fe7a0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fbfca7cc710>
</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 789c5e4743..a72f65e4b3 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.312</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.147</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</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>00:04.812</p></td>
+<td><p>00:02.503</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>00:01.159</p></td>
+<td><p>00:01.232</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>00:00.574</p></td>
+<td><p>00:00.607</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>00:00.552</p></td>
+<td><p>00:00.589</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index e39dbcc005..9c92fab329 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjc0x3aj0/input0.cc'\nsource_filename = \"/tmp/tmpjc0x3aj0/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/tmpsqdsmili/input0.cc'\nsource_filename = \"/tmp/tmpsqdsmili/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/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 8f3a8ee3ba..beaec67a7d 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index c1e6a4a329..c28244ffd8 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/012551ffd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 113662900a..cda602176e 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/012551ffd/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 7df1c6f8e2..d8b3dbb3e3 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/012551ffd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 059c787568..e413310e59 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/012551ffd/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 a069c560d3..82c88d2079 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/012551ffd/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 35c6662141..b9356b88be 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/012551ffd/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 077968c164..2b0ba3ec99 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/012551ffd/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 e8a81776e7..ef04cbb5a6 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/012551ffd/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 7b809415f5..b3cfea7614 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/012551ffd/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 659f61ef44..dff225f8a0 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/012551ffd/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 31f608f66a..f313a551a6 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/012551ffd/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 3555e32137..3d5d5f88b1 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/012551ffd/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 38cb0d4e69..12d4db6ccc 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/012551ffd/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 79d51f8b0a..679f661662 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/012551ffd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 15f01505a5..976e99f0f0 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/012551ffd/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 e70ac91ba4..6793e0cc3d 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/012551ffd/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 e66eeabc1b..2bff4fd1f6 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/012551ffd/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 4a86657332..a4a59678aa 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/012551ffd/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 599c945411..ec308bde14 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/012551ffd/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 d13bc30a81..b4021cf2df 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/012551ffd/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 35b1ec9a56..51dbfc6619 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/012551ffd/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 88cafdff20..f7bc464868 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/012551ffd/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 aa8d27fa7f..07a9ab249f 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/012551ffd/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 51b81b519e..6f8e4fd192 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/012551ffd/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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/012551ffd/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b110367d/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 73577d3861..705a43cd49 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 a0acafd176..b964ba64b1 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:26.609</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.221</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.602</p></td>
+<td><p>00:26.214</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index f08fea58d4..cf870e478a 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 28.98s!
+resnet18_v1 inference graph built in 28.55s!
</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 63c583552e..b2cb2a757e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 19.60s!
+yolov3-tiny inference graph built in 19.35s!
</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 45306cec7c..6c2e1547fd 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.353</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.083</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:51.507</p></td>
+<td><p>00:51.587</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>00:48.846</p></td>
+<td><p>00:48.495</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 e41ea81114..72ce58cad4 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.203</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.275</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.739</p></td>
+<td><p>00:02.773</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>00:00.464</p></td>
+<td><p>00:00.502</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 9731bb2aa9..f7a8a08bbb 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.820</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.887</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.440</p></td>
+<td><p>00:00.471</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>00:00.380</p></td>
+<td><p>00:00.416</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 826a23b6b6..58c81af5c8 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -577,7 +577,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 98.105 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 98.507 ms
</pre></div>
</div>
</div>
