[js/webgpu] Provide a vectorized algorithm for GroupedConv #18884
Conversation
|
@fs-eire @guschmue @satyajandhyala Please take a look, thanks. |
|
/azp run ONNX Runtime Web CI Pipeline |
|
/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
/azp run Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline |
|
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-python-checks-ci-pipeline,onnxruntime-binary-size-checks-ci-pipeline,Android CI Pipeline |
|
/azp run iOS CI Pipeline,ONNX Runtime React Native CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
2 similar comments
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
@fs-eire @guschmue @satyajandhyala any more comments on this? |
|
I am running the unit tests on my local machine to check if CI reports false error. |
Passed on my local as well. It should be a false error. Let me merge it and watch the main branch. |
I locally tried NV and Intel machines. All cases pass on both of them on latest main. I can't reproduce those failures. Any idea for this? |
…icrosoft#18884)" This reverts commit fd6bab4 due to below cases failure on bots [webgpu]Conv - conv - vectorize group - B [webgpu]Conv - conv - vectorize group - D
…#18884) ### Description This PR provides a vectorized algorithm for NHWC GroupedConv to improve performance. The aggregate time of GroupedConv in mobilenetv2-12 becomes ~1ms from ~4ms on Intel Alder Lake machine. About 20% improvement for the whole model.
Description
This PR provides a vectorized algorithm for NHWC GroupedConv to improve performance.
The aggregate time of GroupedConv in mobilenetv2-12 becomes ~1ms from ~4ms on Intel Alder Lake machine. About 20% improvement for the whole model.