You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/28 15:03:27 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@61144f9d8711aad15d2b1a19d983a4891e1be706)
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 4f4e410db3 deploying docs (apache/tvm@61144f9d8711aad15d2b1a19d983a4891e1be706)
4f4e410db3 is described below
commit 4f4e410db39cb33e5228b44354fd0ad5c2111379
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Nov 28 15:03:20 2022 +0000
deploying docs (apache/tvm@61144f9d8711aad15d2b1a19d983a4891e1be706)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 327199 -> 324292 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22934 -> 23851 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 | 4 +-
.../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 | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 900 ++++++++++++++-------
.../tune_network_cuda.rst.txt | 7 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 83 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 817 ++-----------------
.../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 | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 61 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
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 | 11 +-
docs/how_to/compile_models/from_pytorch.html | 11 +-
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 | 4 +-
.../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 | 44 +-
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 | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 900 ++++++++++++++-------
.../tune_with_autoscheduler/tune_network_cuda.html | 3 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 83 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 817 ++-----------------
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 | 16 +-
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 | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 267 +++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
130 files changed, 2282 insertions(+), 2953 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9acba7fd3b..fd04aec899 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index fb0f49ab60..176d23232e 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 a05e979313..f4531ea61f 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 9.613 seconds)
+ **Total running time of the script:** ( 1 minutes 11.256 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 30629a6d70..8dd3a9ba63 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 1s/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 926ms/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 0055c09987..55c9792c77 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.zip97a78d84-9dd6-45c0-a1bb-ed12a2d188dd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipcc40aad3-8dcc-404a-b9a3-f010e7144676 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 7a286bc10b..4a874c6b4b 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]
28%|##8 | 11.8M/41.5M [00:00<00:00, 124MB/s]
57%|#####6 | 23.6M/41.5M [00:00<00:00, 109MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 105MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 106MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 66.0MB/s]
30%|### | 12.6M/41.5M [00:00<00:00, 61.4MB/s]
45%|####4 | 18.5M/41.5M [00:00<00:00, 38.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 39.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 51.1MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 48.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 48.4MB/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 282f1f1da7..1a4aaa01dd 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]
26%|##6 | 11.8M/44.7M [00:00<00:00, 123MB/s]
53%|#####2 | 23.5M/44.7M [00:00<00:00, 109MB/s]
76%|#######6 | 34.0M/44.7M [00:00<00:00, 105MB/s]
99%|#########8| 44.0M/44.7M [00:00<00:00, 103MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 46.7MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 69.8MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 80.3MB/s]
76%|#######5 | 33.9M/44.7M [00:00<00:00, 73.1MB/s]
93%|#########2| 41.4M/44.7M [00:00<00:00, 74.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 72.1MB/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 90fe5f95b5..6d87cb14e3 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 13.118 seconds)
+ **Total running time of the script:** ( 1 minutes 9.903 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 a41f86716b..7704b5753b 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
=================
-**05:42.732** total execution time for **how_to_compile_models** files:
+**05:39.882** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.256 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.613 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:09.903 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.430 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.882 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.885 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.454 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.161 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.510 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.745 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.404 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.706 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.305 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.756 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.632 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.386 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.388 | 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 ab46d3c398..45ce5b5b7d 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)
- 3344.6771 3343.5188 3359.0259 3336.9567 6.5112
+ 3340.6784 3339.5931 3347.4538 3337.5561 3.1354
@@ -732,7 +732,7 @@ well as provides information about the model's performance
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.226 seconds)
+ **Total running time of the script:** ( 1 minutes 0.472 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
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 0b6ea2411f..c9d8f23837 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1232 15.9256 16.9046 15.7265 0.4393
+ 16.0077 15.9722 16.3833 15.8812 0.1352
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 244206a134..bb1764a81a 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]
9%|8 | 14.6M/170M [00:00<00:01, 153MB/s]
17%|#7 | 29.2M/170M [00:00<00:01, 116MB/s]
24%|##4 | 40.8M/170M [00:00<00:01, 108MB/s]
30%|### | 51.3M/170M [00:00<00:01, 106MB/s]
36%|###6 | 61.6M/170M [00:00<00:01, 104MB/s]
42%|####2 | 71.6M/170M [00:00<00:01, 99.5MB/s]
48%|####7 | 81.2M/170M [00:00<00:00, 97.9MB/s]
53%|#####3 | 90.5M/170M [00:00<00:00, 87.2MB/s]
59%|#####8 | 100M/170M [00:01<00:00, 90.8MB/s]
64%|######4 | 109M/170M [00:01<00:00, 90.8MB/s]
69%|######9 | 118M/170M [00:01<00:00, 90.5MB/s]
75%|#######4 | 127M/170M [00:01<00:00, 92.4MB/s]
80%|######## | 136M/170M [00:01<00:00, 68.0MB/s]
87%|########6 | 147M/170M [00:01<00:00, 78.7MB/s]
92%|#########1| 156M/170M [00:01<00:00, 78.4MB/s]
96%|#########6| 164M/170M [00:01<00:00, 74.2MB/s]
100%|##########| 170M/170M [00:01<00:00, 90.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 57.4MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 63.0MB/s]
13%|#3 | 22.3M/170M [00:00<00:02, 64.1MB/s]
17%|#6 | 28.5M/170M [00:00<00:02, 60.9MB/s]
22%|##2 | 37.4M/170M [00:00<00:01, 71.5MB/s]
26%|##6 | 44.4M/170M [00:00<00:01, 69.6MB/s]
30%|### | 51.1M/170M [00:00<00:02, 58.8MB/s]
37%|###6 | 62.3M/170M [00:00<00:01, 74.0MB/s]
41%|####1 | 69.8M/170M [00:01<00:01, 66.9MB/s]
45%|####5 | 76.5M/170M [00:01<00:01, 67.5MB/s]
49%|####9 | 83.2M/170M [00:01<00:01, 65.2MB/s]
53%|#####3 | 90.1M/170M [00:01<00:01, 63.9MB/s]
57%|#####6 | 96.3M/170M [00:01<00:01, 55.1MB/s]
60%|###### | 102M/170M [00:01<00:01, 54.5MB/s]
63%|######3 | 108M/170M [00:01<00:01, 46.0MB/s]
67%|######7 | 114M/170M [00:02<00:01, 48.1MB/s]
71%|####### | 120M/170M [00:02<00:01, 50.9MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 56.2MB/s]
80%|######## | 136M/170M [00:02<00:00, 62.1MB/s]
85%|########4 | 144M/170M [00:02<00:00, 64.1MB/s]
89%|########9 | 152M/170M [00:02<00:00, 61.2MB/s]
93%|#########3| 158M/170M [00:02<00:00, 49.1MB/s]
96%|#########6| 163M/170M [00:03<00:00, 42.2MB/s]
100%|##########| 170M/170M [00:03<00:00, 57.5MB/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 16.418 seconds)
+ **Total running time of the script:** ( 3 minutes 9.036 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 8ead1316d3..ada2110091 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]
86%|########6 | 11.7M/13.6M [00:00<00:00, 91.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 99.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 46.3MB/s]
92%|#########1| 12.4M/13.6M [00:00<00:00, 44.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 48.2MB/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)
- 90.2859 90.1851 92.7542 90.0537 0.3070
+ 90.0908 89.9916 95.0659 89.7488 0.5376
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.492 seconds)
+ **Total running time of the script:** ( 1 minutes 4.587 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 5025d9b733..3441ef0dcd 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)
- 120.6198 120.6334 122.5440 119.6961 0.4538
+ 120.9077 121.0449 123.9441 118.0763 0.7607
@@ -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 23.458 seconds)
+ **Total running time of the script:** ( 2 minutes 21.673 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 e38e97859c..87c019150f 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 15.534 seconds)
+ **Total running time of the script:** ( 1 minutes 35.169 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 c25da7652f..39ed12b8b8 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]
3%|3 | 4538/132723 [00:00<00:02, 44814.51KB/s]
9%|9 | 11993/132723 [00:00<00:01, 62213.42KB/s]
15%|#5 | 20557/132723 [00:00<00:01, 72876.88KB/s]
22%|##1 | 29146/132723 [00:00<00:01, 77993.37KB/s]
28%|##8 | 37813/132723 [00:00<00:01, 81115.11KB/s]
35%|###4 | 46453/132723 [00:00<00:01, 82907.69KB/s]
41%|####1 | 55020/132723 [00:00<00:00, 83808.82KB/s]
48%|####8 | 63742/132723 [00:00<00:00, 84891.79KB/s]
55%|#####4 | 72422/132723 [00:00<00:00, 85485.81KB/s]
61%|######1 | 81184/132723 [00:01<00:00, 86142.15KB/s]
68%|######7 | 89799/132723 [00:01<00:00, 86131.44KB/s]
74%|#######4 | 98532/132723 [00:01<00:00, 86493.05KB/s]
81%|######## | 107215/132723 [00:01<00:00, 86593.44KB/s]
87%|########7 | 115918/132723 [00:01<00:00, 86724.06KB/s]
94%|#########3| 124591/132723 [00:01<00:00, 86465.60KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82996.38KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
0%| | 477/132723 [00:00<00:28, 4601.06KB/s]
1%| | 1242/132723 [00:00<00:20, 6300.41KB/s]
2%|1 | 2202/132723 [00:00<00:16, 7747.18KB/s]
3%|2 | 3386/132723 [00:00<00:13, 9332.63KB/s]
4%|3 | 4874/132723 [00:00<00:11, 11306.33KB/s]
5%|5 | 6714/132723 [00:00<00:09, 13695.70KB/s]
7%|6 | 9066/132723 [00:00<00:07, 16887.11KB/s]
9%|9 | 12057/132723 [00:00<00:05, 21018.31KB/s]
12%|#1 | 15706/132723 [00:00<00:04, 25833.38KB/s]
15%|#5 | 20410/132723 [00:01<00:03, 32314.43KB/s]
20%|#9 | 26279/132723 [00:01<00:02, 40365.48KB/s]
25%|##5 | 33423/132723 [00:01<00:01, 49800.65KB/s]
31%|### | 40846/132723 [00:01<00:01, 57191.17KB/s]
36%|###6 | 48362/132723 [00:01<00:01, 62611.36KB/s]
42%|####2 | 55901/132723 [00:01<00:01, 66458.14KB/s]
48%|####7 | 63410/1327
23 [00:01<00:01, 69052.25KB/s]
54%|#####3 | 71023/132723 [00:01<00:00, 71177.13KB/s]
59%|#####9 | 78603/132723 [00:01<00:00, 72564.12KB/s]
65%|######4 | 86233/132723 [00:01<00:00, 73685.05KB/s]
71%|####### | 93798/132723 [00:02<00:00, 74273.71KB/s]
76%|#######6 | 101360/132723 [00:02<00:00, 74676.41KB/s]
82%|########2 | 108907/132723 [00:02<00:00, 74912.00KB/s]
88%|########7 | 116618/132723 [00:02<00:00, 75502.95KB/s]
94%|#########3| 124506/132723 [00:02<00:00, 76466.75KB/s]
100%|#########9| 132446/132723 [00:02<00:00, 77344.28KB/s]
100%|##########| 132723/132723 [00:02<00:00, 52768.49KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 4.738 seconds)
+ **Total running time of the script:** ( 2 minutes 59.629 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 1d83277606..195af967e7 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
=================
-**13:32.624** total execution time for **how_to_deploy_models** files:
+**13:33.406** 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``) | 03:16.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:09.036 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:04.738 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:59.629 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.458 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:21.673 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:15.534 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.169 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.492 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.587 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:01.226 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:00.472 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.516 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.530 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.734 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.306 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.997 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index ef02b71081..9d0f63769e 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.zip714dc02d-2f12-4161-a4c5-d99666d55c17 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip3a926a0d-246a-46b6-81be-f2da37e3b7d8 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 e239dd6b35..b47d729962 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
=================
-**00:49.266** total execution time for **how_to_extend_tvm** files:
+**00:46.633** 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``) | 00:45.688 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.179 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.509 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.442 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.004 | 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 0a261519de..1c20d1de66 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: 7449us [7449us] (46.52%; 46.52%)
- FoldScaleAxis: 8566us [8us] (53.48%; 53.48%)
- FoldConstant: 8557us [1755us] (53.43%; 99.91%)
- InferType: 6802us [6802us] (42.47%; 79.49%)
+ InferType: 7338us [7338us] (46.67%; 46.67%)
+ FoldScaleAxis: 8385us [7us] (53.33%; 53.33%)
+ FoldConstant: 8379us [1709us] (53.29%; 99.92%)
+ InferType: 6670us [6670us] (42.42%; 79.60%)
@@ -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: 6916us [6916us] (45.14%; 45.14%)
- FoldScaleAxis: 8405us [6us] (54.86%; 54.86%)
- FoldConstant: 8399us [1735us] (54.82%; 99.93%)
- InferType: 6664us [6664us] (43.49%; 79.34%)
+ InferType: 6679us [6679us] (44.71%; 44.71%)
+ FoldScaleAxis: 8259us [5us] (55.29%; 55.29%)
+ FoldConstant: 8254us [1688us] (55.25%; 99.94%)
+ InferType: 6566us [6566us] (43.96%; 79.55%)
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 beaa32e416..a5b275238f 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: 49.608894 ms
+ Convolution: 35.872768 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 2fd2adaa55..66d662cca6 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: 12.536627 ms
+ conv2d with tensor core: 13.067497 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 e0e3738737..5b44c5df10 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: 0.018991
- Baseline: 3.245249
+ Numpy running time: 0.018249
+ Baseline: 3.245860
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.307920
+ Opt1: 0.301167
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.337509
+ Opt2: 0.333597
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115460
+ Opt3: 0.114993
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109356
+ Opt4: 0.109305
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110808
+ Opt5: 0.110966
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146717
+ Opt6: 0.146460
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 c38c1bc22c..260458546a 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
=================
-**00:34.543** total execution time for **how_to_optimize_operators** files:
+**00:34.145** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.702 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.480 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.419 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.024 | 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 c79e4c6c57..47fbc1ce19 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
=================
-**08:57.170** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:48.983** 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``) | 05:31.898 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:30.318 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.389 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.005 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:00.664 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:59.581 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:26.623 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.058 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.637 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.347 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.820 | 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 b1765a3f7c..f29af0c781 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,153 +239,356 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), 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" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((7 < floormod((threadIdx.x_1*12), 63)) && (floormod((threadIdx.x_1*12), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod((threadIdx.x_1 [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 1), 63)) && (floormod(((threadIdx.x_1*12) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 1), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx.x_1* [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 2), 63)) && (floormod(((threadIdx.x_1*12) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 2), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx.x_1*5 [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 3), 63)) && (floormod(((threadIdx.x_1*12) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 3), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 4), 63)) && (floormod(((threadIdx.x_1*12) + 4), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 4), 63), 7)*7)) + rx.outer.outer) + floormod(((threadId [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 5), 63)) && (floormod(((threadIdx.x_1*12) + 5), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 5), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 6), 63)) && (floormod(((threadIdx.x_1*12) + 6), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 6), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 7), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)*7)) + rx.outer.outer) + floormod((threadIdx. [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 8), 63)) && (floormod(((threadIdx.x_1*12) + 8), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 8), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 9), 63)) && (floormod(((threadIdx.x_1*12) + 9), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 9), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 10), 63)) && (floormod(((threadIdx.x_1*12) + 10), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 10), 63), 7)*7)) + rx.outer.outer) + floormod(((thre [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 11), 63)) && (floormod(((threadIdx.x_1*12) + 11), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 11), 63), 7)*7)) + rx.outer.outer) + floormod(((threa [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 164), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 768)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 816)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 96)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 864)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 912)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 771)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 819)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 867)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 147)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 915)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 774)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 822)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 102)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 870)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 150)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 918)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 777)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 825)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 105)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 873)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 153)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 921)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 780)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 828)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 876)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 156)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 924)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 783)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 831)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 111)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 879)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 159)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 927)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 786)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 834)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 114)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 882)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 162)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 930)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 789)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 837)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 885)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 165)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 933)]))
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 2), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 4), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 4), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 6), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 6), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 8), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 8), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floor [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 12), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 12), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floor [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 14), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 14), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + flo [...]
