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.

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

13544: Update floor op #15583

Merged
merged 2 commits into from
Dec 7, 2024
Merged

13544: Update floor op #15583

merged 2 commits into from
Dec 7, 2024

Conversation

mouliraj-mcw
Copy link
Contributor

@mouliraj-mcw mouliraj-mcw commented Dec 1, 2024

Ticket

Link to Github Issue #13544

Problem description

  • Floor op ignore values outside range of i16

What's changed

  • Updated the logic to support fp32

Profiling Results : Shape used [1, 1, 102400, 32]

Kernel Duration [ns]

  • Bfloat16 : 68870
  • Float32 : 156560

Checklist

  • All Post commit CI

@mouliraj-mcw mouliraj-mcw force-pushed the mouliraj/round_update branch 3 times, most recently from a86c6e7 to d7e8075 Compare December 2, 2024 12:32
Copy link
Contributor

@Aswinmcw Aswinmcw left a comment

Choose a reason for hiding this comment

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

LGTM

@mouliraj-mcw mouliraj-mcw force-pushed the mouliraj/round_update branch from d7e8075 to da4540b Compare December 3, 2024 04:22
Copy link
Contributor

@eyonland eyonland left a comment

Choose a reason for hiding this comment

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

See my comment. I'd like to hear how we might handle this in a better way going forward.

@mouliraj-mcw mouliraj-mcw force-pushed the mouliraj/round_update branch from da4540b to ac64948 Compare December 7, 2024 05:48
@mouliraj-mcw mouliraj-mcw merged commit 3afc3b8 into main Dec 7, 2024
119 checks passed
@mouliraj-mcw mouliraj-mcw deleted the mouliraj/round_update branch December 7, 2024 07:51
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

8 participants