@@ -651,7 +651,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.241 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.892 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index c1d9694bd6..76de8c15ae 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 1.54/1.54 result: MeasureResult(costs=(0.17421450440000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9419920444488525, timestamp=1670242029.2260752) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
-No: 2 GFLOPS: 0.50/1.54 result: MeasureResult(costs=(0.5390976992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.774592876434326, timestamp=1670242038.762536) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 3 GFLOPS: 3.68/3.68 result: MeasureResult(costs=(0.07290719279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.316204309463501, timestamp=1670242040.8460305) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
-No: 4 GFLOPS: 2.13/3.68 result: MeasureResult(costs=(0.12614115320000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.139291763305664, timestamp=1670242043.0274477) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 5 GFLOPS: 1.30/3.68 result: MeasureResult(costs=(0.207265825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.44674015045166, timestamp=1670242046.7015278) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
-No: 6 GFLOPS: 12.93/12.93 result: MeasureResult(costs=(0.020757763399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.581312894821167, timestamp=1670242047.2026014) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
-No: 7 GFLOPS: 1.85/12.93 result: MeasureResult(costs=(0.1451806354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.462167263031006, timestamp=1670242050.435471) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 8 GFLOPS: 2.12/12.93 result: MeasureResult(costs=(0.1268626322,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.222801685333252, timestamp=1670242052.6698747) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
-No: 9 GFLOPS: 4.18/12.93 result: MeasureResult(costs=(0.0641592044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1838116645812988, timestamp=1670242053.9685485) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-No: 10 GFLOPS: 0.51/12.93 result: MeasureResult(costs=(0.5291263476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.605321168899536, timestamp=1670242062.5988066) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+No: 1 GFLOPS: 2.23/2.23 result: MeasureResult(costs=(0.12029255000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0748164653778076, timestamp=1670263001.7466872) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 2 GFLOPS: 11.62/11.62 result: MeasureResult(costs=(0.0231057826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6172356605529785, timestamp=1670263002.3245099) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+No: 3 GFLOPS: 7.16/11.62 result: MeasureResult(costs=(0.037492918400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.730154275894165, timestamp=1670263003.8298085) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+No: 4 GFLOPS: 13.06/13.06 result: MeasureResult(costs=(0.0205578244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.491940975189209, timestamp=1670263004.3282335) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+No: 5 GFLOPS: 1.21/13.06 result: MeasureResult(costs=(0.2222937174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.688504695892334, timestamp=1670263008.3134856) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+No: 6 GFLOPS: 3.32/13.06 result: MeasureResult(costs=(0.08076983979999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4589121341705322, timestamp=1670263010.5136514) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+No: 7 GFLOPS: 3.64/13.06 result: MeasureResult(costs=(0.073786626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.343045949935913, timestamp=1670263012.6057835) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 8 GFLOPS: 8.69/13.06 result: MeasureResult(costs=(0.0308980176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8301124572753906, timestamp=1670263013.3047175) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+No: 9 GFLOPS: 9.91/13.06 result: MeasureResult(costs=(0.0270800922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5659821033477783, timestamp=1670263013.9851444) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 10 GFLOPS: 13.06/13.06 result: MeasureResult(costs=(0.020546659000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.45844483375549316, timestamp=1670263014.4817972) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
</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 ba655936b9..9e06d11c20 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 516.4432707599997, 'median': 516.3726706499972, 'std': 1.4022422790593192}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.3368666399474, 'median': 513.5566341999947, 'std': 1.7051907359419172}
</pre></div>
</div>
</div>
@@ -712,177 +712,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 14.45/ 14.45 GFLOPS | Progress: (4/20) | 8.60 s
-[Task 1/25] Current/Best: 8.62/ 23.26 GFLOPS | Progress: (8/20) | 12.58 s
-[Task 1/25] Current/Best: 9.37/ 23.26 GFLOPS | Progress: (12/20) | 16.05 s
-[Task 1/25] Current/Best: 7.91/ 23.26 GFLOPS | Progress: (16/20) | 19.22 s
-[Task 1/25] Current/Best: 18.08/ 23.26 GFLOPS | Progress: (20/20) | 20.93 s Done.
+[Task 1/25] Current/Best: 21.50/ 21.50 GFLOPS | Progress: (4/20) | 7.24 s
+[Task 1/25] Current/Best: 16.87/ 21.50 GFLOPS | Progress: (8/20) | 11.30 s
+[Task 1/25] Current/Best: 18.97/ 21.50 GFLOPS | Progress: (12/20) | 16.20 s
+[Task 1/25] Current/Best: 8.86/ 21.50 GFLOPS | Progress: (16/20) | 19.51 s
+[Task 1/25] Current/Best: 12.40/ 22.71 GFLOPS | Progress: (20/20) | 21.60 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.06/ 17.23 GFLOPS | Progress: (4/20) | 2.65 s
-[Task 2/25] Current/Best: 5.73/ 19.13 GFLOPS | Progress: (8/20) | 3.74 s
-[Task 2/25] Current/Best: 18.31/ 19.13 GFLOPS | Progress: (12/20) | 5.07 s
-[Task 2/25] Current/Best: 9.96/ 19.13 GFLOPS | Progress: (16/20) | 6.62 s
-[Task 2/25] Current/Best: 4.55/ 21.95 GFLOPS | Progress: (20/20) | 7.97 s Done.
+[Task 2/25] Current/Best: 16.73/ 18.35 GFLOPS | Progress: (4/20) | 2.84 s
+[Task 2/25] Current/Best: 14.25/ 18.35 GFLOPS | Progress: (8/20) | 4.28 s
+[Task 2/25] Current/Best: 10.98/ 18.35 GFLOPS | Progress: (12/20) | 6.14 s
+[Task 2/25] Current/Best: 16.08/ 19.88 GFLOPS | Progress: (16/20) | 7.19 s
+[Task 2/25] Current/Best: 15.23/ 19.88 GFLOPS | Progress: (20/20) | 8.65 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 12.69/ 18.12 GFLOPS | Progress: (4/20) | 4.01 s
-[Task 3/25] Current/Best: 9.25/ 18.12 GFLOPS | Progress: (8/20) | 7.04 s
-[Task 3/25] Current/Best: 6.80/ 23.61 GFLOPS | Progress: (12/20) | 9.78 s
-[Task 3/25] Current/Best: 14.56/ 23.61 GFLOPS | Progress: (16/20) | 11.83 s
-[Task 3/25] Current/Best: 19.23/ 23.61 GFLOPS | Progress: (20/20) | 13.76 s Done.