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 168), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 504), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1400), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1456), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1512), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1848), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2072), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2184), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2520), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2632), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2856), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3080)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3192), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3248), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3304)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3304), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3640)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3752)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3864)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3864), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3976)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3976), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4088)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4200)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4200), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4368), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4424)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4536)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4536), 144)*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" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4592), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2304)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2305)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2306)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2307)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2308)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2309)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2310)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2311)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2312)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2313)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2314)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2315)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2316)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2317)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2318)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2319)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2320)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2321)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2322)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2323)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2324)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2325)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2326)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2327)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2328)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2329)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2330)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2331)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2332)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2333)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2334)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2335)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2336)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2337)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2338)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2339)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2448)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2449)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2450)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2451)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2452)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2453)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2454)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2455)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2456)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 153)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2457)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 154)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2458)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 155)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2459)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 156)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2460)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 157)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2461)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 158)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2462)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 159)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2463)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 160)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2464)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 161)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2465)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 162)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2466)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 163)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2467)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 164)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2468)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 165)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2469)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 166)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2470)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 167)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2471)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 168)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2472)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 169)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2473)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 170)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2474)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 171)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2475)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 172)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2476)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 173)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2477)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 174)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2478)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 175)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2479)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 176)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2480)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 177)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2481)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 178)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2482)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 179)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2483)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (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*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
- compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute_3[((((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[((((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -440,7 +643,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.392 ms
+ Execution time of this operator: 0.367 ms
@@ -488,33 +691,33 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
- 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=4)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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_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=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ 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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
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_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=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)
@@ -537,14 +740,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=12)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -562,141 +765,262 @@ 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[8];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[1536];
+ 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[4];
+ __shared__ float pad_temp_shared[432];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((7 < ((((int)threadIdx.x) * 12) % 63)) && (((((int)threadIdx.x) * 12) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + ((((((int)threadIdx.x) * 12) % 63) / 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((7 <= (((((int)threadIdx.x) * 12) + 1) % 63)) && ((((((int)threadIdx.x) * 12) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 1) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 1) % 7)) - 8)] : [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((7 < (((((int)threadIdx.x) * 12) + 2) % 63)) && ((((((int)threadIdx.x) * 12) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 2) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 2) % 7)) - 8)] : [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((7 < (((((int)threadIdx.x) * 12) + 3) % 63)) && ((((((int)threadIdx.x) * 12) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 3) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 3) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((7 <= (((((int)threadIdx.x) * 12) + 4) % 63)) && ((((((int)threadIdx.x) * 12) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 4) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 4) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((7 < (((((int)threadIdx.x) * 12) + 5) % 63)) && ((((((int)threadIdx.x) * 12) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 5) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 5) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((7 < (((((int)threadIdx.x) * 12) + 6) % 63)) && ((((((int)threadIdx.x) * 12) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 6) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 6) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 12) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) / 7) + 1) % 9) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.00000 [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((7 < (((((int)threadIdx.x) * 12) + 8) % 63)) && ((((((int)threadIdx.x) * 12) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 8) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 1) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((7 < (((((int)threadIdx.x) * 12) + 9) % 63)) && ((((((int)threadIdx.x) * 12) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 9) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 2) % 7)) - [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((7 <= (((((int)threadIdx.x) * 12) + 10) % 63)) && ((((((int)threadIdx.x) * 12) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 10) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 3) % 7 [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((7 < (((((int)threadIdx.x) * 12) + 11) % 63)) && ((((((int)threadIdx.x) * 12) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 11) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 4) % 7) [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 4) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 4) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 20) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 164) {
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 28) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 768)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 816)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 864)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 912)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 771)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 819)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 867)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 147)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 915)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 774)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 822)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 870)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 150)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 918)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 777)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 825)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 873)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 153)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 921)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 780)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 828)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 876)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 156)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 924)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 783)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 831)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 879)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 159)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 927)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 786)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 834)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 882)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 162)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 930)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 789)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 837)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 885)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 165)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 933)]));
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 2) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 2) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 4) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 4) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 27) * 49)) + ((((((int)threadIdx.x) + 4) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 6) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 6) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 27) * 49)) + ((((((int)threadIdx.x) + 6) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 8) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 8) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 12) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 12) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 27) * 49)) + ((((((int)threadIdx.x) + 12) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] [...]
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 14) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 27) * 49)) + ((((((int)threadIdx.x) + 14) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8) [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2408) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2520) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2632) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 3080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3304) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3864)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3864) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3976) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4200) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4424) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2304)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2305)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2306)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2307)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2308)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2309)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2310)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2311)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2312)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2313)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2314)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2315)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2316)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2317)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2318)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2319)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2320)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2321)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2322)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2323)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2324)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2325)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2326)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2327)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2328)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2329)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2330)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2331)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2332)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2333)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2334)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2335)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2336)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2337)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2338)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2339)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2448)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2449)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2450)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2451)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2452)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2453)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2454)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2455)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2456)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 153)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2457)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 154)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2458)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 155)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2459)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 156)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2460)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 157)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2461)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 158)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2462)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 159)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2463)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 160)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2464)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 161)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2465)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 162)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2466)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 163)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2467)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 164)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2468)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 165)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2469)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 166)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2470)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 167)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2471)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 168)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2472)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 169)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2473)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 170)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2474)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 171)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2475)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 172)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2476)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 173)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2477)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 174)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2478)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 175)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2479)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 176)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2480)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 177)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2481)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 178)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2482)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 179)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2483)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
@@ -758,7 +1082,7 @@ 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 31.898 seconds)
+ **Total running time of the script:** ( 5 minutes 30.318 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 a18d7e601c..5421b5a16a 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)
- 7.8485 7.8484 7.8516 7.8454 0.0025
+ 7.8549 7.8561 7.8574 7.8511 0.0027
@@ -669,11 +669,6 @@ Other Tips
with :any:`auto_scheduler.RPCRunner`.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.664 seconds)
-
-
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
.. only:: html
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 3a97629146..04c698fc68 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)
- 755.9013 755.2582 757.2791 755.1665 0.9750
+ 753.8896 753.9109 754.0111 753.7469 0.1089
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.389 seconds)
+ **Total running time of the script:** ( 1 minutes 30.005 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 df483ba956..4228c5c2c6 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
@@ -386,27 +386,76 @@ 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, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*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, 32) {
- 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.inner*16) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.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 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*1024) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_21]*16) + cse_var_20)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (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))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 8)] = max((compute_4[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -462,7 +511,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.684 ms
+ Execution time of this operator: 3.780 ms
diff --git a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
index 5a55d2675f..e390e16f68 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:38.701** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.256** 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``) | 00:38.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.220 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 3a14c6ae1f..a83fe0769b 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,7 +265,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 533.35/533.35 result: MeasureResult(costs=(0.0004340539370860928,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.865936279296875, timestamp=1669642833.1997926) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3980720
+ No: 2 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -387,8 +388,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7737275
- 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, 512, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6320389
+ No: 3 GFLOPS: 23.83/533.35 result: MeasureResult(costs=(0.009714981727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.378678560256958, timestamp=1669642834.809128) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2973483
+ No: 4 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -510,8 +512,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3204802
- 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, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3280842
+ No: 5 GFLOPS: 18.27/533.35 result: MeasureResult(costs=(0.012670737333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4939541816711426, timestamp=1669642837.4081566) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5686619
+ No: 6 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -633,8 +636,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904150
- 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, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7638365
+ No: 7 GFLOPS: 84.78/533.35 result: MeasureResult(costs=(0.002730521945945946,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1698782444000244, timestamp=1669642838.9629657) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1008743
+ No: 8 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -756,8 +760,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7760839
- 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, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5225123
+ No: 9 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -879,9 +883,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620741
- No: 6 GFLOPS: 2.34/2.34 result: MeasureResult(costs=(0.09906224799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9588117599487305, timestamp=1669636977.7683833) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746338
- No: 7 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3827463
+ No: 10 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,8 +1006,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7432442
- No: 8 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6214249
+ No: 11 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,8 +1129,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4755383
- No: 9 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6459244
+ No: 12 GFLOPS: 457.18/533.35 result: MeasureResult(costs=(0.000506372243801653,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8325767517089844, timestamp=1669642842.0127907) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7633626
+ No: 13 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,8 +1253,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6662910
- No: 10 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 2]), ('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, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,576260
+ No: 14 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2041350
+ No: 15 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1372,8 +1394,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4233511
- No: 11 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5286795
+ No: 16 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1495,8 +1517,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8818349
- No: 12 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3374969
+ No: 17 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1618,8 +1640,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2681356
- No: 13 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2996293
+ No: 18 GFLOPS: 1.93/533.35 result: MeasureResult(costs=(0.12008470149999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4473347663879395, timestamp=1669642855.9362817) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3690672
+ No: 19 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1741,746 +1764,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5610233
- No: 14 GFLOPS: 7.47/7.47 result: MeasureResult(costs=(0.03098774325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.33935809135437, timestamp=1669636981.5201042) [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
- No: 15 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127872
- No: 16 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,494076
- No: 17 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10002729
- No: 18 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,911536
- No: 19 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9628256
- No: 20 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9846618
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6501970
+ No: 20 GFLOPS: 56.60/533.35 result: MeasureResult(costs=(0.0040902542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2511205673217773, timestamp=1669642856.5935314) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6123095
@@ -2535,9 +1820,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
+ [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3980720
Finish loading 20 records
- Time cost of this operator: 0.025340
+ Time cost of this operator: 0.000761
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 ee57eac1b5..680e217f2d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.709 (1, 2, 10, 10, 3) 2 1 [312.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.982 (1, 6, 10, 10) 1 1 [3.11]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.31 (1, 1, 10, 10, 3) 1 1 [0.982]
- Total_time - 316.892 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.2 98.721 (1, 2, 10, 10, 3) 2 1 [311.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.041 0.965 (1, 6, 10, 10) 1 1 [3.041]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.315 (1, 1, 10, 10, 3) 1 1 [0.992]
+ Total_time - 315.233 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.51 (1, 6, 10, 10, 1) 2 1 [103.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.687 (1, 6, 10, 10) 1 1 [1.782]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.803 (1, 3, 10, 10, 1) 1 1 [0.848]
- Total_time - 105.63 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.2 97.399 (1, 6, 10, 10, 1) 2 1 [102.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.687 (1, 6, 10, 10) 1 1 [1.77]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 0.914 (1, 1, 10, 10, 3) 1 1 [0.959]
+ Total_time - 104.929 - - - - -
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 0a08803f44..69bcbc7b37 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, 73.8MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 94.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.758 seconds)
+ **Total running time of the script:** ( 1 minutes 0.658 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 8785b7aad3..ddf02225ea 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/tmpjto5t1tf/images/random'
+ '/tmp/tmp5cpedw3l/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
: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/tmpjto5t1tf/images/target contains 8144 images
- /tmp/tmpjto5t1tf/images/random contains 5000 images
+ /tmp/tmp5cpedw3l/images/target contains 8144 images
+ /tmp/tmp5cpedw3l/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: 0.2341 - accuracy: 0.9201 - val_loss: 0.1064 - val_accuracy: 0.9653 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.2099 - accuracy: 0.9303 - val_loss: 0.1267 - val_accuracy: 0.9569 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1084 - accuracy: 0.9589 - val_loss: 0.1079 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0911 - accuracy: 0.9669 - val_loss: 0.2151 - val_accuracy: 0.9320 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0589 - accuracy: 0.9781 - val_loss: 0.0970 - val_accuracy: 0.9675 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0650 - accuracy: 0.9761 - val_loss: 0.1129 - val_accuracy: 0.9619 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7fc15ed50990>
+ <keras.callbacks.History object at 0x7feaeb80a050>
@@ -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:** ( 3 minutes 59.372 seconds)
+ **Total running time of the script:** ( 4 minutes 26.455 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 5e147b6d1f..835a1b15a0 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
=================
-**06:07.586** total execution time for **how_to_work_with_microtvm** files:
+**06:27.381** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 03:59.372 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:26.455 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:00.658 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.246 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.351 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.248 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.666 | 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 d1feff1f01..e56aca3ed9 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
=================
-**00:44.803** total execution time for **how_to_work_with_relay** files:
+**00:43.333** 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``) | 00:32.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.854 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.358 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.993 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:02.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.479 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index d7a5f3a461..854779d3bc 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 0x7fc1d85d5710>
+ <function my_cuda_math_rule at 0x7feae967c950>
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 9e8a351d9c..63d779e797 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:06.367** total execution time for **how_to_work_with_schedules** files:
+**00:07.916** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.826 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.491 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.201 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.567 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.550 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.018 | 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 5a9b6a7dd1..c08f570076 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/tmpq6rzp0lm/input0.cc'\nsource_filename = \"/tmp/tmpq6rzp0lm/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/tmp8176sa_w/input0.cc'\nsource_filename = \"/tmp/tmp8176sa_w/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 2729aa314c..61a4ab2e73 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:27.294** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.771** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.287 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.765 | 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 229079fc64..682ed2c711 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 30.43s!
+ resnet18_v1 inference graph built in 28.41s!
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 0384c3a108..a5c91faefa 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.39s!
+ yolov3-tiny inference graph built in 19.14s!
