Skip to content

dnn: improve scatter and scatterND speed with multi-threading#24813

Merged
asmorkalov merged 5 commits intoopencv:4.xfrom
fengyuentau:speedup_scatter
Jan 17, 2024
Merged

dnn: improve scatter and scatterND speed with multi-threading#24813
asmorkalov merged 5 commits intoopencv:4.xfrom
fengyuentau:speedup_scatter

Conversation

@fengyuentau
Copy link
Copy Markdown
Member

@fengyuentau fengyuentau commented Jan 5, 2024 •
edited by opencv-alalek
Loading

Benchmark was done on M1 Macbook Air (16G mem). Time is in milliseconds.

*: Shapes of input, indices, updates are all [2, 128, 64, 50].

Operator w/ this PR w/o this PR ORT
Scatter (Reduction=None, axis=0) 2.04 7.36 6.81
Scatter (Reduction=Add, axis=0) 2.00 7.61 6.33
ScatterND (Reduction=None) 1.41 6.59 17.52
ScatterND (Reduction=Add) 1.37 6.83 16.34

Scripts for ORT benchmark: ort_benchmark.zip

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

  • I agree to contribute to the project under Apache 2 License.
  • To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
  • The PR is proposed to the proper branch
  • There is a reference to the original bug report and related work
  • There is accuracy test, performance test and test data in opencv_extra repository, if applicable
    Patch to opencv_extra has the same branch name.
  • The feature is well documented and sample code can be built with the project CMake
force_builders=Linux OpenCL

@fengyuentau fengyuentau added this to the 4.10.0 milestone Jan 5, 2024
@fengyuentau fengyuentau requested a review from dkurt January 5, 2024 09:29
@asmorkalov asmorkalov requested a review from vpisarev January 17, 2024 09:18
@asmorkalov
Copy link
Copy Markdown
Contributor

asmorkalov commented Jan 17, 2024

@vpisarev @dkurt Friendly reminder.

dkurt
dkurt approved these changes Jan 17, 2024
View reviewed changes
Copy link
Copy Markdown
Member

@dkurt dkurt left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good improvement, thanks!

@asmorkalov asmorkalov merged commit ac4c0bf into opencv:4.x Jan 17, 2024
@opencv-alalek
Copy link
Copy Markdown
Contributor

opencv-alalek commented Jan 17, 2024

There are broken OpenCL tests: https://pullrequest.opencv.org/buildbot/builders/precommit_opencl_linux/builds/100340

@fengyuentau
Copy link
Copy Markdown
Member Author

fengyuentau commented Jan 17, 2024

Let me take care of that.

@fengyuentau fengyuentau deleted the speedup_scatter branch January 18, 2024 02:40
@fengyuentau fengyuentau mentioned this pull request Jan 18, 2024
Merged
6 tasks
@asmorkalov asmorkalov mentioned this pull request Jan 23, 2024
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@dkurt dkurt dkurt approved these changes

@vpisarev vpisarev Awaiting requested review from vpisarev

Assignees

No one assigned

Labels

category: dnn optimization

Projects

None yet

Milestone

4.10.0

Development

Successfully merging this pull request may close these issues.

4 participants

@fengyuentau @asmorkalov @opencv-alalek @dkurt