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

Continue investigating LSTM speedups #3305

Open
1 of 4 tasks
sffc opened this issue Apr 13, 2023 · 4 comments
Open
1 of 4 tasks

Continue investigating LSTM speedups #3305

sffc opened this issue Apr 13, 2023 · 4 comments
Assignees
@pdogr
Labels
C-segmentation Component: Segmentation S-medium Size: Less than a week (larger bug fix or enhancement) T-enhancement Type: Nice-to-have but not required
Milestone
2.x Priority ⟨P2⟩

Comments

@sffc
Copy link
Member

sffc commented Apr 13, 2023 •
edited
Loading

Some things we think might work to make it faster still:
@sffc sffc added T-enhancement Type: Nice-to-have but not required C-segmentation Component: Segmentation S-medium Size: Less than a week (larger bug fix or enhancement) labels Apr 13, 2023
@robertbastian robertbastian mentioned this issue Apr 20, 2023
Merged
@robertbastian
Copy link
Member

Closing #3301 for now

@sffc sffc added this to the 1.x Priority ⟨P2⟩ milestone Apr 20, 2023
@robertbastian robertbastian added the discuss-priority Discuss at the next ICU4X meeting label May 11, 2023
@robertbastian robertbastian removed their assignment May 12, 2023
@robertbastian robertbastian removed the discuss-priority Discuss at the next ICU4X meeting label May 12, 2023
@robertbastian
Copy link
Member

Discussion: it should be possible to use simd intrinsics even from unaligned data, @sffc has some ARM code that maintains performance (please post)

@sffc
Copy link
Member Author

sffc commented May 12, 2023

Discussion: it should be possible to use simd intrinsics even from unaligned data, @sffc has some ARM code that maintains performance (please post)

#3430

@sffc
Copy link
Member Author

sffc commented Jan 4, 2025

Wonder if processing-in-memory (PIM) could improve the performance

https://techxplore.com/news/2024-11-software-package-bypass-cpu-efficient.html

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@pdogr pdogr

Labels
C-segmentation Component: Segmentation S-medium Size: Less than a week (larger bug fix or enhancement) T-enhancement Type: Nice-to-have but not required
Projects
None yet
Milestone
2.x Priority ⟨P2⟩
Development

No branches or pull requests
3 participants
@sffc @robertbastian @pdogr