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 4ce6115ab1..4dfea25f42 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
=================
-**01:42.511** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.961** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.033 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.638 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.478 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.323 | 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 e4e81aeb2c..14969b8ff1 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
=================
-**00:03.166** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.174** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.709 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.735 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.456 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.439 | 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 e3a691b31d..71017c0535 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
=================
-**00:00.804** total execution time for **topic_vta_tutorials** files:
+**00:00.770** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.409 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.374 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.360 | 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 6962ab7f21..1327271375 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
- .T
-
@@ -332,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.375 ms
+ Execution time of this operator: 93.712 ms
@@ -450,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.969 seconds)
+ **Total running time of the script:** ( 1 minutes 21.969 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 6fd77423c9..744f886c38 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: 2.57/2.57 result: MeasureResult(costs=(0.10462719839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8281018733978271, timestamp=1669635554.1587062) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 2 GFLOPS: 12.99/12.99 result: MeasureResult(costs=(0.020664898600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5226318836212158, timestamp=1669635554.699581) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
- No: 3 GFLOPS: 10.19/12.99 result: MeasureResult(costs=(0.026348740400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8465473651885986, timestamp=1669635556.0615485) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
- No: 4 GFLOPS: 8.70/12.99 result: MeasureResult(costs=(0.030860226799999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8248922824859619, timestamp=1669635557.4794347) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
- No: 5 GFLOPS: 4.07/12.99 result: MeasureResult(costs=(0.06600606540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2161962985992432, timestamp=1669635558.8116148) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
- No: 6 GFLOPS: 2.43/12.99 result: MeasureResult(costs=(0.1103962426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.913161277770996, timestamp=1669635561.514688) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
- No: 7 GFLOPS: 0.90/12.99 result: MeasureResult(costs=(0.2998592632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942259311676025, timestamp=1669635566.4768138) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
- No: 8 GFLOPS: 1.91/12.99 result: MeasureResult(costs=(0.1405420992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.429777145385742, timestamp=1669635568.932175) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 9 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.018724787799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.47362279891967773, timestamp=1669635569.5193236) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 10 GFLOPS: 10.73/14.34 result: MeasureResult(costs=(0.0250093266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562950611114502, timestamp=1669635570.0888388) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
+ No: 1 GFLOPS: 1.54/1.54 result: MeasureResult(costs=(0.1737638714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.927121877670288, timestamp=1669641420.4367385) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 2 GFLOPS: 3.68/3.68 result: MeasureResult(costs=(0.0729572428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3492066860198975, timestamp=1669641421.8072093) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+ No: 3 GFLOPS: 9.97/9.97 result: MeasureResult(costs=(0.0269202026,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6164209842681885, timestamp=1669641423.1304102) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+ No: 4 GFLOPS: 0.51/9.97 result: MeasureResult(costs=(0.5307152626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.6624596118927, timestamp=1669641432.5372407) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 5 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.021017550399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49544835090637207, timestamp=1669641433.1491547) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+ No: 6 GFLOPS: 2.69/12.77 result: MeasureResult(costs=(0.09979856740000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7374615669250488, timestamp=1669641434.905883) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 7 GFLOPS: 0.90/12.77 result: MeasureResult(costs=(0.2995993068,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942751407623291, timestamp=1669641440.6305485) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+ No: 8 GFLOPS: 0.83/12.77 result: MeasureResult(costs=(0.321642802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.309566259384155, timestamp=1669641445.9727027) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 9 GFLOPS: 11.86/12.77 result: MeasureResult(costs=(0.0226419244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5397887229919434, timestamp=1669641446.6248975) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 10 GFLOPS: 1.18/12.77 result: MeasureResult(costs=(0.22772719600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.754491090774536, timestamp=1669641450.4300933) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 74f2eda5ed..4398510e93 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': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
+ {'mean': 523.03492, 'median': 522.3141131500029, 'std': 3.237501830193314}
@@ -554,31 +554,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.35/ 17.91 GFLOPS | Progress: (4/20) | 7.20 s
[Task 1/25] Current/Best: 12.44/ 17.91 GFLOPS | Progress: (8/20) | 11.21 s
[Task 1/25] Current/Best: 11.17/ 17.91 GFLOPS | Progress: (12/20) | 13.91 s
[Task 1/25] Current/Best: 7.15/ 21.25 GFLOPS | Progress: (16/20) | 15.77 s
[Task 1/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 17.76 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 7.60/ 15.88 GFLOPS | Progress: (4/20) | 2.84 s
[Task 2/25] Current/Best: 6.13/ 15.88 GFLOPS | Progress: (8/20) | 4.18 s
[Task 2/25] Current/Best: 21.69/ 21.69 GFLOPS | Progress: (12/20) | 5.27 s
[Task 2/25] Current/Best: 9.51/ 21.69 GFLOPS | Progress: (16/20) | 6.84 s
[Task 2/25] Current/Best: 16.65/ 21.69 GFLOPS | Progress: (20/20) | 8.55 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.57/ 15.33 GFLOPS | Progress: (4/20) | 3.77 s
[Task 3/25] Current/Best: 11.61/ 15.33 GFLOPS | Progress: (8/20) | 6.09 s
[Task 3/25] Current/Best: 12.42/ 19.62 GFLOPS | Progress: (12/20) | 8.00 s
[Task 3/25] Current/Best: 17.84/ 19.62 GFLOPS | Progress: (16/20) | 10.12 s
[Task 3/25] Current/Best: 10.16/ 19.86 GFLOPS | Progress: (20/20) | 11.98 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 3.42 s
[Task 4/25] Current/Best: 6.16/ 17.31 GFLOPS | Progress: (8/20) | 5.18 s
[Task 4/25] Current/Best: 9.28/ 22.19 GFLOPS | Progress: (12/20) | 9.94 s
[Task 4/25] Current/Best: 6.47/ 22.19 GFLOPS | Progress: (16/20) | 11.93 s
[Task 4/25] Current/Best: 19.38/ 22.19 GFLOPS | Progress: (20/20) | 13.25 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 3.56 s
[Task 5/25] Current/Best: 6.00/ 12.20 GFLOPS | Progress: (8/20) | 5.54 s
[Task 5/25] Current/Best: 3.08/ 20.88 GFLOPS | Progress: (12/20) | 7.43 s
[Task 5/25] Current/Best: 8.04/ 22.55 GFLOPS | Progress: (16/20) | 9.54 s
[Task 5/25] Current/Best: 17.91/ 22.55 GFLOPS | Progress: (20/20) | 11.11 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/20) | 4.83 s
[Task 6/25] Current/Best: 10.60/ 18.77 GFLOPS | Progress: (8/20) | 9.56 s
[Task 6/25] Current/Best: 12.17/ 18.77 GFLOPS | Progress: (12/20) | 11.66 s
[Task 6/25] Current/Best: 8.38/ 18.77 GFLOPS | Progress: (16/20) | 14.00 s
[Task 6/25] Current/Best: 9.76/ 18.77 GFLOPS | Progress: (20/20) | 19.03 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.25/ 15.25 GFLOPS | Progress: (4/20) | 4.15 s
[Task 7/25] Current/Best: 12.06/ 15.25 GFLOPS | Progress: (8/20) | 6.06 s
[Task 7/25] Current/Best: 15.13/ 15.75 GFLOPS | Progress: (12/20) | 8.50 s
[Task 7/25] Current/Best: 7.11/ 15.84 GFLOPS | Progress: (16/20) | 11.07 s
[Task 7/25] Current/Best: 15.83/ 15.84 GFLOPS | Progress: (20/20) | 13.12 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.39/ 12.87 GFLOPS | Progress: (4/20) | 5.76 s
[Task 8/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (8/20) | 8.17 s
[Task 8/25] Current/Best: 11.20/ 20.71 GFLOPS | Progress: (12/20) | 16.64 s
[Task 8/25] Current/Best: 12.92/ 20.71 GFLOPS | Progress: (16/20) | 19.86 s
[Task 8/25] Current/Best: 4.14/ 20.71 GFLOPS | Progress: (20/20) | 22.65 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 22.53/ 22.53 GFLOPS | Progress: (4/20) | 4.80 s
[Task 9/25] Current/Best: 12.86/ 22.53 GFLOPS | Progress: (8/20) | 6.48 s
[Task 9/25] Current/Best: 16.12/ 22.53 GFLOPS | Progress: (12/20) | 10.27 s
[Task 9/25] Current/Best: 14.03/ 22.53 GFLOPS | Progress: (16/20) | 13.29 s
[Task 9/25] Current/Best: 14.10/ 22.53 GFLOPS | Progress: (20/20) | 17.00 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 3.60 s
[Task 10/25] Current/Best: 12.30/ 18.22 GFLOPS | Progress: (8/20) | 4.96 s
[Task 10/25] Current/Best: 11.81/ 20.44 GFLOPS | Progress: (12/20) | 7.80 s
[Task 10/25] Current/Best: 13.28/ 20.44 GFLOPS | Progress: (16/20) | 10.40 s
[Task 10/25] Current/Best: 18.40/ 20.44 GFLOPS | Progress: (20/20) | 12.83 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.02/ 20.82 GFLOPS | Progress: (4/20) | 4.99 s
[Task 11/25] Current/Best: 13.52/ 21.49 GFLOPS | Progress: (8/20) | 8.20 s
[Task 11/25] Current/Best: 11.47/ 21.49 GFLOPS | Progress: (12/20) | 10.32 s
[Task 11/25] Current/Best: 17.80/ 21.49 GFLOPS | Progress: (16/20) | 12.25 s
[Task 11/25] Current/Best: 6.15/ 22.38 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.13/ 13.79 GFLOPS | Progress: (4/20) | 3.64 s
[Task 12/25] Current/Best: 17.47/ 18.18 GFLOPS | Progress: (8/20) | 5.29 s
[Task 12/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 7.44 s
[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (16/20) | 9.65 s
[Task 12/25] Current/Best: 14.82/ 19.04 GFLOPS | Progress: (20/20) | 11.55 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.00/ 12.99 GFLOPS | Progress: (4/20) | 4.78 s
[Task 13/25] Current/Best: 15.11/ 16.32 GFLOPS | Progress: (8/20) | 7.61 s
[Task 13/25] Current/Best: 11.00/ 16.32 GFLOPS | Progress: (12/20) | 12.11 s
[Task 13/25] Current/Best: 8.41/ 18.24 GFLOPS | Progress: (16/20) | 16.97 s
[Task 13/25] Current/Best: 13.37/ 18.24 GFLOPS | Progress: (20/20) | 20.01 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 10.44/ 14.69 GFLOPS | Progress: (4/20) | 4.47 s
[Task 14/25] Current/Best: 14.24/ 14.69 GFLOPS | Progress: (8/20) | 9.95 s
[Task 14/25] Current/Best: 12.34/ 17.20 GFLOPS | Progress: (12/20) | 12.11 s
[Task 14/25] Current/Best: 18.32/ 18.97 GFLOPS | Progress: (16/20) | 14.80 s
[Task 14/25] Current/Best: 3.03/ 18.97 GFLOPS | Progress: (20/20) | 17.62 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 12.24/ 15.99 GFLOPS | Progress: (4/20) | 7.54 s
[Task 15/25] Current/Best: 12.69/ 18.08 GFLOPS | Progress: (8/20) | 9.63 s
[Task 15/25] Current/Best: 3.12/ 18.08 GFLOPS | Progress: (12/20) | 11.82 s Done.
-
[Task 15/25] Current/Best: 13.44/ 18.08 GFLOPS | Progress: (16/20) | 14.49 s
[Task 15/25] Current/Best: 15.82/ 18.08 GFLOPS | Progress: (20/20) | 16.39 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.27/ 21.01 GFLOPS | Progress: (4/20) | 3.27 s
[Task 16/25] Current/Best: 11.84/ 21.01 GFLOPS | Progress: (8/20) | 5.21 s
[Task 16/25] Current/Best: 13.75/ 21.66 GFLOPS | Progress: (12/20) | 6.83 s
[Task 16/25] Current/Best: 12.15/ 22.09 GFLOPS | Progress: (16/20) | 9.27 s
[Task 16/25] Current/Best: 12.27/ 22.09 GFLOPS | Progress: (20/20) | 11.17 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.03/ 22.98 GFLOPS | Progress: (4/20) | 3.54 s
[Task 17/25] Current/Best: 9.48/ 22.98 GFLOPS | Progress: (8/20) | 6.35 s
[Task 17/25] Current/Best: 10.16/ 22.98 GFLOPS | Progress: (12/20) | 8.84 s
[Task 17/25] Current/Best: 11.86/ 22.98 GFLOPS | Progress: (16/20) | 11.73 s
[Task 17/25] Current/Best: 5.20/ 22.98 GFLOPS | Progress: (20/20) | 14.23 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 14.35/ 14.35 GFLOPS | Progress: (4/20) | 3.93 s
[Task 18/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (8/20) | 5.40 s
[Task 18/25] Current/Best: 15.69/ 22.72 GFLOPS | Progress: (12/20) | 9.31 s
[Task 18/25] Current/Best: 13.96/ 22.72 GFLOPS | Progress: (16/20) | 11.42 s
[Task 18/25] Current/Best: 17.39/ 22.72 GFLOPS | Progress: (20/20) | 14.88 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.56/ 14.25 GFLOPS | Progress: (4/20) | 5.04 s
[Task 19/25] Current/Best: 21.33/ 21.97 GFLOPS | Progress: (8/20) | 7.31 s
[Task 19/25] Current/Best: 8.39/ 21.97 GFLOPS | Progress: (12/20) | 12.43 s
[Task 19/25] Current/Best: 10.35/ 21.97 GFLOPS | Progress: (16/20) | 17.63 s
[Task 19/25] Current/Best: 17.07/ 21.97 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: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 3.32 s
[Task 20/25] Current/Best: 11.65/ 18.84 GFLOPS | Progress: (8/20) | 6.55 s
[Task 20/25] Current/Best: 16.43/ 18.84 GFLOPS | Progress: (12/20) | 9.11 s
[Task 20/25] Current/Best: 8.84/ 18.84 GFLOPS | Progress: (16/20) | 12.91 s
[Task 20/25] Current/Best: 16.06/ 18.84 GFLOPS | Progress: (20/20) | 14.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 12.44/ 17.26 GFLOPS | Progress: (4/20) | 4.37 s
[Task 21/25] Current/Best: 10.99/ 17.26 GFLOPS | Progress: (8/20) | 6.21 s Done.
