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

Optimize copyChunk in RootPPL #55

Open
dlunde opened this issue Sep 23, 2021 · 0 comments
Open

Optimize copyChunk in RootPPL #55

dlunde opened this issue Sep 23, 2021 · 0 comments
Labels
enhancement New feature or request

Comments

@dlunde
Copy link
Collaborator

dlunde commented Sep 23, 2021

We (Joey, David, and I) noticed that the copyChunk function in RootPPL can potentially be optimized further by doing aligned copies even when the source and target locations are not exactly aligned on the GPU. Currently, when unaligned, copyChunk resorts to memcpy as soon as this is not the case (and memcpy is quite inefficient on the GPU for some reason).
@dlunde dlunde added the enhancement New feature or request label Sep 23, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@dlunde