Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[WIP]add inference mode for op perf benchmark #15453

Closed
wants to merge 2 commits into from
Closed

[WIP]add inference mode for op perf benchmark #15453

wants to merge 2 commits into from

Conversation

roywei
Copy link
Member

@roywei roywei commented Jul 3, 2019

As one of the efforts to address #15429

We need to run op perf in inference mode as well as in 1.4.1 where runtime_feature is not available.

@pengzhao-intel
Copy link
Contributor

Thanks for the improvement.
Could you paste the output of inference OP for both CPU and GPU?

@roywei roywei changed the title add inference mode for op perf benchmark [WIP]add inference mode for op perf benchmark Jul 8, 2019
@roywei
Copy link
Member Author

roywei commented Jul 8, 2019

@mxnet-label-bot add [performance, pr-work-in-progress]

@marcoabreu marcoabreu added Performance pr-work-in-progress PR is still work in progress labels Jul 8, 2019
@roywei roywei closed this Jul 22, 2019
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers
No reviews
Assignees
No one assigned
Labels
Performance pr-work-in-progress PR is still work in progress
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@roywei @pengzhao-intel @marcoabreu