-
[Task 21/25] Current/Best: 7.57/ 17.26 GFLOPS | Progress: (12/20) | 8.48 s
[Task 21/25] Current/Best: 17.11/ 17.26 GFLOPS | Progress: (16/20) | 11.26 s
[Task 21/25] Current/Best: 14.08/ 17.26 GFLOPS | Progress: (20/20) | 15.30 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.55/ 13.88 GFLOPS | Progress: (4/20) | 4.35 s
[Task 22/25] Current/Best: 4.52/ 16.29 GFLOPS | Progress: (8/20) | 6.07 s
[Task 22/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.43 s
[Task 22/25] Current/Best: 7.08/ 19.56 GFLOPS | Progress: (16/20) | 9.63 s
[Task 22/25] Current/Best: 18.66/ 19.56 GFLOPS | Progress: (20/20) | 11.32 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 4.42/ 19.23 GFLOPS | Progress: (4/20) | 3.77 s
[Task 23/25] Current/Best: 11.96/ 20.75 GFLOPS | Progress: (8/20) | 5.70 s
[Task 23/25] Current/Best: 17.04/ 20.75 GFLOPS | Progress: (12/20) | 8.37 s
[Task 23/25] Current/Best: 20.41/ 20.75 GFLOPS | Progress: (16/20) | 11.13 s
[Task 23/25] Current/Best: 18.96/ 20.75 GFLOPS | Progress: (20/20) | 16.82 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.77/ 5.76 GFLOPS | Progress: (4/20) | 4.72 s
[Task 24/25] Current/Best: 1.45/ 7.07 GFLOPS | Progress: (8/20) | 15.22 s
[Task 24/25] Current/Best: 2.59/ 7.18 GFLOPS | Progress: (12/20) | 25.98 s
[Task 24/25] Current/Best: 2.80/ 7.18 GFLOPS | Progress: (16/20) | 37.65 s
[Task 24/25] Current/Best: 4.45/ 7.18 GFLOPS | Progress: (20/20) | 49.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 25/25] Current/Best: 3.02/ 8.42 GFLOPS | Progress: (4/20) | 4.89 s
[Task 25/25] Current/Best: 1.54/ 8.42 GFLOPS | Progress: (8/20) | 15.65 s
[Task 25/25] Current/Best: 3.00/ 9.40 GFLOPS | Progress: (12/20) | 19.98 s
[Task 25/25] Current/Best: 3.82/ 9.40 GFLOPS | Progress: (16/20) | 30.71 s
[Task 25/25] Current/Best: 5.73/ 9.40 GFLOPS | Progress: (20/20) | 34.15 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 11.85/ 12.47 GFLOPS | Progress: (4/20) | 8.00 s
[Task 1/25] Current/Best: 4.10/ 14.69 GFLOPS | Progress: (8/20) | 12.27 s
[Task 1/25] Current/Best: 1.92/ 14.69 GFLOPS | Progress: (12/20) | 17.03 s
[Task 1/25] Current/Best: 6.73/ 14.69 GFLOPS | Progress: (16/20) | 19.94 s
[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (20/20) | 22.55 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (4/20) | 3.02 s
[Task 2/25] Current/Best: 8.09/ 20.59 GFLOPS | Progress: (8/20) | 4.66 s
[Task 2/25] Current/Best: 12.10/ 20.59 GFLOPS | Progress: (12/20) | 6.07 s
[Task 2/25] Current/Best: 4.25/ 20.59 GFLOPS | Progress: (16/20) | 7.39 s
[Task 2/25] Current/Best: 6.51/ 20.59 GFLOPS | Progress: (20/20) | 8.54 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.28/ 22.23 GFLOPS | Progress: (4/20) | 4.01 s
[Task 3/25] Current/Best: 7.57/ 22.23 GFLOPS | Progress: (8/20) | 6.06 s
[Task 3/25] Current/Best: 15.75/ 22.23 GFLOPS | Progress: (12/20) | 9.29 s
[Task 3/25] Current/Best: 13.24/ 22.23 GFLOPS | Progress: (16/20) | 11.24 s
[Task 3/25] Current/Best: 7.48/ 22.23 GFLOPS | Progress: (20/20) | 13.16 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 10.45/ 12.61 GFLOPS | Progress: (4/20) | 5.87 s
[Task 4/25] Current/Best: 9.03/ 13.81 GFLOPS | Progress: (8/20) | 8.16 s
[Task 4/25] Current/Best: 13.94/ 18.40 GFLOPS | Progress: (12/20) | 14.57 s
[Task 4/25] Current/Best: 12.97/ 18.40 GFLOPS | Progress: (16/20) | 17.13 s
[Task 4/25] Current/Best: 5.02/ 18.60 GFLOPS | Progress: (20/20) | 21.66 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (4/20) | 3.33 s
[Task 5/25] Current/Best: 17.61/ 22.23 GFLOPS | Progress: (8/20) | 5.57 s
[Task 5/25] Current/Best: 13.80/ 22.23 GFLOPS | Progress: (12/20) | 8.17 s
[Task 5/25] Current/Best: 16.35/ 22.23 GFLOPS | Progress: (16/20) | 9.93 s
[Task 5/25] Current/Best: 3.06/ 22.23 GFLOPS | Progress: (20/20) | 11.54 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 17.80/ 17.80 GFLOPS | Progress: (4/20) | 3.74 s
[Task 6/25] Current/Best: 15.35/ 18.20 GFLOPS | Progress: (8/20) | 5.57 s
[Task 6/25] Current/Best: 5.53/ 18.20 GFLOPS | Progress: (12/20) | 7.87 s
[Task 6/25] Current/Best: 9.39/ 18.20 GFLOPS | Progress: (16/20) | 14.36 s
[Task 6/25] Current/Best: 16.52/ 18.20 GFLOPS | Progress: (20/20) | 16.48 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.00/ 15.54 GFLOPS | Progress: (4/20) | 3.79 s
[Task 7/25] Current/Best: 8.05/ 15.54 GFLOPS | Progress: (8/20) | 6.38 s
[Task 7/25] Current/Best: 7.41/ 16.17 GFLOPS | Progress: (12/20) | 9.63 s
[Task 7/25] Current/Best: 9.60/ 16.17 GFLOPS | Progress: (16/20) | 11.83 s
[Task 7/25] Current/Best: 8.90/ 16.17 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: 4.86/ 14.69 GFLOPS | Progress: (4/20) | 6.08 s
[Task 8/25] Current/Best: 12.04/ 14.69 GFLOPS | Progress: (8/20) | 14.67 s
[Task 8/25] Current/Best: 15.05/ 15.05 GFLOPS | Progress: (12/20) | 20.23 s
[Task 8/25] Current/Best: 9.25/ 19.37 GFLOPS | Progress: (16/20) | 31.39 s
[Task 8/25] Current/Best: 11.16/ 19.37 GFLOPS | Progress: (20/20) | 37.87 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 9.58/ 17.83 GFLOPS | Progress: (4/20) | 12.35 s
[Task 9/25] Current/Best: 22.58/ 22.58 GFLOPS | Progress: (8/20) | 16.57 s
[Task 9/25] Current/Best: 5.85/ 22.58 GFLOPS | Progress: (12/20) | 18.12 s
[Task 9/25] Current/Best: 5.15/ 22.58 GFLOPS | Progress: (16/20) | 23.00 s
[Task 9/25] Current/Best: 11.39/ 22.58 GFLOPS | Progress: (20/20) | 27.66 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.50/ 16.31 GFLOPS | Progress: (4/20) | 3.36 s
[Task 10/25] Current/Best: 9.07/ 16.31 GFLOPS | Progress: (8/20) | 5.77 s
[Task 10/25] Current/Best: 10.91/ 19.02 GFLOPS | Progress: (12/20) | 7.40 s
[Task 10/25] Current/Best: 11.29/ 19.02 GFLOPS | Progress: (16/20) | 8.97 s
[Task 10/25] Current/Best: 13.33/ 19.02 GFLOPS | Progress: (20/20
) | 10.62 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 21.45/ 21.45 GFLOPS | Progress: (4/20) | 3.45 s
[Task 11/25] Current/Best: 20.11/ 21.45 GFLOPS | Progress: (8/20) | 5.68 s
[Task 11/25] Current/Best: 9.12/ 21.45 GFLOPS | Progress: (12/20) | 8.72 s
[Task 11/25] Current/Best: 19.55/ 21.45 GFLOPS | Progress: (16/20) | 10.90 s
[Task 11/25] Current/Best: 16.52/ 21.45 GFLOPS | Progress: (20/20) | 12.68 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (4/20) | 4.60 s
[Task 12/25] Current/Best: 9.71/ 18.08 GFLOPS | Progress: (8/20) | 8.93 s
[Task 12/25] Current/Best: 4.50/ 18.08 GFLOPS | Progress: (12/20) | 11.46 s
[Task 12/25] Current/Best: 4.25/ 18.08 GFLOPS | Progress: (16/20) | 16.11 s
[Task 12/25] Current/Best: 3.37/ 18.08 GFLOPS | Progress: (20/20) | 20.50 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.80/ 15.36 GFLOPS | Progress: (4/20) | 6.30 s
[Task 13/25] Current/Best: 10.10/ 16.54 GFLOPS | Progress: (8/20) | 9.30 s
[Task 13/25] Current/Best: 18.60/ 20.26 GFLOPS | Progress: (12/20) | 11.31 s
[Task 13/25] Current/Best: 19.94/ 20.26 GFLOPS | Progress: (16/20) | 13.92 s
[Task 13/25] Current/Best: 16.00/ 20.26 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.68/ 13.14 GFLOPS | Progress: (4/20) | 3.71 s
[Task 14/25] Current/Best: 13.72/ 13.72 GFLOPS | Progress: (8/20) | 6.64 s
[Task 14/25] Current/Best: 4.39/ 17.35 GFLOPS | Progress: (12/20) | 9.33 s Done.
+
[Task 14/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (16/20) | 11.49 s
[Task 14/25] Current/Best: 7.84/ 18.95 GFLOPS | Progress: (20/20) | 19.76 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 6.82/ 20.45 GFLOPS | Progress: (4/20) | 3.27 s
[Task 15/25] Current/Best: 6.15/ 20.45 GFLOPS | Progress: (8/20) | 4.83 s
[Task 15/25] Current/Best: 10.31/ 20.45 GFLOPS | Progress: (12/20) | 6.23 s
[Task 15/25] Current/Best: 15.45/ 20.45 GFLOPS | Progress: (16/20) | 11.40 s
[Task 15/25] Current/Best: 18.10/ 22.62 GFLOPS | Progress: (20/20) | 12.57 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.26/ 18.30 GFLOPS | Progress: (4/20) | 3.57 s
[Task 16/25] Current/Best: 12.28/ 18.30 GFLOPS | Progress: (8/20) | 6.36 s
[Task 16/25] Current/Best: 9.61/ 18.30 GFLOPS | Progress: (12/20) | 7.62 s
[Task 16/25] Current/Best: 14.35/ 19.00 GFLOPS | Progress: (16/20) | 9.96 s
[Task 16/25] Current/Best: 17.91/ 19.00 GFLOPS | Progress: (20/20) | 11.48 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.57/ 16.66 GFLOPS | Progress: (4/20) | 4.42 s
[Task 17/25] Current/Best: 12.17/ 20.15 GFLOPS | Progress: (8/20) | 7.57 s
[Task 17/25] Current/Best: 6.46/ 23.00 GFLOPS | Progress: (12/20) | 10.35 s
[Task 17/25] Current/Best: 10.90/ 23.00 GFLOPS | Progress: (16/20) | 13.76 s
[Task 17/25] Current/Best: 11.50/ 23.00 GFLOPS | Progress: (20/20) | 15.90 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.83/ 14.67 GFLOPS | Progress: (4/20) | 4.14 s
[Task 18/25] Current/Best: 5.91/ 18.49 GFLOPS | Progress: (8/20) | 6.47 s
[Task 18/25] Current/Best: 15.72/ 18.49 GFLOPS | Progress: (12/20) | 8.43 s
[Task 18/25] Current/Best: 2.88/ 18.49 GFLOPS | Progress: (16/20) | 11.18 s
[Task 18/25] Current/Best: 14.97/ 18.49 GFLOPS | Progress: (20/20) | 13.00 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 3.09/ 14.32 GFLOPS | Progress: (4/20) | 9.42 s
[Task 19/25] Current/Best: 4.60/ 18.84 GFLOPS | Progress: (8/20) | 12.78 s
[Task 19/25] Current/Best: 10.55/ 18.84 GFLOPS | Progress: (12/20) | 15.76 s
[Task 19/25] Current/Best: 18.17/ 22.42 GFLOPS | Progress: (16/20) | 19.24 s
[Task 19/25] Current/Best: 9.33/ 22.42 GFLOPS | Progress: (20/20) | 21.84 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.70/ 17.45 GFLOPS | Progress: (4/20) | 3.45 s
[Task 20/25] Current/Best: 18.68/ 18.68 GFLOPS | Progress: (8/20) | 6.63 s
[Task 20/25] Current/Best: 15.93/ 18.68 GFLOPS | Progress: (12/20) | 10.95 s
[Task 20/25] Current/Best: 12.39/ 18.68 GFLOPS | Progress: (16/20) | 12.65 s
[Task 20/25] Current/Best: 12.92/ 18.68 GFLOPS | Progress: (20/20) | 14.78 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 8.75/ 19.24 GFLOPS | Progress: (4/20) | 3.41 s
[Task 21/25] Current/Best: 11.99/ 19.24 GFLOPS | Progress: (8/20) | 5.48 s
[Task 21/25] Current/Best: 22.57/ 22.57 GFLOPS | Progress: (12/20) | 7.08 s
[Task 21/25] Current/Best: 10.05/ 22.57 GFLOPS | Progress: (16/20) | 9.33 s Done.
+
[Task 21/25] Current/Best: 20.62/ 22.57 GFLOPS | Progress: (20/20) | 11.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (4/20) | 3.77 s
[Task 22/25] Current/Best: 5.27/ 19.13 GFLOPS | Progress: (8/20) | 5.61 s
[Task 22/25] Current/Best: 5.29/ 19.13 GFLOPS | Progress: (12/20) | 7.80 s
[Task 22/25] Current/Best: 15.64/ 19.13 GFLOPS | Progress: (16/20) | 9.03 s
[Task 22/25] Current/Best: 10.05/ 19.13 GFLOPS | Progress: (20/20) | 11.61 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 8.24/ 12.63 GFLOPS | Progress: (4/20) | 5.21 s
[Task 23/25] Current/Best: 15.02/ 20.29 GFLOPS | Progress: (8/20) | 7.34 s
[Task 23/25] Current/Best: 11.89/ 20.29 GFLOPS | Progress: (12/20) | 9.18 s
[Task 23/25] Current/Best: 11.10/ 20.29 GFLOPS | Progress: (16/20) | 14.44 s
[Task 23/25] Current/Best: 19.72/ 20.29 GFLOPS | Progress: (20/20) | 16.29 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.42/ 4.42 GFLOPS | Progress: (4/20) | 12.23 s
[Task 24/25] Current/Best: 9.90/ 9.90 GFLOPS | Progress: (8/20) | 13.91 s
[Task 24/25] Current/Best: 3.05/ 9.90 GFLOPS | Progress: (12/20) | 24.18 s
[Task 24/25] Current/Best: 3.03/ 9.90 GFLOPS | Progress: (16/20) | 36.06 s
[Task 24/25] Current/Best: 1.05/ 9.90 GFLOPS | Progress: (20/20) | 41.01 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 5.19/ 9.76 GFLOPS | Progress: (4/20) | 12.18 s
[Task 25/25] Current/Best: 8.19/ 9.76 GFLOPS | Progress: (8/20) | 14.49 s
[Task 25/25] Current/Best: 6.26/ 9.76 GFLOPS | Progress: (12/20) | 25.21 s
[Task 25/25] Current/Best: 7.23/ 9.76 GFLOPS | Progress: (16/20) | 35.89 s
[Task 25/25] Current/Best: 8.13/ 9.76 GFLOPS | Progress: (20/20) | 40.54 s
@@ -674,8 +673,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 430.0801938499967, 'median': 430.3779723499929, 'std': 2.429183228660658}
- unoptimized: {'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
+ optimized: {'mean': 414.7481115500045, 'median': 414.6498360999999, 'std': 1.4220691099397493}
+ unoptimized: {'mean': 523.03492, 'median': 522.3141131500029, 'std': 3.237501830193314}
@@ -756,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 43.197 seconds)
+ **Total running time of the script:** ( 11 minutes 13.730 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 5335169695..002def568d 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
- 1.271e-07 secs/op
+ 1.289e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 30d2480849..311451800c 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, 0xe8b6070)), stage(b, placeholder(b, 0x28a726d0)), 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, 0xc674890)), stage(b, placeholder(b, 0x128fcc50)), 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 47beedc667..981ea6253b 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
=================
-**14:17.904** total execution time for **tutorial** files:
+**14:47.663** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:43.197 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:13.730 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.969 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:21.969 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.362 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.301 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.192 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:36.706 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.967 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.560 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.254 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.440 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.777 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.772 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.175 | 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``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.003 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.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 0c32a022db..ce6f303025 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000007
+ naive: 0.000008
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000012
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.441079999352951e-06 1.0
- naive 6.696100000000001e-06 0.8998828127882337
- parallel 6.950399999999999e-06 0.9340579594097067
- vector 2.53151e-05 3.4020733552389317
+ numpy 7.225399999697402e-06 1.0
+ naive 7.883e-06 1.0910122623425884
+ parallel 1.1852e-05 1.6403244111739639
+ vector 2.5136799999999996e-05 3.478949262470274
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019053
+ Numpy running time: 0.018634
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.256209
+ none: 3.262746
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.314476
+ blocking: 0.305868
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.345962
+ vectorization: 0.345219
@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: 0.119863
+ loop permutation: 0.121067
@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: 0.110230
+ array packing: 0.108728
@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: 0.110165
+ block caching: 0.109726
@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: 0.146200
+ parallelization: 0.146219
@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 3.2562085157 1.0
- blocking 0.3144764388 0.09657748798448669
- vectorization 0.3459622566 0.10624696020906607
- loop permutation 0.1198630473 0.036810617846514834
- array packing 0.1102295502 0.033852116554735905
- block caching 0.11016505830000001 0.03383231072851531
- parallelization 0.14619960810000002 0.044898724204881245
+ none 3.2627462856999996 1.0
+ blocking 0.3058683523 0.09374567481405562
+ vectorization 0.3452194227 0.10580639512579679
+ loop permutation 0.12106699810000002 0.0371058573051217
+ array packing 0.10872769699999998 0.03332398154172543
+ block caching 0.10972645919999999 0.033630092441116345
+ parallelization 0.14621879570000001 0.04481463861926665
diff --git a/docs/commit_hash b/docs/commit_hash
index 195621ac50..25b944b557 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fc59b6dbdf445c09f70d20c8156cc940f696fdcd
+61144f9d8711aad15d2b1a19d983a4891e1be706
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 9630ce4116..a30eaccbfb 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 9.613 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.256 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 71f55e8c3e..2be8c78361 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 1s/step
+1/1 [==============================] - 1s 926ms/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 2705446ccc..c257f1afd9 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.zip97a78d84-9dd6-45c0-a1bb-ed12a2d188dd 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.zipcc40aad3-8dcc-404a-b9a3-f010e7144676 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 6182647b39..ca2ab46489 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,10 +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]
- 28%|##8 | 11.8M/41.5M [00:00<00:00, 124MB/s]
- 57%|#####6 | 23.6M/41.5M [00:00<00:00, 109MB/s]
- 82%|########2 | 34.1M/41.5M [00:00<00:00, 105MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 106MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 66.0MB/s]
+ 30%|### | 12.6M/41.5M [00:00<00:00, 61.4MB/s]
+ 45%|####4 | 18.5M/41.5M [00:00<00:00, 38.5MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 39.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 51.1MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 48.5MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 48.4MB/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 4e3cb71159..618b7d8312 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,11 +431,12 @@ 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]
- 26%|##6 | 11.8M/44.7M [00:00<00:00, 123MB/s]
- 53%|#####2 | 23.5M/44.7M [00:00<00:00, 109MB/s]
- 76%|#######6 | 34.0M/44.7M [00:00<00:00, 105MB/s]
- 99%|#########8| 44.0M/44.7M [00:00<00:00, 103MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 46.7MB/s]
+ 36%|###5 | 16.0M/44.7M [00:00<00:00, 69.8MB/s]
+ 58%|#####8 | 26.1M/44.7M [00:00<00:00, 80.3MB/s]
+ 76%|#######5 | 33.9M/44.7M [00:00<00:00, 73.1MB/s]
+ 93%|#########2| 41.4M/44.7M [00:00<00:00, 74.9MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 72.1MB/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 9655212b9f..dd1e47475b 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 13.118 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.903 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 e9520af4ff..e4a6d13a64 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>05:42.732</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:39.882</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>01:13.118</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>01:11.256</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>01:09.613</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>01:09.903</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>00:46.430</p></td>
+<td><p>00:45.882</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>00:31.885</p></td>
+<td><p>00:31.454</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>00:29.059</p></td>
+<td><p>00:28.161</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>00:26.510</p></td>
+<td><p>00:25.745</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>00:24.404</p></td>
+<td><p>00:25.706</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>00:22.305</p></td>
+<td><p>00:22.756</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>00:17.022</p></td>
+<td><p>00:16.632</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>00:02.386</p></td>
+<td><p>00:02.388</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 1b37eda98e..3f1005386a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,10 +919,10 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3344.6771 3343.5188 3359.0259 3336.9567 6.5112
+ 3340.6784 3339.5931 3347.4538 3337.5561 3.1354
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.226 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.472 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 50b794c140..b1cdbc979d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1232 15.9256 16.9046 15.7265 0.4393
+ 16.0077 15.9722 16.3833 15.8812 0.1352
</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 01d6bae03b..66354c8018 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,23 +453,30 @@ 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]
- 9%|8 | 14.6M/170M [00:00<00:01, 153MB/s]
- 17%|#7 | 29.2M/170M [00:00<00:01, 116MB/s]
- 24%|##4 | 40.8M/170M [00:00<00:01, 108MB/s]
- 30%|### | 51.3M/170M [00:00<00:01, 106MB/s]
- 36%|###6 | 61.6M/170M [00:00<00:01, 104MB/s]
- 42%|####2 | 71.6M/170M [00:00<00:01, 99.5MB/s]
- 48%|####7 | 81.2M/170M [00:00<00:00, 97.9MB/s]
- 53%|#####3 | 90.5M/170M [00:00<00:00, 87.2MB/s]
- 59%|#####8 | 100M/170M [00:01<00:00, 90.8MB/s]
- 64%|######4 | 109M/170M [00:01<00:00, 90.8MB/s]
- 69%|######9 | 118M/170M [00:01<00:00, 90.5MB/s]
- 75%|#######4 | 127M/170M [00:01<00:00, 92.4MB/s]
- 80%|######## | 136M/170M [00:01<00:00, 68.0MB/s]
- 87%|########6 | 147M/170M [00:01<00:00, 78.7MB/s]
- 92%|#########1| 156M/170M [00:01<00:00, 78.4MB/s]
- 96%|#########6| 164M/170M [00:01<00:00, 74.2MB/s]
-100%|##########| 170M/170M [00:01<00:00, 90.0MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 57.4MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 63.0MB/s]
+ 13%|#3 | 22.3M/170M [00:00<00:02, 64.1MB/s]
+ 17%|#6 | 28.5M/170M [00:00<00:02, 60.9MB/s]
+ 22%|##2 | 37.4M/170M [00:00<00:01, 71.5MB/s]
+ 26%|##6 | 44.4M/170M [00:00<00:01, 69.6MB/s]
+ 30%|### | 51.1M/170M [00:00<00:02, 58.8MB/s]
+ 37%|###6 | 62.3M/170M [00:00<00:01, 74.0MB/s]
+ 41%|####1 | 69.8M/170M [00:01<00:01, 66.9MB/s]
+ 45%|####5 | 76.5M/170M [00:01<00:01, 67.5MB/s]
+ 49%|####9 | 83.2M/170M [00:01<00:01, 65.2MB/s]
+ 53%|#####3 | 90.1M/170M [00:01<00:01, 63.9MB/s]
+ 57%|#####6 | 96.3M/170M [00:01<00:01, 55.1MB/s]
+ 60%|###### | 102M/170M [00:01<00:01, 54.5MB/s]
+ 63%|######3 | 108M/170M [00:01<00:01, 46.0MB/s]
+ 67%|######7 | 114M/170M [00:02<00:01, 48.1MB/s]
+ 71%|####### | 120M/170M [00:02<00:01, 50.9MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 56.2MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 62.1MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 64.1MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 61.2MB/s]
+ 93%|#########3| 158M/170M [00:02<00:00, 49.1MB/s]
+ 96%|#########6| 163M/170M [00:03<00:00, 42.2MB/s]
+100%|##########| 170M/170M [00:03<00:00, 57.5MB/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=& [...]