+[Task 3/25] Current/Best: 18.54/ 20.06 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 3/25] Current/Best: 9.03/ 20.06 GFLOPS | Progress: (8/20) | 5.76 s
+[Task 3/25] Current/Best: 17.19/ 20.06 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 3/25] Current/Best: 11.12/ 20.06 GFLOPS | Progress: (16/20) | 10.01 s
+[Task 3/25] Current/Best: 12.89/ 24.07 GFLOPS | Progress: (20/20) | 12.81 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 12.70/ 19.58 GFLOPS | Progress: (4/20) | 4.19 s
-[Task 4/25] Current/Best: 13.79/ 19.58 GFLOPS | Progress: (8/20) | 8.70 s
-[Task 4/25] Current/Best: 15.85/ 19.58 GFLOPS | Progress: (12/20) | 11.85 s
-[Task 4/25] Current/Best: 8.44/ 19.58 GFLOPS | Progress: (16/20) | 14.62 s
-[Task 4/25] Current/Best: 14.85/ 19.58 GFLOPS | Progress: (20/20) | 18.94 s Done.
+[Task 4/25] Current/Best: 12.36/ 12.36 GFLOPS | Progress: (4/20) | 12.44 s
+[Task 4/25] Current/Best: 15.65/ 16.41 GFLOPS | Progress: (8/20) | 14.56 s
+[Task 4/25] Current/Best: 16.08/ 16.41 GFLOPS | Progress: (12/20) | 19.63 s
+[Task 4/25] Current/Best: 12.39/ 17.16 GFLOPS | Progress: (16/20) | 21.55 s
+[Task 4/25] Current/Best: 20.41/ 20.41 GFLOPS | Progress: (20/20) | 26.37 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 12.17/ 13.76 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 5/25] Current/Best: 14.60/ 16.14 GFLOPS | Progress: (8/20) | 5.56 s
-[Task 5/25] Current/Best: 16.72/ 16.72 GFLOPS | Progress: (12/20) | 7.19 s
-[Task 5/25] Current/Best: 11.17/ 16.72 GFLOPS | Progress: (16/20) | 9.13 s
-[Task 5/25] Current/Best: 14.26/ 16.81 GFLOPS | Progress: (20/20) | 10.91 s Done.
+[Task 5/25] Current/Best: 11.81/ 14.50 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 5/25] Current/Best: 20.95/ 22.61 GFLOPS | Progress: (8/20) | 4.98 s
+[Task 5/25] Current/Best: 18.19/ 22.61 GFLOPS | Progress: (12/20) | 6.94 s
+[Task 5/25] Current/Best: 17.70/ 22.61 GFLOPS | Progress: (16/20) | 8.22 s
+[Task 5/25] Current/Best: 8.80/ 22.61 GFLOPS | Progress: (20/20) | 10.21 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 8.09/ 14.64 GFLOPS | Progress: (4/20) | 4.09 s
-[Task 6/25] Current/Best: 13.34/ 14.64 GFLOPS | Progress: (8/20) | 6.75 s
-[Task 6/25] Current/Best: 14.81/ 14.81 GFLOPS | Progress: (12/20) | 10.53 s
-[Task 6/25] Current/Best: 14.01/ 18.25 GFLOPS | Progress: (16/20) | 12.71 s
-[Task 6/25] Current/Best: 10.03/ 18.25 GFLOPS | Progress: (20/20) | 16.18 s Done.
+[Task 6/25] Current/Best: 5.60/ 13.63 GFLOPS | Progress: (4/20) | 4.49 s
+[Task 6/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (8/20) | 6.31 s
+[Task 6/25] Current/Best: 8.61/ 18.21 GFLOPS | Progress: (12/20) | 8.87 s
+[Task 6/25] Current/Best: 10.71/ 18.21 GFLOPS | Progress: (16/20) | 11.15 s
+[Task 6/25] Current/Best: 12.72/ 18.21 GFLOPS | Progress: (20/20) | 14.73 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 16.83/ 16.83 GFLOPS | Progress: (4/20) | 4.08 s
-[Task 7/25] Current/Best: 11.72/ 16.83 GFLOPS | Progress: (8/20) | 6.02 s
-[Task 7/25] Current/Best: 6.16/ 16.83 GFLOPS | Progress: (12/20) | 8.47 s
-[Task 7/25] Current/Best: 7.19/ 16.83 GFLOPS | Progress: (16/20) | 11.99 s
-[Task 7/25] Current/Best: 6.81/ 16.83 GFLOPS | Progress: (20/20) | 14.36 s Done.
