Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[js/webgpu] Increase workgroupSize if only one workgroup is dispached #22709

Merged
merged 2 commits into from
Nov 5, 2024
Merged

[js/webgpu] Increase workgroupSize if only one workgroup is dispached #22709

merged 2 commits into from
Nov 5, 2024

Conversation

qjia7
Copy link
Contributor

@qjia7 qjia7 commented Nov 4, 2024

#22031

For reduce related ops, we should increase workgroupSize to improve parallelism if only one workgroup is dispatched.

The total ReduceMean time becomes 8.98 ms from 77.79 ms on my iGPUs.

@qjia7
[js/webgpu] Increase workgroupSize if only one workgroup is dispached
38287f9 
For reduce related ops, we should increase workgroupSize to improve
parallelism if only one workgroup is dispatched.
@qjia7
Copy link
Contributor Author

qjia7 commented Nov 4, 2024

@guschmue @fs-eire Please take a look, thanks.

@fs-eire
Copy link
Contributor

fs-eire commented Nov 4, 2024

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline

@fs-eire
Copy link
Contributor

fs-eire commented Nov 4, 2024

/azp run Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline

@fs-eire
Copy link
Contributor

fs-eire commented Nov 4, 2024

/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,CoreML CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

2 similar comments
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

guschmue
guschmue previously approved these changes Nov 4, 2024
View reviewed changes
@guschmue guschmue added the ep:WebGPU ort-web webgpu provider label Nov 4, 2024
@qjia7 qjia7 requested a review from fs-eire November 5, 2024 05:07
@guschmue
Copy link
Contributor

guschmue commented Nov 5, 2024

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline

@guschmue
Copy link
Contributor

guschmue commented Nov 5, 2024

/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

@guschmue
Copy link
Contributor

guschmue commented Nov 5, 2024

/azp run 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,Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines could not run because the pipeline triggers exclude this branch/path.

@guschmue
Copy link
Contributor

guschmue commented Nov 5, 2024

/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines could not run because the pipeline triggers exclude this branch/path.

@guschmue guschmue merged commit d5b2730 into microsoft:main Nov 5, 2024
50 checks passed
@qjia7 qjia7 deleted the opt_reduce branch November 7, 2024 02:22
ishwar-raut1 pushed a commit to ishwar-raut1/onnxruntime that referenced this pull request Nov 19, 2024
@qjia7
[js/webgpu] Increase workgroupSize if only one workgroup is dispached (…
66c8333 
…microsoft#22709)

microsoft#22031

For reduce related ops, we should increase workgroupSize to improve
parallelism if only one workgroup is dispatched.

The total ReduceMean time becomes 8.98 ms from 77.79 ms on my iGPUs.
guschmue pushed a commit that referenced this pull request Dec 2, 2024
@qjia7 @guschmue
[js/webgpu] Increase workgroupSize if only one workgroup is dispached (…
b906b30 
…#22709)

#22031

For reduce related ops, we should increase workgroupSize to improve
parallelism if only one workgroup is dispatched.

The total ReduceMean time becomes 8.98 ms from 77.79 ms on my iGPUs.
ankitm3k pushed a commit to intel/onnxruntime that referenced this pull request Dec 11, 2024
@qjia7 @ankitm3k
[js/webgpu] Increase workgroupSize if only one workgroup is dispached (…
53a4319 
…microsoft#22709)

microsoft#22031

For reduce related ops, we should increase workgroupSize to improve
parallelism if only one workgroup is dispatched.

The total ReduceMean time becomes 8.98 ms from 77.79 ms on my iGPUs.
ankitm3k pushed a commit to intel/onnxruntime that referenced this pull request Dec 11, 2024
@qjia7 @ankitm3k
[js/webgpu] Increase workgroupSize if only one workgroup is dispached (…
63533ea 
…microsoft#22709)

microsoft#22031

For reduce related ops, we should increase workgroupSize to improve
parallelism if only one workgroup is dispatched.

The total ReduceMean time becomes 8.98 ms from 77.79 ms on my iGPUs.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@guschmue guschmue guschmue approved these changes

@fs-eire fs-eire Awaiting requested review from fs-eire

Assignees
No one assigned
Labels
ep:WebGPU ort-web webgpu provider
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@qjia7 @fs-eire @guschmue