@@ -567,7 +574,7 @@ 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 16.418 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 9.036 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 11f706ceec..10cb10be4d 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]
- 86%|########6 | 11.7M/13.6M [00:00<00:00, 91.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 99.0MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 46.3MB/s]
+ 92%|#########1| 12.4M/13.6M [00:00<00:00, 44.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 48.2MB/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)
- 90.2859 90.1851 92.7542 90.0537 0.3070
+ 90.0908 89.9916 95.0659 89.7488 0.5376
</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 6.492 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.587 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 e065426b6c..317dbfd793 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)
- 120.6198 120.6334 122.5440 119.6961 0.4538
+ 120.9077 121.0449 123.9441 118.0763 0.7607
</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 23.458 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.673 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 63f5d4c34a..c636eba574 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 15.534 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.169 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 1b11900ab1..1e9824a5e8 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,22 +462,32 @@ 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]
- 3%|3 | 4538/132723 [00:00<00:02, 44814.51KB/s]
- 9%|9 | 11993/132723 [00:00<00:01, 62213.42KB/s]
- 15%|#5 | 20557/132723 [00:00<00:01, 72876.88KB/s]
- 22%|##1 | 29146/132723 [00:00<00:01, 77993.37KB/s]
- 28%|##8 | 37813/132723 [00:00<00:01, 81115.11KB/s]
- 35%|###4 | 46453/132723 [00:00<00:01, 82907.69KB/s]
- 41%|####1 | 55020/132723 [00:00<00:00, 83808.82KB/s]
- 48%|####8 | 63742/132723 [00:00<00:00, 84891.79KB/s]
- 55%|#####4 | 72422/132723 [00:00<00:00, 85485.81KB/s]
- 61%|######1 | 81184/132723 [00:01<00:00, 86142.15KB/s]
- 68%|######7 | 89799/132723 [00:01<00:00, 86131.44KB/s]
- 74%|#######4 | 98532/132723 [00:01<00:00, 86493.05KB/s]
- 81%|######## | 107215/132723 [00:01<00:00, 86593.44KB/s]
- 87%|########7 | 115918/132723 [00:01<00:00, 86724.06KB/s]
- 94%|#########3| 124591/132723 [00:01<00:00, 86465.60KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 82996.38KB/s]
+ 0%| | 477/132723 [00:00<00:28, 4601.06KB/s]
+ 1%| | 1242/132723 [00:00<00:20, 6300.41KB/s]
+ 2%|1 | 2202/132723 [00:00<00:16, 7747.18KB/s]
+ 3%|2 | 3386/132723 [00:00<00:13, 9332.63KB/s]
+ 4%|3 | 4874/132723 [00:00<00:11, 11306.33KB/s]
+ 5%|5 | 6714/132723 [00:00<00:09, 13695.70KB/s]
+ 7%|6 | 9066/132723 [00:00<00:07, 16887.11KB/s]
+ 9%|9 | 12057/132723 [00:00<00:05, 21018.31KB/s]
+ 12%|#1 | 15706/132723 [00:00<00:04, 25833.38KB/s]
+ 15%|#5 | 20410/132723 [00:01<00:03, 32314.43KB/s]
+ 20%|#9 | 26279/132723 [00:01<00:02, 40365.48KB/s]
+ 25%|##5 | 33423/132723 [00:01<00:01, 49800.65KB/s]
+ 31%|### | 40846/132723 [00:01<00:01, 57191.17KB/s]
+ 36%|###6 | 48362/132723 [00:01<00:01, 62611.36KB/s]
+ 42%|####2 | 55901/132723 [00:01<00:01, 66458.14KB/s]
+ 48%|####7 | 63410/132723 [00:01<00:01, 69052.25KB/s]
+ 54%|#####3 | 71023/132723 [00:01<00:00, 71177.13KB/s]
+ 59%|#####9 | 78603/132723 [00:01<00:00, 72564.12KB/s]
+ 65%|######4 | 86233/132723 [00:01<00:00, 73685.05KB/s]
+ 71%|####### | 93798/132723 [00:02<00:00, 74273.71KB/s]
+ 76%|#######6 | 101360/132723 [00:02<00:00, 74676.41KB/s]
+ 82%|########2 | 108907/132723 [00:02<00:00, 74912.00KB/s]
+ 88%|########7 | 116618/132723 [00:02<00:00, 75502.95KB/s]
+ 94%|#########3| 124506/132723 [00:02<00:00, 76466.75KB/s]
+100%|#########9| 132446/132723 [00:02<00:00, 77344.28KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 52768.49KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -516,7 +526,7 @@ 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 4.738 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.629 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 5b969f604c..d51dfb7e4a 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:32.624</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:33.406</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>03:16.418</p></td>
+<td><p>03:09.036</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>03:04.738</p></td>
+<td><p>02:59.629</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>02:23.458</p></td>
+<td><p>02:21.673</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>01:15.534</p></td>
+<td><p>01:35.169</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.492</p></td>
+<td><p>01:04.587</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>01:01.226</p></td>
+<td><p>01:00.472</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>00:35.516</p></td>
+<td><p>00:34.530</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>00:24.734</p></td>
+<td><p>00:24.306</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>00:24.502</p></td>
+<td><p>00:23.997</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>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 6d9b6c569c..f541ee097d 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.zip714dc02d-2f12-4161-a4c5-d99666d55c17 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.zip3a926a0d-246a-46b6-81be-f2da37e3b7d8 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 c2f7c7d827..2783e12b3f 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>00:49.266</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.633</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.688</p></td>
+<td><p>00:43.179</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>00:02.509</p></td>
+<td><p>00:02.442</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>00:01.062</p></td>
+<td><p>00:01.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 6354c3419b..14f5520260 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: 7449us [7449us] (46.52%; 46.52%)
-FoldScaleAxis: 8566us [8us] (53.48%; 53.48%)
- FoldConstant: 8557us [1755us] (53.43%; 99.91%)
- InferType: 6802us [6802us] (42.47%; 79.49%)
+InferType: 7338us [7338us] (46.67%; 46.67%)
+FoldScaleAxis: 8385us [7us] (53.33%; 53.33%)
+ FoldConstant: 8379us [1709us] (53.29%; 99.92%)
+ InferType: 6670us [6670us] (42.42%; 79.60%)
</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: 6916us [6916us] (45.14%; 45.14%)
-FoldScaleAxis: 8405us [6us] (54.86%; 54.86%)
- FoldConstant: 8399us [1735us] (54.82%; 99.93%)
- InferType: 6664us [6664us] (43.49%; 79.34%)
+InferType: 6679us [6679us] (44.71%; 44.71%)
+FoldScaleAxis: 8259us [5us] (55.29%; 55.29%)
+ FoldConstant: 8254us [1688us] (55.25%; 99.94%)
+ InferType: 6566us [6566us] (43.96%; 79.55%)
</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 bb0f1ef762..dac4b0b88e 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: 49.608894 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.872768 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 e46fd0cccf..f215728197 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: 12.536627 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.067497 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 2edb696079..053e04ca6d 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: 0.018991
-Baseline: 3.245249
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018249
+Baseline: 3.245860
</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: 0.307920
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301167
</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: 0.337509
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333597
</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: 0.115460
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114993
</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: 0.109356
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109305
</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: 0.110808
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110966
</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: 0.146717
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146460
</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 fdb1b2c3e0..5c588043ed 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>00:34.543</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.145</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>00:31.963</p></td>
+<td><p>00:31.702</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>00:01.480</p></td>
+<td><p>00:01.419</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>00:01.100</p></td>
+<td><p>00:01.024</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 f5b0f57b14..5336d28127 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>08:57.170</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:48.983</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:31.898</p></td>
+<td><p>05:30.318</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>01:31.389</p></td>
+<td><p>01:30.005</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>01:00.664</p></td>
+<td><p>00:59.581</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>00:29.814</p></td>
+<td><p>00:26.623</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.058</p></td>
+<td><p>00:11.637</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.347</p></td>
+<td><p>00:10.820</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index f1d8d6815e..6f5bfef812 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -503,153 +503,356 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), 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" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), 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" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((7 < floormod((threadIdx.x_1*12), 63)) && (floormod((threadIdx.x_1*12), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21 [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 1), 63)) && (floormod(((threadIdx.x_1*12) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 1), 63), 7)*7)) + rx.outer.ou [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 2), 63)) && (floormod(((threadIdx.x_1*12) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 2), 63), 7)*7)) + rx.outer.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 3), 63)) && (floormod(((threadIdx.x_1*12) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 3), 63), 7)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 4), 63)) && (floormod(((threadIdx.x_1*12) + 4), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 4), 63), 7)*7)) + rx.ou [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 5), 63)) && (floormod(((threadIdx.x_1*12) + 5), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 5), 63), 7)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 6), 63)) && (floormod(((threadIdx.x_1*12) + 6), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 6), 63), 7)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 7), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 8), 63)) && (floormod(((threadIdx.x_1*12) + 8), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 8), 63), 7)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 9), 63)) && (floormod(((threadIdx.x_1*12) + 9), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 9), 63), 7)*7)) + rx.out [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 10), 63)) && (floormod(((threadIdx.x_1*12) + 10), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 10), 63), 7)*7)) + r [...]
- }
- if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 11), 63)) && (floormod(((threadIdx.x_1*12) + 11), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 11), 63), 7)*7)) + rx [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 164), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 768)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 816)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 96)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 864)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 912)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 771)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 819)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 867)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 147)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 915)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 774)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 822)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 102)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 870)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 150)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 918)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 777)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 825)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 105)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 873)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 153)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 921)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 780)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 828)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 876)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 156)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 924)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 783)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 831)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 111)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 879)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 159)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 927)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 786)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 834)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 114)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 882)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 162)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 930)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 789)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 837)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 885)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 165)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 933)]))
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 2), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 27), 9)*7)) + (floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 4), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 4), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 27), 9)*7)) + (floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 6), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 6), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 27), 9)*7)) + (floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 8), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 8), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 27), 9)*7)) + (floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 9)*7)) + (flo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 12), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 12), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 27), 9)*7)) + (flo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 14), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 14), 27), 9)*7)) + (f [...]