+[Task 7/25] Current/Best: 14.55/ 22.76 GFLOPS | Progress: (4/20) | 3.48 s
+[Task 7/25] Current/Best: 19.83/ 22.76 GFLOPS | Progress: (8/20) | 6.28 s
+[Task 7/25] Current/Best: 4.84/ 22.76 GFLOPS | Progress: (12/20) | 9.27 s
+[Task 7/25] Current/Best: 3.08/ 22.76 GFLOPS | Progress: (16/20) | 12.09 s
+[Task 7/25] Current/Best: 11.25/ 22.76 GFLOPS | Progress: (20/20) | 15.57 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 15.12/ 15.12 GFLOPS | Progress: (4/20) | 4.88 s
-[Task 8/25] Current/Best: 18.32/ 18.51 GFLOPS | Progress: (8/20) | 6.96 s
-[Task 8/25] Current/Best: 5.65/ 18.51 GFLOPS | Progress: (12/20) | 8.96 s
-[Task 8/25] Current/Best: 13.40/ 18.51 GFLOPS | Progress: (16/20) | 12.20 s
-[Task 8/25] Current/Best: 4.62/ 18.51 GFLOPS | Progress: (20/20) | 16.99 s Done.
+[Task 8/25] Current/Best: 4.14/ 10.35 GFLOPS | Progress: (4/20) | 9.86 s
+[Task 8/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (8/20) | 18.30 s
+[Task 8/25] Current/Best: 7.49/ 12.13 GFLOPS | Progress: (12/20) | 25.05 s
+[Task 8/25] Current/Best: 9.13/ 14.32 GFLOPS | Progress: (16/20) | 31.43 s
+[Task 8/25] Current/Best: 11.41/ 14.32 GFLOPS | Progress: (20/20) | 33.99 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.42/ 20.93 GFLOPS | Progress: (4/20) | 2.89 s
-[Task 9/25] Current/Best: 5.77/ 20.93 GFLOPS | Progress: (8/20) | 12.31 s
-[Task 9/25] Current/Best: 13.54/ 20.93 GFLOPS | Progress: (12/20) | 15.45 s
-[Task 9/25] Current/Best: 20.74/ 20.93 GFLOPS | Progress: (16/20) | 23.97 s
-[Task 9/25] Current/Best: 9.94/ 20.93 GFLOPS | Progress: (20/20) | 26.98 s Done.
+[Task 9/25] Current/Best: 20.04/ 20.04 GFLOPS | Progress: (4/20) | 2.97 s
+[Task 9/25] Current/Best: 8.76/ 20.04 GFLOPS | Progress: (8/20) | 10.77 s
+[Task 9/25] Current/Best: 6.16/ 20.04 GFLOPS | Progress: (12/20) | 16.41 s
+[Task 9/25] Current/Best: 12.44/ 20.24 GFLOPS | Progress: (16/20) | 19.32 s
+[Task 9/25] Current/Best: 3.20/ 20.24 GFLOPS | Progress: (20/20) | 20.84 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 12.85/ 17.63 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 10/25] Current/Best: 5.74/ 17.63 GFLOPS | Progress: (8/20) | 5.42 s
-[Task 10/25] Current/Best: 10.85/ 17.63 GFLOPS | Progress: (12/20) | 8.11 s
-[Task 10/25] Current/Best: 8.07/ 18.11 GFLOPS | Progress: (16/20) | 9.72 s
-[Task 10/25] Current/Best: 14.31/ 18.11 GFLOPS | Progress: (20/20) | 11.66 s Done.
+[Task 10/25] Current/Best: 7.88/ 17.82 GFLOPS | Progress: (4/20) | 3.29 s
+[Task 10/25] Current/Best: 7.89/ 17.82 GFLOPS | Progress: (8/20) | 4.90 s
+[Task 10/25] Current/Best: 4.07/ 17.82 GFLOPS | Progress: (12/20) | 6.75 s
+[Task 10/25] Current/Best: 18.23/ 18.60 GFLOPS | Progress: (16/20) | 8.09 s
+[Task 10/25] Current/Best: 7.62/ 20.13 GFLOPS | Progress: (20/20) | 9.35 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.42/ 19.29 GFLOPS | Progress: (4/20) | 3.64 s
-[Task 11/25] Current/Best: 11.68/ 19.29 GFLOPS | Progress: (8/20) | 6.20 s
-[Task 11/25] Current/Best: 11.71/ 19.29 GFLOPS | Progress: (12/20) | 8.65 s
-[Task 11/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (16/20) | 11.39 s
-[Task 11/25] Current/Best: 6.03/ 21.85 GFLOPS | Progress: (20/20) | 13.65 s Done.
