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

[Paddle-TRT] MaskRCNN OPs stream optimization #31641

Merged
merged 1 commit into from
Mar 19, 2021
Merged

[Paddle-TRT] MaskRCNN OPs stream optimization #31641

merged 1 commit into from
Mar 19, 2021

Conversation

zlsh80826
Copy link
Collaborator

@zlsh80826 zlsh80826 commented Mar 15, 2021 •
edited
Loading

PR types

Performance optimization

PR changes

OPs

Describe

  1. GetLengthLoD, GPUDistFpnProposalsHelper should run on context stream
  2. remove two unnecessary context wait (no data is sent between host and device)
  3. sub_lod_data can be memcpy in batch, reduce multiple times sychronization
  4. The is ~1% e2e performance gain on trt-fp16/maskrcnn inference

@paddle-bot-old
Copy link

Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@cryoco cryoco requested a review from jerrywgz March 18, 2021 06:01
jerrywgz
jerrywgz approved these changes Mar 18, 2021
View reviewed changes
Copy link
Contributor

@jerrywgz jerrywgz left a comment

Choose a reason for hiding this comment

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

LGTM

@cryoco cryoco merged commit 50cafa0 into PaddlePaddle:develop Mar 19, 2021
@zlsh80826 zlsh80826 changed the title MaskRCNN OPs stream optimization [Paddle-TRT] MaskRCNN OPs stream optimization Jan 6, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jerrywgz jerrywgz jerrywgz approved these changes

Assignees
No one assigned
Labels
NVIDIA
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@zlsh80826 @jerrywgz @cryoco