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 168), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 504), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1400), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1456), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1512), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1848), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2072), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2184), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2520), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2632), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2856), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3080)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3192), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3248), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3304)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3304), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3640)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3752)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3864)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3864), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3976)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3976), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4088)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4200)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4200), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4368), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4424)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4536)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4536), 144)*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" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel_3[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4592), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2304)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2305)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2306)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2307)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2308)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2309)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2310)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2311)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2312)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2313)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2314)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2315)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2316)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2317)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2318)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2319)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2320)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2321)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2322)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2323)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2324)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2325)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2326)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2327)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2328)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2329)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2330)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2331)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2332)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2333)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2334)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2335)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2336)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2337)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2338)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2339)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*108) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2448)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2449)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2450)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2451)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2452)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2453)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2454)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2455)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2456)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 153)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2457)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 154)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2458)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 155)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2459)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 156)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2460)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 157)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2461)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 158)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2462)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 159)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2463)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 160)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2464)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 161)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2465)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 162)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2466)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 163)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2467)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 164)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2468)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 165)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2469)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 166)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2470)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 167)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2471)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 168)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2472)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 169)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2473)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 170)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2474)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 171)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2475)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 172)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2476)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 173)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2477)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 174)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2478)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 175)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2479)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 176)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2480)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 177)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2481)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 178)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2482)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 179)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*108) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*36)) + 2483)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (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*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
- compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute_3[((((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[((((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -686,7 +889,7 @@ 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: 0.392 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.367 ms
</pre></div>
</div>
</div>
@@ -715,33 +918,33 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
-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=4)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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_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=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
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_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=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)
@@ -764,14 +967,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=12)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -789,141 +992,262 @@ 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[8];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[1536];
+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[4];
+ __shared__ float pad_temp_shared[432];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((7 < ((((int)threadIdx.x) * 12) % 63)) && (((((int)threadIdx.x) * 12) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + ((((((int)threadIdx.x) * 12) % 63) / 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((7 <= (((((int)threadIdx.x) * 12) + 1) % 63)) && ((((((int)threadIdx.x) * 12) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 1) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)thre [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((7 < (((((int)threadIdx.x) * 12) + 2) % 63)) && ((((((int)threadIdx.x) * 12) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 2) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threa [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((7 < (((((int)threadIdx.x) * 12) + 3) % 63)) && ((((((int)threadIdx.x) * 12) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 3) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((7 <= (((((int)threadIdx.x) * 12) + 4) % 63)) && ((((((int)threadIdx.x) * 12) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 4) % 63) / 7) * 7)) + rx_outer_outer) + (((((in [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((7 < (((((int)threadIdx.x) * 12) + 5) % 63)) && ((((((int)threadIdx.x) * 12) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 5) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((7 < (((((int)threadIdx.x) * 12) + 6) % 63)) && ((((((int)threadIdx.x) * 12) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 6) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 12) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) / 7) + 1) % 9) * 7)) + rx_outer_outer) + ((((int)threadI [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((7 < (((((int)threadIdx.x) * 12) + 8) % 63)) && ((((((int)threadIdx.x) * 12) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 8) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((7 < (((((int)threadIdx.x) * 12) + 9) % 63)) && ((((((int)threadIdx.x) * 12) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 9) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((7 <= (((((int)threadIdx.x) * 12) + 10) % 63)) && ((((((int)threadIdx.x) * 12) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 10) % 63) / 7) * 7)) + rx_outer_outer) + ((( [...]
- }
- if (((int)threadIdx.x) < 84) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((7 < (((((int)threadIdx.x) * 12) + 11) % 63)) && ((((((int)threadIdx.x) * 12) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 11) % 63) / 7) * 7)) + rx_outer_outer) + (((( [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 4) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 4) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 20) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 164) {
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 28) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 768)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 816)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 864)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 912)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 771)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 819)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 867)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 147)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 915)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 774)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 822)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 870)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 150)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 918)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 777)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 825)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 873)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 153)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 921)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 780)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 828)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 876)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 156)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 924)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 783)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 831)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 879)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 159)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 927)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 786)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 834)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 882)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 162)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 930)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 789)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 837)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 885)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 165)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 933)]));
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 2) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 2) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 27) * 49)) + ((((((int)threadIdx.x) + 2) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)thr [...]
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 4) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 4) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 27) * 49)) + ((((((int)threadIdx.x) + 4) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)t [...]
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 6) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 6) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 27) * 49)) + ((((((int)threadIdx.x) + 6) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)t [...]
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 8) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 8) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)t [...]
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 12) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 12) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 27) * 49)) + ((((((int)threadIdx.x) + 12) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 14) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 27) * 49)) + ((((((int)threadIdx.x) + 14) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((( [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2408) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2520) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2632) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 3080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3304) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3864)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3864) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3976) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4200) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4424) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2304)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2305)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2306)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2307)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2308)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2309)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2310)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2311)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2312)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2313)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2314)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2315)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2316)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2317)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2318)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2319)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2320)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2321)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2322)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2323)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2324)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2325)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2326)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2327)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2328)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2329)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2330)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2331)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2332)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2333)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2334)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2335)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2336)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2337)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2338)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2339)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2448)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2449)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2450)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2451)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2452)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2453)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2454)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2455)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2456)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 153)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2457)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 154)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2458)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 155)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2459)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 156)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2460)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 157)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2461)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 158)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2462)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 159)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2463)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 160)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2464)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 161)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2465)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 162)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2466)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 163)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2467)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 164)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2468)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 165)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2469)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 166)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2470)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 167)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2471)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 168)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2472)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 169)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2473)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 170)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2474)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 171)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2475)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 172)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2476)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 173)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2477)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 174)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2478)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 175)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2479)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 176)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2480)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 177)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2481)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 178)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2482)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 179)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 108) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 36)) + 2483)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
</pre></div>
@@ -960,7 +1284,7 @@ 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 31.898 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 30.318 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 166b5e6bf4..2fcb6f93fb 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)
- 7.8485 7.8484 7.8516 7.8454 0.0025
+ 7.8549 7.8561 7.8574 7.8511 0.0027
</pre></div>
</div>
</div>
@@ -937,7 +937,6 @@ 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 0.664 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 261a8b44dd..7aec9278a0 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)
- 755.9013 755.2582 757.2791 755.1665 0.9750
+ 753.8896 753.9109 754.0111 753.7469 0.1089
</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 31.389 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.005 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 9705f2d496..439df74748 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,27 +632,76 @@ 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, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*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, 32) {
- 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.inner*16) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.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 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*1024) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_21]*16) + cse_var_20)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (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))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 8)] = max((compute_4[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -690,7 +739,7 @@ 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: 1.684 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.780 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index 7be26b6640..1cb653b995 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>00:38.701</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.256</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:38.663</p></td>
+<td><p>00:40.220</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index bbd2fdcf0d..45f1b29c72 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,7 +567,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 533.35/533.35 result: MeasureResult(costs=(0.0004340539370860928,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.865936279296875, timestamp=1669642833.1997926) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3980720
+No: 2 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -689,8 +690,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7737275
-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, 512, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6320389
+No: 3 GFLOPS: 23.83/533.35 result: MeasureResult(costs=(0.009714981727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.378678560256958, timestamp=1669642834.809128) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2973483
+No: 4 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -812,8 +814,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3204802
-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, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3280842
+No: 5 GFLOPS: 18.27/533.35 result: MeasureResult(costs=(0.012670737333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4939541816711426, timestamp=1669642837.4081566) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5686619
+No: 6 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -935,8 +938,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904150
-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, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7638365
+No: 7 GFLOPS: 84.78/533.35 result: MeasureResult(costs=(0.002730521945945946,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1698782444000244, timestamp=1669642838.9629657) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1008743
+No: 8 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1058,8 +1062,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7760839
-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, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5225123
+No: 9 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1181,9 +1185,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620741
-No: 6 GFLOPS: 2.34/2.34 result: MeasureResult(costs=(0.09906224799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9588117599487305, timestamp=1669636977.7683833) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746338
-No: 7 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3827463
+No: 10 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1305,8 +1308,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7432442
-No: 8 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6214249
+No: 11 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1428,8 +1431,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4755383
-No: 9 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6459244
+No: 12 GFLOPS: 457.18/533.35 result: MeasureResult(costs=(0.000506372243801653,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8325767517089844, timestamp=1669642842.0127907) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7633626
+No: 13 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1551,8 +1555,26 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6662910
-No: 10 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 2]), ('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, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,576260
+No: 14 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2041350
+No: 15 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1674,8 +1696,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4233511
-No: 11 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5286795
+No: 16 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1797,8 +1819,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8818349
-No: 12 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3374969
+No: 17 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1920,8 +1942,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2681356
-No: 13 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2996293
+No: 18 GFLOPS: 1.93/533.35 result: MeasureResult(costs=(0.12008470149999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4473347663879395, timestamp=1669642855.9362817) [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3690672
+No: 19 GFLOPS: 0.00/533.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2043,746 +2066,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5610233
-No: 14 GFLOPS: 7.47/7.47 result: MeasureResult(costs=(0.03098774325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.33935809135437, timestamp=1669636981.5201042) [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
-No: 15 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127872
-No: 16 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,494076
-No: 17 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10002729
-No: 18 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,911536
-No: 19 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9628256
-No: 20 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:389
- 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:375
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:270
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9846618
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6501970
+No: 20 GFLOPS: 56.60/533.35 result: MeasureResult(costs=(0.0040902542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2511205673217773, timestamp=1669642856.5935314) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6123095
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2821,9 +2106,9 @@ 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, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
+[('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3980720
Finish loading 20 records
-Time cost of this operator: 0.025340
+Time cost of this operator: 0.000761
</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 5debb6e495..e7f24057ea 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.709 (1, 2, 10, 10, 3) 2 1 [312.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.982 (1, 6, 10, 10) 1 1 [3.11]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.31 (1, 1, 10, 10, 3) 1 1 [0.982]
-Total_time - 316.892 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.2 98.721 (1, 2, 10, 10, 3) 2 1 [311.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.041 0.965 (1, 6, 10, 10) 1 1 [3.041]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.992 0.315 (1, 1, 10, 10, 3) 1 1 [0.992]
+Total_time - 315.233 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.51 (1, 6, 10, 10, 1) 2 1 [103.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.687 (1, 6, 10, 10) 1 1 [1.782]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.803 (1, 3, 10, 10, 1) 1 1 [0.848]
-Total_time - 105.63 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.2 97.399 (1, 6, 10, 10, 1) 2 1 [102.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.687 (1, 6, 10, 10) 1 1 [1.77]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 0.914 (1, 1, 10, 10, 3) 1 1 [0.959]
+Total_time - 104.929 - - - - -
</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 8cdba227a5..0a4ed4af9d 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, 73.8MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 94.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -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 4.758 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.658 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 13434f8f24..6f1ec67280 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/tmpjto5t1tf/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp5cpedw3l/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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpjto5t1tf/images/target contains 8144 images
-/tmp/tmpjto5t1tf/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp5cpedw3l/images/target contains 8144 images
+/tmp/tmp5cpedw3l/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: 0.2341 - accuracy: 0.9201 - val_loss: 0.1064 - val_accuracy: 0.9653 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2099 - accuracy: 0.9303 - val_loss: 0.1267 - val_accuracy: 0.9569 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1084 - accuracy: 0.9589 - val_loss: 0.1079 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0911 - accuracy: 0.9669 - val_loss: 0.2151 - val_accuracy: 0.9320 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0589 - accuracy: 0.9781 - val_loss: 0.0970 - val_accuracy: 0.9675 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0650 - accuracy: 0.9761 - val_loss: 0.1129 - val_accuracy: 0.9619 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7fc15ed50990>
+<keras.callbacks.History object at 0x7feaeb80a050>
</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> ( 3 minutes 59.372 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 26.455 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 9803dc5fab..3033bc4c77 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>06:07.586</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:27.381</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>03:59.372</p></td>
+<td><p>04:26.455</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>01:04.758</p></td>
+<td><p>01:00.658</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>00:51.246</p></td>
+<td><p>00:48.351</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.363</p></td>
+<td><p>00:08.248</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>00:03.844</p></td>
+<td><p>00:03.666</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 abef18a04f..9fe88b3e2f 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>00:44.803</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.333</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>00:32.406</p></td>
+<td><p>00:31.854</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>00:10.358</p></td>
+<td><p>00:09.993</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>00:02.033</p></td>
+<td><p>00:01.479</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 165c54939b..6e3b83e369 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 0x7fc1d85d5710>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7feae967c950>
</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 6730dec7b8..071600a6a9 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>00:06.367</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.916</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:03.826</p></td>
+<td><p>00:05.491</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>00:01.201</p></td>
+<td><p>00:01.100</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>00:00.571</p></td>
+<td><p>00:00.567</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.558</p></td>
+<td><p>00:00.550</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.115</p></td>
+<td><p>00:00.113</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -373,11 +373,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.018</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 0e347290ca..3deb5ff1dc 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/tmpq6rzp0lm/input0.cc'\nsource_filename = \"/tmp/tmpq6rzp0lm/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/tmp8176sa_w/input0.cc'\nsource_filename = \"/tmp/tmp8176sa_w/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 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<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"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<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="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 ae038e6855..b2ec311b9e 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 ad752e0c39..89ea67b66f 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/fc59b6dbd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 e06874eb44..113b517a13 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/fc59b6dbd/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 1257f8d494..0b1dbbd7b1 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/fc59b6dbd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 f2ec8c6ca8..97629537ba 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/fc59b6dbd/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 65be0bf244..2f0d9464ab 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/fc59b6dbd/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 a28e18a141..60aca59e3a 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/fc59b6dbd/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 2a325b6e7e..bc3b2ca2ca 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/fc59b6dbd/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 4a635042e5..51e86101b6 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/fc59b6dbd/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 045bfc455d..0eef76c0d1 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/fc59b6dbd/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 b97c720d7a..acd7d409b1 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/fc59b6dbd/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 b8987c2b2d..34306b69d0 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/fc59b6dbd/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 cf1cff2f2b..54f42b28f3 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/fc59b6dbd/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 13b980b44d..fd81c5b456 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/fc59b6dbd/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 16696f4acc..c12a53ffa9 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/fc59b6dbd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 51f42a843a..c81e61e23e 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/fc59b6dbd/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 1d0ce5d272..b2c2195463 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/fc59b6dbd/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 de16ca81fb..ae7aa3dc3a 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/fc59b6dbd/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 7caca5d181..94e10eae8f 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/fc59b6dbd/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 0d1f8eb87e..c1bee57dd5 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/fc59b6dbd/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 41afdfb8c0..67579e12b7 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/fc59b6dbd/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 980f75bee6..48c04effac 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/fc59b6dbd/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 8add31aaeb..3277305a2f 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/fc59b6dbd/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 c7ca4e7707..223a5c60b6 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/fc59b6dbd/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 1858a8a909..0936f3aea2 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/fc59b6dbd/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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/fc59b6dbd/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61144f9d8/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 f05c74f30d..948f6b5888 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 c282a6786b..41b87eaa6e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:27.294</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:25.771</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:27.287</p></td>
+<td><p>00:25.765</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 c1f5e6c9db..4a0599b7c9 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 30.43s!
+resnet18_v1 inference graph built in 28.41s!
</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 e289757d92..b70e662e76 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.39s!
+yolov3-tiny inference graph built in 19.14s!