+[Task 11/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (4/20) | 3.89 s
+[Task 11/25] Current/Best: 12.24/ 22.05 GFLOPS | Progress: (8/20) | 6.43 s
+[Task 11/25] Current/Best: 18.43/ 22.05 GFLOPS | Progress: (12/20) | 8.45 s
+[Task 11/25] Current/Best: 22.10/ 22.10 GFLOPS | Progress: (16/20) | 10.40 s
+[Task 11/25] Current/Best: 10.78/ 22.10 GFLOPS | Progress: (20/20) | 12.69 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 11.63/ 19.93 GFLOPS | Progress: (4/20) | 5.63 s
-[Task 12/25] Current/Best: 14.06/ 19.93 GFLOPS | Progress: (8/20) | 11.97 s
-[Task 12/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (12/20) | 19.17 s
-[Task 12/25] Current/Best: 17.95/ 22.13 GFLOPS | Progress: (16/20) | 21.57 s
-[Task 12/25] Current/Best: 13.33/ 22.13 GFLOPS | Progress: (20/20) | 24.66 s Done.
+[Task 12/25] Current/Best: 9.88/ 14.63 GFLOPS | Progress: (4/20) | 5.73 s
+[Task 12/25] Current/Best: 15.60/ 15.60 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 12/25] Current/Best: 7.99/ 18.72 GFLOPS | Progress: (12/20) | 9.85 s
+[Task 12/25] Current/Best: 14.84/ 19.19 GFLOPS | Progress: (16/20) | 11.92 s
+[Task 12/25] Current/Best: 2.55/ 19.19 GFLOPS | Progress: (20/20) | 14.75 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 11.53/ 20.67 GFLOPS | Progress: (4/20) | 5.23 s
-[Task 13/25] Current/Best: 18.60/ 20.67 GFLOPS | Progress: (8/20) | 7.62 s
-[Task 13/25] Current/Best: 7.09/ 20.67 GFLOPS | Progress: (12/20) | 10.83 s
-[Task 13/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (16/20) | 13.50 s
-[Task 13/25] Current/Best: 6.43/ 22.13 GFLOPS | Progress: (20/20) | 17.41 s Done.
+[Task 13/25] Current/Best: 14.03/ 16.41 GFLOPS | Progress: (4/20) | 4.86 s
+[Task 13/25] Current/Best: 6.46/ 17.60 GFLOPS | Progress: (8/20) | 7.68 s
+[Task 13/25] Current/Best: 16.81/ 21.15 GFLOPS | Progress: (12/20) | 9.33 s
+[Task 13/25] Current/Best: 23.24/ 23.24 GFLOPS | Progress: (16/20) | 11.24 s
+[Task 13/25] Current/Best: 12.26/ 23.24 GFLOPS | Progress: (20/20) | 14.12 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 3.40/ 12.90 GFLOPS | Progress: (4/20) | 4.22 s
-[Task 14/25] Current/Best: 12.66/ 15.98 GFLOPS | Progress: (8/20) | 7.88 s
-[Task 14/25] Current/Best: 4.22/ 15.98 GFLOPS | Progress: (12/20) | 12.01 s
-[Task 14/25] Current/Best: 13.68/ 15.99 GFLOPS | Progress: (16/20) | 13.62 s
-[Task 14/25] Current/Best: 11.17/ 15.99 GFLOPS | Progress: (20/20) | 17.84 s
+[Task 14/25] Current/Best: 11.69/ 14.06 GFLOPS | Progress: (4/20) | 5.22 s
+[Task 14/25] Current/Best: 9.73/ 18.45 GFLOPS | Progress: (8/20) | 7.55 s
+[Task 14/25] Current/Best: 15.82/ 18.45 GFLOPS | Progress: (12/20) | 9.59 s
+[Task 14/25] Current/Best: 5.50/ 18.45 GFLOPS | Progress: (16/20) | 12.48 s
+[Task 14/25] Current/Best: 12.54/ 18.45 GFLOPS | Progress: (20/20) | 18.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 18.33/ 19.54 GFLOPS | Progress: (4/20) | 3.00 s
-[Task 15/25] Current/Best: 12.44/ 19.54 GFLOPS | Progress: (8/20) | 4.92 s Done.
+[Task 15/25] Current/Best: 23.23/ 23.23 GFLOPS | Progress: (4/20) | 5.06 s
+[Task 15/25] Current/Best: 12.14/ 23.23 GFLOPS | Progress: (8/20) | 6.56 s
+[Task 15/25] Current/Best: 10.26/ 23.23 GFLOPS | Progress: (12/20) | 13.06 s Done.
+
+[Task 15/25] Current/Best: 6.48/ 23.23 GFLOPS | Progress: (16/20) | 14.50 s
+[Task 15/25] Current/Best: 4.87/ 23.23 GFLOPS | Progress: (20/20) | 16.00 s Done.