</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 8edb89caeb..3668019956 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>01:42.511</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:39.961</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:52.033</p></td>
+<td><p>00:51.638</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>00:50.478</p></td>
+<td><p>00:48.323</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 dd26f73801..2d90c3a3dd 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>00:03.166</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.174</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>00:02.709</p></td>
+<td><p>00:02.735</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>00:00.456</p></td>
+<td><p>00:00.439</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 3313ce649d..d1af3b8568 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>00:00.804</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.770</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>00:00.430</p></td>
+<td><p>00:00.409</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>00:00.374</p></td>
+<td><p>00:00.360</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 7beb86e8a6..285442a6d7 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,10 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-.T
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -581,7 +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: 95.375 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.712 ms
</pre></div>
</div>
</div>
@@ -655,7 +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 36.969 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.969 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 4a7731c2d3..5c684e6cbb 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: 2.57/2.57 result: MeasureResult(costs=(0.10462719839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8281018733978271, timestamp=1669635554.1587062) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 2 GFLOPS: 12.99/12.99 result: MeasureResult(costs=(0.020664898600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5226318836212158, timestamp=1669635554.699581) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
-No: 3 GFLOPS: 10.19/12.99 result: MeasureResult(costs=(0.026348740400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8465473651885986, timestamp=1669635556.0615485) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
-No: 4 GFLOPS: 8.70/12.99 result: MeasureResult(costs=(0.030860226799999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8248922824859619, timestamp=1669635557.4794347) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
-No: 5 GFLOPS: 4.07/12.99 result: MeasureResult(costs=(0.06600606540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2161962985992432, timestamp=1669635558.8116148) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
-No: 6 GFLOPS: 2.43/12.99 result: MeasureResult(costs=(0.1103962426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.913161277770996, timestamp=1669635561.514688) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
-No: 7 GFLOPS: 0.90/12.99 result: MeasureResult(costs=(0.2998592632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942259311676025, timestamp=1669635566.4768138) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
-No: 8 GFLOPS: 1.91/12.99 result: MeasureResult(costs=(0.1405420992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.429777145385742, timestamp=1669635568.932175) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 9 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.018724787799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.47362279891967773, timestamp=1669635569.5193236) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
-No: 10 GFLOPS: 10.73/14.34 result: MeasureResult(costs=(0.0250093266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562950611114502, timestamp=1669635570.0888388) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
+No: 1 GFLOPS: 1.54/1.54 result: MeasureResult(costs=(0.1737638714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.927121877670288, timestamp=1669641420.4367385) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+No: 2 GFLOPS: 3.68/3.68 result: MeasureResult(costs=(0.0729572428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3492066860198975, timestamp=1669641421.8072093) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+No: 3 GFLOPS: 9.97/9.97 result: MeasureResult(costs=(0.0269202026,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6164209842681885, timestamp=1669641423.1304102) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+No: 4 GFLOPS: 0.51/9.97 result: MeasureResult(costs=(0.5307152626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.6624596118927, timestamp=1669641432.5372407) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+No: 5 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.021017550399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49544835090637207, timestamp=1669641433.1491547) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+No: 6 GFLOPS: 2.69/12.77 result: MeasureResult(costs=(0.09979856740000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7374615669250488, timestamp=1669641434.905883) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 7 GFLOPS: 0.90/12.77 result: MeasureResult(costs=(0.2995993068,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942751407623291, timestamp=1669641440.6305485) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+No: 8 GFLOPS: 0.83/12.77 result: MeasureResult(costs=(0.321642802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.309566259384155, timestamp=1669641445.9727027) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 9 GFLOPS: 11.86/12.77 result: MeasureResult(costs=(0.0226419244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5397887229919434, timestamp=1669641446.6248975) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 10 GFLOPS: 1.18/12.77 result: MeasureResult(costs=(0.22772719600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.754491090774536, timestamp=1669641450.4300933) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
</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 646322a3aa..f310710a08 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': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 523.03492, 'median': 522.3141131500029, 'std': 3.237501830193314}
</pre></div>
</div>
</div>
@@ -712,179 +712,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 12.35/ 17.91 GFLOPS | Progress: (4/20) | 7.20 s
-[Task 1/25] Current/Best: 12.44/ 17.91 GFLOPS | Progress: (8/20) | 11.21 s
-[Task 1/25] Current/Best: 11.17/ 17.91 GFLOPS | Progress: (12/20) | 13.91 s
-[Task 1/25] Current/Best: 7.15/ 21.25 GFLOPS | Progress: (16/20) | 15.77 s
-[Task 1/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 17.76 s Done.
+[Task 1/25] Current/Best: 11.85/ 12.47 GFLOPS | Progress: (4/20) | 8.00 s
+[Task 1/25] Current/Best: 4.10/ 14.69 GFLOPS | Progress: (8/20) | 12.27 s
+[Task 1/25] Current/Best: 1.92/ 14.69 GFLOPS | Progress: (12/20) | 17.03 s
+[Task 1/25] Current/Best: 6.73/ 14.69 GFLOPS | Progress: (16/20) | 19.94 s
+[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (20/20) | 22.55 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 7.60/ 15.88 GFLOPS | Progress: (4/20) | 2.84 s
-[Task 2/25] Current/Best: 6.13/ 15.88 GFLOPS | Progress: (8/20) | 4.18 s
-[Task 2/25] Current/Best: 21.69/ 21.69 GFLOPS | Progress: (12/20) | 5.27 s
-[Task 2/25] Current/Best: 9.51/ 21.69 GFLOPS | Progress: (16/20) | 6.84 s
-[Task 2/25] Current/Best: 16.65/ 21.69 GFLOPS | Progress: (20/20) | 8.55 s Done.
+[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (4/20) | 3.02 s
+[Task 2/25] Current/Best: 8.09/ 20.59 GFLOPS | Progress: (8/20) | 4.66 s
+[Task 2/25] Current/Best: 12.10/ 20.59 GFLOPS | Progress: (12/20) | 6.07 s
+[Task 2/25] Current/Best: 4.25/ 20.59 GFLOPS | Progress: (16/20) | 7.39 s
+[Task 2/25] Current/Best: 6.51/ 20.59 GFLOPS | Progress: (20/20) | 8.54 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 14.57/ 15.33 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 3/25] Current/Best: 11.61/ 15.33 GFLOPS | Progress: (8/20) | 6.09 s
-[Task 3/25] Current/Best: 12.42/ 19.62 GFLOPS | Progress: (12/20) | 8.00 s
-[Task 3/25] Current/Best: 17.84/ 19.62 GFLOPS | Progress: (16/20) | 10.12 s
-[Task 3/25] Current/Best: 10.16/ 19.86 GFLOPS | Progress: (20/20) | 11.98 s Done.
+[Task 3/25] Current/Best: 12.28/ 22.23 GFLOPS | Progress: (4/20) | 4.01 s
+[Task 3/25] Current/Best: 7.57/ 22.23 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 3/25] Current/Best: 15.75/ 22.23 GFLOPS | Progress: (12/20) | 9.29 s
+[Task 3/25] Current/Best: 13.24/ 22.23 GFLOPS | Progress: (16/20) | 11.24 s
+[Task 3/25] Current/Best: 7.48/ 22.23 GFLOPS | Progress: (20/20) | 13.16 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 3.42 s
-[Task 4/25] Current/Best: 6.16/ 17.31 GFLOPS | Progress: (8/20) | 5.18 s
-[Task 4/25] Current/Best: 9.28/ 22.19 GFLOPS | Progress: (12/20) | 9.94 s
-[Task 4/25] Current/Best: 6.47/ 22.19 GFLOPS | Progress: (16/20) | 11.93 s
-[Task 4/25] Current/Best: 19.38/ 22.19 GFLOPS | Progress: (20/20) | 13.25 s Done.
+[Task 4/25] Current/Best: 10.45/ 12.61 GFLOPS | Progress: (4/20) | 5.87 s
+[Task 4/25] Current/Best: 9.03/ 13.81 GFLOPS | Progress: (8/20) | 8.16 s
+[Task 4/25] Current/Best: 13.94/ 18.40 GFLOPS | Progress: (12/20) | 14.57 s
+[Task 4/25] Current/Best: 12.97/ 18.40 GFLOPS | Progress: (16/20) | 17.13 s
+[Task 4/25] Current/Best: 5.02/ 18.60 GFLOPS | Progress: (20/20) | 21.66 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 3.56 s
-[Task 5/25] Current/Best: 6.00/ 12.20 GFLOPS | Progress: (8/20) | 5.54 s
-[Task 5/25] Current/Best: 3.08/ 20.88 GFLOPS | Progress: (12/20) | 7.43 s
-[Task 5/25] Current/Best: 8.04/ 22.55 GFLOPS | Progress: (16/20) | 9.54 s
-[Task 5/25] Current/Best: 17.91/ 22.55 GFLOPS | Progress: (20/20) | 11.11 s Done.
+[Task 5/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 5/25] Current/Best: 17.61/ 22.23 GFLOPS | Progress: (8/20) | 5.57 s
+[Task 5/25] Current/Best: 13.80/ 22.23 GFLOPS | Progress: (12/20) | 8.17 s
+[Task 5/25] Current/Best: 16.35/ 22.23 GFLOPS | Progress: (16/20) | 9.93 s
+[Task 5/25] Current/Best: 3.06/ 22.23 GFLOPS | Progress: (20/20) | 11.54 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/20) | 4.83 s
-[Task 6/25] Current/Best: 10.60/ 18.77 GFLOPS | Progress: (8/20) | 9.56 s
-[Task 6/25] Current/Best: 12.17/ 18.77 GFLOPS | Progress: (12/20) | 11.66 s
-[Task 6/25] Current/Best: 8.38/ 18.77 GFLOPS | Progress: (16/20) | 14.00 s
-[Task 6/25] Current/Best: 9.76/ 18.77 GFLOPS | Progress: (20/20) | 19.03 s Done.
+[Task 6/25] Current/Best: 17.80/ 17.80 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 6/25] Current/Best: 15.35/ 18.20 GFLOPS | Progress: (8/20) | 5.57 s
+[Task 6/25] Current/Best: 5.53/ 18.20 GFLOPS | Progress: (12/20) | 7.87 s
+[Task 6/25] Current/Best: 9.39/ 18.20 GFLOPS | Progress: (16/20) | 14.36 s
+[Task 6/25] Current/Best: 16.52/ 18.20 GFLOPS | Progress: (20/20) | 16.48 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 15.25/ 15.25 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 7/25] Current/Best: 12.06/ 15.25 GFLOPS | Progress: (8/20) | 6.06 s
-[Task 7/25] Current/Best: 15.13/ 15.75 GFLOPS | Progress: (12/20) | 8.50 s
-[Task 7/25] Current/Best: 7.11/ 15.84 GFLOPS | Progress: (16/20) | 11.07 s
-[Task 7/25] Current/Best: 15.83/ 15.84 GFLOPS | Progress: (20/20) | 13.12 s Done.
+[Task 7/25] Current/Best: 12.00/ 15.54 GFLOPS | Progress: (4/20) | 3.79 s
+[Task 7/25] Current/Best: 8.05/ 15.54 GFLOPS | Progress: (8/20) | 6.38 s
+[Task 7/25] Current/Best: 7.41/ 16.17 GFLOPS | Progress: (12/20) | 9.63 s
+[Task 7/25] Current/Best: 9.60/ 16.17 GFLOPS | Progress: (16/20) | 11.83 s
+[Task 7/25] Current/Best: 8.90/ 16.17 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: 4.39/ 12.87 GFLOPS | Progress: (4/20) | 5.76 s
-[Task 8/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (8/20) | 8.17 s
-[Task 8/25] Current/Best: 11.20/ 20.71 GFLOPS | Progress: (12/20) | 16.64 s
-[Task 8/25] Current/Best: 12.92/ 20.71 GFLOPS | Progress: (16/20) | 19.86 s
-[Task 8/25] Current/Best: 4.14/ 20.71 GFLOPS | Progress: (20/20) | 22.65 s Done.
+[Task 8/25] Current/Best: 4.86/ 14.69 GFLOPS | Progress: (4/20) | 6.08 s
+[Task 8/25] Current/Best: 12.04/ 14.69 GFLOPS | Progress: (8/20) | 14.67 s
+[Task 8/25] Current/Best: 15.05/ 15.05 GFLOPS | Progress: (12/20) | 20.23 s
+[Task 8/25] Current/Best: 9.25/ 19.37 GFLOPS | Progress: (16/20) | 31.39 s
+[Task 8/25] Current/Best: 11.16/ 19.37 GFLOPS | Progress: (20/20) | 37.87 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 22.53/ 22.53 GFLOPS | Progress: (4/20) | 4.80 s
-[Task 9/25] Current/Best: 12.86/ 22.53 GFLOPS | Progress: (8/20) | 6.48 s
-[Task 9/25] Current/Best: 16.12/ 22.53 GFLOPS | Progress: (12/20) | 10.27 s
-[Task 9/25] Current/Best: 14.03/ 22.53 GFLOPS | Progress: (16/20) | 13.29 s
-[Task 9/25] Current/Best: 14.10/ 22.53 GFLOPS | Progress: (20/20) | 17.00 s Done.
-
+[Task 9/25] Current/Best: 9.58/ 17.83 GFLOPS | Progress: (4/20) | 12.35 s
+[Task 9/25] Current/Best: 22.58/ 22.58 GFLOPS | Progress: (8/20) | 16.57 s
+[Task 9/25] Current/Best: 5.85/ 22.58 GFLOPS | Progress: (12/20) | 18.12 s
+[Task 9/25] Current/Best: 5.15/ 22.58 GFLOPS | Progress: (16/20) | 23.00 s
+[Task 9/25] Current/Best: 11.39/ 22.58 GFLOPS | Progress: (20/20) | 27.66 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 10/25] Current/Best: 12.30/ 18.22 GFLOPS | Progress: (8/20) | 4.96 s
-[Task 10/25] Current/Best: 11.81/ 20.44 GFLOPS | Progress: (12/20) | 7.80 s
-[Task 10/25] Current/Best: 13.28/ 20.44 GFLOPS | Progress: (16/20) | 10.40 s
-[Task 10/25] Current/Best: 18.40/ 20.44 GFLOPS | Progress: (20/20) | 12.83 s Done.
+[Task 10/25] Current/Best: 3.50/ 16.31 GFLOPS | Progress: (4/20) | 3.36 s
+[Task 10/25] Current/Best: 9.07/ 16.31 GFLOPS | Progress: (8/20) | 5.77 s
+[Task 10/25] Current/Best: 10.91/ 19.02 GFLOPS | Progress: (12/20) | 7.40 s
+[Task 10/25] Current/Best: 11.29/ 19.02 GFLOPS | Progress: (16/20) | 8.97 s
+[Task 10/25] Current/Best: 13.33/ 19.02 GFLOPS | Progress: (20/20) | 10.62 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 13.02/ 20.82 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 11/25] Current/Best: 13.52/ 21.49 GFLOPS | Progress: (8/20) | 8.20 s
-[Task 11/25] Current/Best: 11.47/ 21.49 GFLOPS | Progress: (12/20) | 10.32 s
-[Task 11/25] Current/Best: 17.80/ 21.49 GFLOPS | Progress: (16/20) | 12.25 s
-[Task 11/25] Current/Best: 6.15/ 22.38 GFLOPS | Progress: (20/20) | 14.79 s Done.
+[Task 11/25] Current/Best: 21.45/ 21.45 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 11/25] Current/Best: 20.11/ 21.45 GFLOPS | Progress: (8/20) | 5.68 s
+[Task 11/25] Current/Best: 9.12/ 21.45 GFLOPS | Progress: (12/20) | 8.72 s
+[Task 11/25] Current/Best: 19.55/ 21.45 GFLOPS | Progress: (16/20) | 10.90 s
+[Task 11/25] Current/Best: 16.52/ 21.45 GFLOPS | Progress: (20/20) | 12.68 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 9.13/ 13.79 GFLOPS | Progress: (4/20) | 3.64 s
-[Task 12/25] Current/Best: 17.47/ 18.18 GFLOPS | Progress: (8/20) | 5.29 s
-[Task 12/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 7.44 s
-[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (16/20) | 9.65 s
-[Task 12/25] Current/Best: 14.82/ 19.04 GFLOPS | Progress: (20/20) | 11.55 s Done.
+[Task 12/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (4/20) | 4.60 s
+[Task 12/25] Current/Best: 9.71/ 18.08 GFLOPS | Progress: (8/20) | 8.93 s
+[Task 12/25] Current/Best: 4.50/ 18.08 GFLOPS | Progress: (12/20) | 11.46 s
+[Task 12/25] Current/Best: 4.25/ 18.08 GFLOPS | Progress: (16/20) | 16.11 s
+[Task 12/25] Current/Best: 3.37/ 18.08 GFLOPS | Progress: (20/20) | 20.50 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 10.00/ 12.99 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 13/25] Current/Best: 15.11/ 16.32 GFLOPS | Progress: (8/20) | 7.61 s
-[Task 13/25] Current/Best: 11.00/ 16.32 GFLOPS | Progress: (12/20) | 12.11 s
-[Task 13/25] Current/Best: 8.41/ 18.24 GFLOPS | Progress: (16/20) | 16.97 s
-[Task 13/25] Current/Best: 13.37/ 18.24 GFLOPS | Progress: (20/20) | 20.01 s Done.
+[Task 13/25] Current/Best: 11.80/ 15.36 GFLOPS | Progress: (4/20) | 6.30 s
+[Task 13/25] Current/Best: 10.10/ 16.54 GFLOPS | Progress: (8/20) | 9.30 s
+[Task 13/25] Current/Best: 18.60/ 20.26 GFLOPS | Progress: (12/20) | 11.31 s
+[Task 13/25] Current/Best: 19.94/ 20.26 GFLOPS | Progress: (16/20) | 13.92 s
+[Task 13/25] Current/Best: 16.00/ 20.26 GFLOPS | Progress: (20/20) | 16.68 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 10.44/ 14.69 GFLOPS | Progress: (4/20) | 4.47 s
-[Task 14/25] Current/Best: 14.24/ 14.69 GFLOPS | Progress: (8/20) | 9.95 s
-[Task 14/25] Current/Best: 12.34/ 17.20 GFLOPS | Progress: (12/20) | 12.11 s
-[Task 14/25] Current/Best: 18.32/ 18.97 GFLOPS | Progress: (16/20) | 14.80 s
-[Task 14/25] Current/Best: 3.03/ 18.97 GFLOPS | Progress: (20/20) | 17.62 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 12.24/ 15.99 GFLOPS | Progress: (4/20) | 7.54 s
-[Task 15/25] Current/Best: 12.69/ 18.08 GFLOPS | Progress: (8/20) | 9.63 s
-[Task 15/25] Current/Best: 3.12/ 18.08 GFLOPS | Progress: (12/20) | 11.82 s Done.
+[Task 14/25] Current/Best: 12.68/ 13.14 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 14/25] Current/Best: 13.72/ 13.72 GFLOPS | Progress: (8/20) | 6.64 s
+[Task 14/25] Current/Best: 4.39/ 17.35 GFLOPS | Progress: (12/20) | 9.33 s Done.
-[Task 15/25] Current/Best: 13.44/ 18.08 GFLOPS | Progress: (16/20) | 14.49 s
-[Task 15/25] Current/Best: 15.82/ 18.08 GFLOPS | Progress: (20/20) | 16.39 s Done.
+[Task 14/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (16/20) | 11.49 s
+[Task 14/25] Current/Best: 7.84/ 18.95 GFLOPS | Progress: (20/20) | 19.76 s Done.
+
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 6.82/ 20.45 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 15/25] Current/Best: 6.15/ 20.45 GFLOPS | Progress: (8/20) | 4.83 s
+[Task 15/25] Current/Best: 10.31/ 20.45 GFLOPS | Progress: (12/20) | 6.23 s
+[Task 15/25] Current/Best: 15.45/ 20.45 GFLOPS | Progress: (16/20) | 11.40 s
+[Task 15/25] Current/Best: 18.10/ 22.62 GFLOPS | Progress: (20/20) | 12.57 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 18.27/ 21.01 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 16/25] Current/Best: 11.84/ 21.01 GFLOPS | Progress: (8/20) | 5.21 s
-[Task 16/25] Current/Best: 13.75/ 21.66 GFLOPS | Progress: (12/20) | 6.83 s
-[Task 16/25] Current/Best: 12.15/ 22.09 GFLOPS | Progress: (16/20) | 9.27 s
-[Task 16/25] Current/Best: 12.27/ 22.09 GFLOPS | Progress: (20/20) | 11.17 s Done.
+[Task 16/25] Current/Best: 11.26/ 18.30 GFLOPS | Progress: (4/20) | 3.57 s
+[Task 16/25] Current/Best: 12.28/ 18.30 GFLOPS | Progress: (8/20) | 6.36 s
+[Task 16/25] Current/Best: 9.61/ 18.30 GFLOPS | Progress: (12/20) | 7.62 s
+[Task 16/25] Current/Best: 14.35/ 19.00 GFLOPS | Progress: (16/20) | 9.96 s
+[Task 16/25] Current/Best: 17.91/ 19.00 GFLOPS | Progress: (20/20) | 11.48 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 19.03/ 22.98 GFLOPS | Progress: (4/20) | 3.54 s
-[Task 17/25] Current/Best: 9.48/ 22.98 GFLOPS | Progress: (8/20) | 6.35 s
-[Task 17/25] Current/Best: 10.16/ 22.98 GFLOPS | Progress: (12/20) | 8.84 s
-[Task 17/25] Current/Best: 11.86/ 22.98 GFLOPS | Progress: (16/20) | 11.73 s
-[Task 17/25] Current/Best: 5.20/ 22.98 GFLOPS | Progress: (20/20) | 14.23 s Done.
+[Task 17/25] Current/Best: 12.57/ 16.66 GFLOPS | Progress: (4/20) | 4.42 s
+[Task 17/25] Current/Best: 12.17/ 20.15 GFLOPS | Progress: (8/20) | 7.57 s
+[Task 17/25] Current/Best: 6.46/ 23.00 GFLOPS | Progress: (12/20) | 10.35 s
+[Task 17/25] Current/Best: 10.90/ 23.00 GFLOPS | Progress: (16/20) | 13.76 s
+[Task 17/25] Current/Best: 11.50/ 23.00 GFLOPS | Progress: (20/20) | 15.90 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 14.35/ 14.35 GFLOPS | Progress: (4/20) | 3.93 s
-[Task 18/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (8/20) | 5.40 s
-[Task 18/25] Current/Best: 15.69/ 22.72 GFLOPS | Progress: (12/20) | 9.31 s
-[Task 18/25] Current/Best: 13.96/ 22.72 GFLOPS | Progress: (16/20) | 11.42 s
-[Task 18/25] Current/Best: 17.39/ 22.72 GFLOPS | Progress: (20/20) | 14.88 s Done.
+[Task 18/25] Current/Best: 10.83/ 14.67 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 18/25] Current/Best: 5.91/ 18.49 GFLOPS | Progress: (8/20) | 6.47 s
+[Task 18/25] Current/Best: 15.72/ 18.49 GFLOPS | Progress: (12/20) | 8.43 s
+[Task 18/25] Current/Best: 2.88/ 18.49 GFLOPS | Progress: (16/20) | 11.18 s
+[Task 18/25] Current/Best: 14.97/ 18.49 GFLOPS | Progress: (20/20) | 13.00 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 10.56/ 14.25 GFLOPS | Progress: (4/20) | 5.04 s
-[Task 19/25] Current/Best: 21.33/ 21.97 GFLOPS | Progress: (8/20) | 7.31 s
-[Task 19/25] Current/Best: 8.39/ 21.97 GFLOPS | Progress: (12/20) | 12.43 s
-[Task 19/25] Current/Best: 10.35/ 21.97 GFLOPS | Progress: (16/20) | 17.63 s
-[Task 19/25] Current/Best: 17.07/ 21.97 GFLOPS | Progress: (20/20) | 20.53 s Done.
+[Task 19/25] Current/Best: 3.09/ 14.32 GFLOPS | Progress: (4/20) | 9.42 s
+[Task 19/25] Current/Best: 4.60/ 18.84 GFLOPS | Progress: (8/20) | 12.78 s
+[Task 19/25] Current/Best: 10.55/ 18.84 GFLOPS | Progress: (12/20) | 15.76 s
+[Task 19/25] Current/Best: 18.17/ 22.42 GFLOPS | Progress: (16/20) | 19.24 s
+[Task 19/25] Current/Best: 9.33/ 22.42 GFLOPS | Progress: (20/20) | 21.84 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 20/25] Current/Best: 11.65/ 18.84 GFLOPS | Progress: (8/20) | 6.55 s
-[Task 20/25] Current/Best: 16.43/ 18.84 GFLOPS | Progress: (12/20) | 9.11 s
-[Task 20/25] Current/Best: 8.84/ 18.84 GFLOPS | Progress: (16/20) | 12.91 s
-[Task 20/25] Current/Best: 16.06/ 18.84 GFLOPS | Progress: (20/20) | 14.75 s
+[Task 20/25] Current/Best: 13.70/ 17.45 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 20/25] Current/Best: 18.68/ 18.68 GFLOPS | Progress: (8/20) | 6.63 s
+[Task 20/25] Current/Best: 15.93/ 18.68 GFLOPS | Progress: (12/20) | 10.95 s
+[Task 20/25] Current/Best: 12.39/ 18.68 GFLOPS | Progress: (16/20) | 12.65 s
+[Task 20/25] Current/Best: 12.92/ 18.68 GFLOPS | Progress: (20/20) | 14.78 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 12.44/ 17.26 GFLOPS | Progress: (4/20) | 4.37 s
-[Task 21/25] Current/Best: 10.99/ 17.26 GFLOPS | Progress: (8/20) | 6.21 s Done.
+[Task 21/25] Current/Best: 8.75/ 19.24 GFLOPS | Progress: (4/20) | 3.41 s
+[Task 21/25] Current/Best: 11.99/ 19.24 GFLOPS | Progress: (8/20) | 5.48 s
+[Task 21/25] Current/Best: 22.57/ 22.57 GFLOPS | Progress: (12/20) | 7.08 s
+[Task 21/25] Current/Best: 10.05/ 22.57 GFLOPS | Progress: (16/20) | 9.33 s Done.
-[Task 21/25] Current/Best: 7.57/ 17.26 GFLOPS | Progress: (12/20) | 8.48 s
-[Task 21/25] Current/Best: 17.11/ 17.26 GFLOPS | Progress: (16/20) | 11.26 s
-[Task 21/25] Current/Best: 14.08/ 17.26 GFLOPS | Progress: (20/20) | 15.30 s
+[Task 21/25] Current/Best: 20.62/ 22.57 GFLOPS | Progress: (20/20) | 11.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 10.55/ 13.88 GFLOPS | Progress: (4/20) | 4.35 s
-[Task 22/25] Current/Best: 4.52/ 16.29 GFLOPS | Progress: (8/20) | 6.07 s
-[Task 22/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.43 s
-[Task 22/25] Current/Best: 7.08/ 19.56 GFLOPS | Progress: (16/20) | 9.63 s
-[Task 22/25] Current/Best: 18.66/ 19.56 GFLOPS | Progress: (20/20) | 11.32 s Done.
+[Task 22/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 22/25] Current/Best: 5.27/ 19.13 GFLOPS | Progress: (8/20) | 5.61 s
+[Task 22/25] Current/Best: 5.29/ 19.13 GFLOPS | Progress: (12/20) | 7.80 s
+[Task 22/25] Current/Best: 15.64/ 19.13 GFLOPS | Progress: (16/20) | 9.03 s
+[Task 22/25] Current/Best: 10.05/ 19.13 GFLOPS | Progress: (20/20) | 11.61 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 4.42/ 19.23 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 23/25] Current/Best: 11.96/ 20.75 GFLOPS | Progress: (8/20) | 5.70 s
-[Task 23/25] Current/Best: 17.04/ 20.75 GFLOPS | Progress: (12/20) | 8.37 s
-[Task 23/25] Current/Best: 20.41/ 20.75 GFLOPS | Progress: (16/20) | 11.13 s
-[Task 23/25] Current/Best: 18.96/ 20.75 GFLOPS | Progress: (20/20) | 16.82 s Done.
+[Task 23/25] Current/Best: 8.24/ 12.63 GFLOPS | Progress: (4/20) | 5.21 s
+[Task 23/25] Current/Best: 15.02/ 20.29 GFLOPS | Progress: (8/20) | 7.34 s
+[Task 23/25] Current/Best: 11.89/ 20.29 GFLOPS | Progress: (12/20) | 9.18 s
+[Task 23/25] Current/Best: 11.10/ 20.29 GFLOPS | Progress: (16/20) | 14.44 s
+[Task 23/25] Current/Best: 19.72/ 20.29 GFLOPS | Progress: (20/20) | 16.29 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 1.77/ 5.76 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 24/25] Current/Best: 1.45/ 7.07 GFLOPS | Progress: (8/20) | 15.22 s
-[Task 24/25] Current/Best: 2.59/ 7.18 GFLOPS | Progress: (12/20) | 25.98 s
-[Task 24/25] Current/Best: 2.80/ 7.18 GFLOPS | Progress: (16/20) | 37.65 s
-[Task 24/25] Current/Best: 4.45/ 7.18 GFLOPS | Progress: (20/20) | 49.43 s
+[Task 24/25] Current/Best: 4.42/ 4.42 GFLOPS | Progress: (4/20) | 12.23 s
+[Task 24/25] Current/Best: 9.90/ 9.90 GFLOPS | Progress: (8/20) | 13.91 s
+[Task 24/25] Current/Best: 3.05/ 9.90 GFLOPS | Progress: (12/20) | 24.18 s
+[Task 24/25] Current/Best: 3.03/ 9.90 GFLOPS | Progress: (16/20) | 36.06 s
+[Task 24/25] Current/Best: 1.05/ 9.90 GFLOPS | Progress: (20/20) | 41.01 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-[Task 25/25] Current/Best: 3.02/ 8.42 GFLOPS | Progress: (4/20) | 4.89 s
-[Task 25/25] Current/Best: 1.54/ 8.42 GFLOPS | Progress: (8/20) | 15.65 s
-[Task 25/25] Current/Best: 3.00/ 9.40 GFLOPS | Progress: (12/20) | 19.98 s
-[Task 25/25] Current/Best: 3.82/ 9.40 GFLOPS | Progress: (16/20) | 30.71 s
-[Task 25/25] Current/Best: 5.73/ 9.40 GFLOPS | Progress: (20/20) | 34.15 s
+[Task 25/25] Current/Best: 5.19/ 9.76 GFLOPS | Progress: (4/20) | 12.18 s
+[Task 25/25] Current/Best: 8.19/ 9.76 GFLOPS | Progress: (8/20) | 14.49 s
+[Task 25/25] Current/Best: 6.26/ 9.76 GFLOPS | Progress: (12/20) | 25.21 s
+[Task 25/25] Current/Best: 7.23/ 9.76 GFLOPS | Progress: (16/20) | 35.89 s
+[Task 25/25] Current/Best: 8.13/ 9.76 GFLOPS | Progress: (20/20) | 40.54 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +944,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
-class='n02123159 tiger cat' with probability=0.356377
+<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=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +982,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"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': 430.0801938499967, 'median': 430.3779723499929, 'std': 2.429183228660658}
-unoptimized: {'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 414.7481115500045, 'median': 414.6498360999999, 'std': 1.4220691099397493}
+unoptimized: {'mean': 523.03492, 'median': 522.3141131500029, 'std': 3.237501830193314}
</pre></div>
</div>
</div>
@@ -998,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 43.197 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 13.730 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 81dd4c37ee..e333ebe71f 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>1.271e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.289e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index bb9e1848db..bfe57e577d 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, 0xe8b6070)), stage(b, placeholder(b, 0x28a726d0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xc674890)), stage(b, placeholder(b, 0x128fcc50)), 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 272de94265..c633f63c9a 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>14:17.904</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:47.663</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</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>10:43.197</p></td>
+<td><p>11:13.730</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>01:36.969</p></td>
+<td><p>01:21.969</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>00:59.362</p></td>
+<td><p>00:59.301</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:34.192</p></td>
+<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>00:36.706</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:21.967</p></td>
+<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>00:33.560</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>00:01.254</p></td>
+<td><p>00:01.440</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>00:00.777</p></td>
+<td><p>00:00.772</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>
@@ -381,11 +381,11 @@
<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>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.003</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index ac8039a1cd..79bbf2d5c3 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -552,7 +552,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000007
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -600,7 +600,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000012
</pre></div>
</div>
</div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.441079999352951e-06 1.0
- naive 6.696100000000001e-06 0.8998828127882337
-parallel 6.950399999999999e-06 0.9340579594097067
- vector 2.53151e-05 3.4020733552389317
+ numpy 7.225399999697402e-06 1.0
+ naive 7.883e-06 1.0910122623425884
+parallel 1.1852e-05 1.6403244111739639
+ vector 2.5136799999999996e-05 3.478949262470274
</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: 0.019053
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018634
</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: 3.256209
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.262746
</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: 0.314476
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.305868
</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: 0.345962
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.345219
@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: 0.119863
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.121067
@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: 0.110230
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108728
@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: 0.110165
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.109726
@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: 0.146200
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146219
@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 3.2562085157 1.0
- blocking 0.3144764388 0.09657748798448669
- vectorization 0.3459622566 0.10624696020906607
-loop permutation 0.1198630473 0.036810617846514834
- array packing 0.1102295502 0.033852116554735905
- block caching 0.11016505830000001 0.03383231072851531
- parallelization 0.14619960810000002 0.044898724204881245
+ none 3.2627462856999996 1.0
+ blocking 0.3058683523 0.09374567481405562
+ vectorization 0.3452194227 0.10580639512579679
+loop permutation 0.12106699810000002 0.0371058573051217
+ array packing 0.10872769699999998 0.03332398154172543
+ block caching 0.10972645919999999 0.033630092441116345
+ parallelization 0.14621879570000001 0.04481463861926665
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a