-[Task 15/25] Current/Best: 13.66/ 19.80 GFLOPS | Progress: (12/20) | 8.10 s
-[Task 15/25] Current/Best: 3.19/ 19.80 GFLOPS | Progress: (16/20) | 12.08 s
-[Task 15/25] Current/Best: 15.63/ 19.80 GFLOPS | Progress: (20/20) | 14.04 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 18.26/ 18.69 GFLOPS | Progress: (4/20) | 3.37 s
-[Task 16/25] Current/Best: 7.55/ 18.69 GFLOPS | Progress: (8/20) | 6.55 s
-[Task 16/25] Current/Best: 7.50/ 18.69 GFLOPS | Progress: (12/20) | 9.76 s
-[Task 16/25] Current/Best: 12.36/ 18.69 GFLOPS | Progress: (16/20) | 12.06 s
-[Task 16/25] Current/Best: 10.32/ 19.14 GFLOPS | Progress: (20/20) | 14.00 s Done.
+[Task 16/25] Current/Best: 9.24/ 15.22 GFLOPS | Progress: (4/20) | 3.59 s
+[Task 16/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (8/20) | 7.10 s
+[Task 16/25] Current/Best: 17.16/ 18.20 GFLOPS | Progress: (12/20) | 10.02 s
+[Task 16/25] Current/Best: 16.10/ 18.20 GFLOPS | Progress: (16/20) | 11.36 s
+[Task 16/25] Current/Best: 15.92/ 18.20 GFLOPS | Progress: (20/20) | 12.68 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 17/25] Current/Best: 18.99/ 21.38 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 17/25] Current/Best: 8.15/ 21.38 GFLOPS | Progress: (12/20) | 10.56 s
-[Task 17/25] Current/Best: 6.82/ 21.38 GFLOPS | Progress: (16/20) | 13.91 s
-[Task 17/25] Current/Best: 12.24/ 21.38 GFLOPS | Progress: (20/20) | 16.13 s Done.
+[Task 17/25] Current/Best: 12.22/ 23.08 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 17/25] Current/Best: 17.63/ 23.08 GFLOPS | Progress: (8/20) | 6.86 s
+[Task 17/25] Current/Best: 12.39/ 23.08 GFLOPS | Progress: (12/20) | 10.04 s
+[Task 17/25] Current/Best: 11.65/ 23.11 GFLOPS | Progress: (16/20) | 12.17 s
+[Task 17/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 14.70 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 13.49/ 16.02 GFLOPS | Progress: (4/20) | 3.42 s
-[Task 18/25] Current/Best: 10.02/ 17.60 GFLOPS | Progress: (8/20) | 6.25 s
-[Task 18/25] Current/Best: 15.05/ 17.60 GFLOPS | Progress: (12/20) | 8.46 s
-[Task 18/25] Current/Best: 5.20/ 17.60 GFLOPS | Progress: (16/20) | 13.46 s
-[Task 18/25] Current/Best: 14.23/ 19.42 GFLOPS | Progress: (20/20) | 15.22 s Done.
+[Task 18/25] Current/Best: 14.41/ 14.41 GFLOPS | Progress: (4/20) | 3.73 s
+[Task 18/25] Current/Best: 15.57/ 23.12 GFLOPS | Progress: (8/20) | 7.36 s
+[Task 18/25] Current/Best: 17.55/ 23.12 GFLOPS | Progress: (12/20) | 10.76 s
+[Task 18/25] Current/Best: 14.93/ 23.12 GFLOPS | Progress: (16/20) | 12.30 s
+[Task 18/25] Current/Best: 21.27/ 23.12 GFLOPS | Progress: (20/20) | 13.82 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 11.83/ 20.17 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 19/25] Current/Best: 12.91/ 20.17 GFLOPS | Progress: (8/20) | 9.67 s
-[Task 19/25] Current/Best: 17.88/ 20.75 GFLOPS | Progress: (12/20) | 12.45 s
-[Task 19/25] Current/Best: 17.86/ 22.34 GFLOPS | Progress: (16/20) | 15.67 s
-[Task 19/25] Current/Best: 5.35/ 22.34 GFLOPS | Progress: (20/20) | 20.53 s Done.
+[Task 19/25] Current/Best: 10.57/ 23.65 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 19/25] Current/Best: 22.27/ 23.65 GFLOPS | Progress: (8/20) | 6.94 s
+[Task 19/25] Current/Best: 21.89/ 23.65 GFLOPS | Progress: (12/20) | 8.66 s
+[Task 19/25] Current/Best: 1.55/ 23.65 GFLOPS | Progress: (16/20) | 13.20 s
+[Task 19/25] Current/Best: 19.10/ 23.65 GFLOPS | Progress: (20/20) | 15.20 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 6.19/ 6.73 GFLOPS | Progress: (4/20) | 4.65 s
-[Task 20/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 9.67 s
-[Task 20/25] Current/Best: 4.90/ 18.80 GFLOPS | Progress: (12/20) | 13.55 s
-[Task 20/25] Current/Best: 10.45/ 18.80 GFLOPS | Progress: (16/20) | 15.79 s
-[Task 20/25] Current/Best: 12.72/ 18.80 GFLOPS | Progress: (20/20) | 18.41 s
+[Task 20/25] Current/Best: 15.96/ 15.96 GFLOPS | Progress: (4/20) | 3.47 s
+[Task 20/25] Current/Best: 9.92/ 18.24 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 20/25] Current/Best: 14.04/ 18.24 GFLOPS | Progress: (12/20) | 8.11 s
+[Task 20/25] Current/Best: 10.39/ 18.24 GFLOPS | Progress: (16/20) | 10.03 s
+[Task 20/25] Current/Best: 13.90/ 18.24 GFLOPS | Progress: (20/20) | 12.59 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 11.49/ 17.34 GFLOPS | Progress: (4/20) | 2.90 s Done.
-
-[Task 21/25] Current/Best: 8.23/ 17.34 GFLOPS | Progress: (8/20) | 4.87 s
-[Task 21/25] Current/Best: 2.31/ 17.95 GFLOPS | Progress: (12/20) | 7.19 s
-[Task 21/25] Current/Best: 18.75/ 18.75 GFLOPS | Progress: (16/20) | 8.78 s
-[Task 21/25] Current/Best: 16.85/ 18.75 GFLOPS | Progress: (20/20) | 11.09 s
+[Task 21/25] Current/Best: 13.98/ 16.98 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 21/25] Current/Best: 18.78/ 18.78 GFLOPS | Progress: (8/20) | 5.25 s
+[Task 21/25] Current/Best: 10.39/ 18.78 GFLOPS | Progress: (12/20) | 7.57 s
+[Task 21/25] Current/Best: 13.33/ 18.78 GFLOPS | Progress: (16/20) | 8.95 s
+[Task 21/25] Current/Best: 12.02/ 21.03 GFLOPS | Progress: (20/20) | 10.98 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (4/20) | 5.73 s
-[Task 22/25] Current/Best: 16.59/ 20.43 GFLOPS | Progress: (8/20) | 7.00 s
-[Task 22/25] Current/Best: 3.08/ 20.43 GFLOPS | Progress: (12/20) | 8.68 s
-[Task 22/25] Current/Best: 14.64/ 20.43 GFLOPS | Progress: (16/20) | 11.89 s
-[Task 22/25] Current/Best: 18.34/ 20.43 GFLOPS | Progress: (20/20) | 13.21 s Done.
+[Task 22/25] Current/Best: 9.12/ 9.96 GFLOPS | Progress: (4/20) | 4.84 s Done.
+ Done.
+
+[Task 22/25] Current/Best: 10.29/ 16.33 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 22/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (12/20) | 8.16 s
+[Task 22/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (16/20) | 9.74 s
+[Task 22/25] Current/Best: 1.56/ 19.15 GFLOPS | Progress: (20/20) | 13.52 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 12.07/ 20.15 GFLOPS | Progress: (4/20) | 5.96 s
-[Task 23/25] Current/Best: 18.09/ 20.15 GFLOPS | Progress: (8/20) | 8.59 s
-[Task 23/25] Current/Best: 5.21/ 20.15 GFLOPS | Progress: (12/20) | 11.22 s
-[Task 23/25] Current/Best: 8.24/ 22.79 GFLOPS | Progress: (16/20) | 15.09 s
-[Task 23/25] Current/Best: 17.73/ 22.79 GFLOPS | Progress: (20/20) | 17.48 s Done.
+[Task 23/25] Current/Best: 20.02/ 20.02 GFLOPS | Progress: (4/20) | 6.73 s
+[Task 23/25] Current/Best: 5.28/ 20.02 GFLOPS | Progress: (8/20) | 9.18 s
+[Task 23/25] Current/Best: 9.89/ 20.14 GFLOPS | Progress: (12/20) | 11.83 s
+[Task 23/25] Current/Best: 9.82/ 20.14 GFLOPS | Progress: (16/20) | 14.52 s
+[Task 23/25] Current/Best: 8.36/ 20.14 GFLOPS | Progress: (20/20) | 17.65 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 0.98/ 9.50 GFLOPS | Progress: (4/20) | 5.37 s
-[Task 24/25] Current/Best: 1.69/ 9.50 GFLOPS | Progress: (8/20) | 16.09 s
-[Task 24/25] Current/Best: 1.83/ 9.50 GFLOPS | Progress: (12/20) | 27.59 s
-[Task 24/25] Current/Best: 1.69/ 9.50 GFLOPS | Progress: (16/20) | 39.10 s
-[Task 24/25] Current/Best: 3.64/ 9.59 GFLOPS | Progress: (20/20) | 44.87 s Done.
-
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 7.55/ 8.36 GFLOPS | Progress: (4/20) | 3.03 s
-[Task 25/25] Current/Best: 7.16/ 8.36 GFLOPS | Progress: (8/20) | 4.14 s
-[Task 25/25] Current/Best: 6.17/ 8.61 GFLOPS | Progress: (12/20) | 14.86 s
-[Task 25/25] Current/Best: 6.37/ 8.90 GFLOPS | Progress: (16/20) | 23.74 s
-[Task 25/25] Current/Best: 3.12/ 9.01 GFLOPS | Progress: (20/20) | 28.67 s
+[Task 24/25] Current/Best: 3.23/ 7.72 GFLOPS | Progress: (4/20) | 4.33 s
+[Task 24/25] Current/Best: 1.15/ 10.07 GFLOPS | Progress: (8/20) | 14.83 s
+[Task 24/25] Current/Best: 9.68/ 10.07 GFLOPS | Progress: (12/20) | 26.06 s
+[Task 24/25] Current/Best: 9.85/ 10.07 GFLOPS | Progress: (16/20) | 37.71 s
+[Task 24/25] Current/Best: 1.96/ 10.07 GFLOPS | Progress: (20/20) | 48.25 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 25/25] Current/Best: 10.03/ 10.03 GFLOPS | Progress: (4/20) | 3.36 s
+[Task 25/25] Current/Best: 3.02/ 10.03 GFLOPS | Progress: (8/20) | 13.90 s
+[Task 25/25] Current/Best: 3.06/ 10.03 GFLOPS | Progress: (12/20) | 25.79 s
+[Task 25/25] Current/Best: 5.22/ 10.03 GFLOPS | Progress: (16/20) | 36.46 s
+[Task 25/25] Current/Best: 5.20/ 10.03 GFLOPS | Progress: (20/20) | 47.94 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -944,7 +946,7 @@ model using optimized operators to speed up our computations.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356377
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -981,8 +983,8 @@ 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': 423.5871288499993, 'median': 423.5212795500047, 'std': 1.34763029209712}
-unoptimized: {'mean': 516.4432707599997, 'median': 516.3726706499972, 'std': 1.4022422790593192}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.3863057700073, 'median': 410.34498144999816, 'std': 3.432853636493948}
+unoptimized: {'mean': 513.3368666399474, 'median': 513.5566341999947, 'std': 1.7051907359419172}
</pre></div>
</div>
</div>
@@ -996,7 +998,7 @@ 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 57.960 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 3.960 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 c049812f94..eedadc3f8e 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</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>1.267e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.283e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 2f748495f3..03c3d35e09 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x9501580)), stage(b, placeholder(b, 0x950a7c0)), 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=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x1b364a70)), stage(b, placeholder(b, 0xf927d50)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 04442a8557..8ebe3075ab 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:34.892</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:16.723</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,43 +349,43 @@
</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>10:57.960</p></td>
+<td><p>11:03.960</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:21.241</p></td>
+<td><p>01:19.892</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:58.749</p></td>
+<td><p>00:58.502</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>00:40.251</p></td>
+<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>00:33.608</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><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>00:34.139</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
+<td><p>00:18.692</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.533</p></td>
+<td><p>00:01.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.828</p></td>
+<td><p>00:00.822</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>00:00.181</p></td>
+<td><p>00:00.216</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>00:00.006</p></td>
+<td><p>00:00.007</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>
-<td><p>00:00.002</p></td>
+<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index b06e71f7b2..571550c3dd 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.963939999626746e-06 1.0
- naive 6.6652e-06 0.8369224278827295
-parallel 6.973e-06 0.8755716392045659
- vector 2.53903e-05 3.1881581228876654
+ numpy 7.840300022508017e-06 1.0
+ naive 6.7042e-06 0.8550948281001379
+parallel 7.011e-06 0.8942259836833727
+ vector 2.4628699999999997e-05 3.1412956046701863
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019172
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018293
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.231683
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.205208
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.300975
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.302485
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.337035
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.338956
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116394
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.115099
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108136
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108057
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.109992
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110390
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146137
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146280
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.2316831066 1.0
- blocking 0.30097518700000003 0.09313264236376538
- vectorization 0.3370352539 0.10429093533697034
-loop permutation 0.1163937089 0.036016436346215853
- array packing 0.10813601229999999 0.03346120542548124
- block caching 0.109992387 0.03403563510771363
- parallelization 0.1461374082 0.04522021602351623
+ none 3.2052078806000006 1.0
+ blocking 0.3024845609 0.09437283701030219
+ vectorization 0.3389559137 0.10575161622170633
+loop permutation 0.11509879910000001 0.03590993264326245
+ array packing 0.10805690429999999 0.03371291608074176
+ block caching 0.1103904456 0.03444096286801073
+ parallelization 0.1462801062 0.0456382586244662
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a