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

Avoid unnecessary extra indirection in allocation helpers #99661

Open
jkotas opened this issue Mar 13, 2024 · 4 comments
Open

Avoid unnecessary extra indirection in allocation helpers #99661

jkotas opened this issue Mar 13, 2024 · 4 comments
Assignees
@VSadov
Labels
area-VM-coreclr tenet-performance Performance related issue
Milestone
9.0.0

Comments

@jkotas
Copy link
Member

jkotas commented Mar 13, 2024

Context: #99552 (comment)

The allocation helpers in CoreCLR have an unnecessary extra indirection. The alloc_context can be thread static directly. The extra indirection via Thread is unnecessary. The allocation helpers in native AOT do not have this indirection. It would be nice to port the improvement to regular CoreCLR and unify how the allocation helpers work.
@jkotas jkotas added area-VM-coreclr tenet-performance Performance related issue and removed area-PAL-coreclr labels Mar 13, 2024
@dotnet-policy-service dotnet-policy-service bot added the untriaged New issue has not been triaged by the area owner label Mar 13, 2024
@jkotas
Copy link
Member Author

jkotas commented Mar 13, 2024

@VSadov Are you interested in looking into this?

@jkotas jkotas mentioned this issue Mar 13, 2024
Closed
@VSadov
Copy link
Member

VSadov commented Mar 13, 2024

@VSadov Are you interested in looking into this?

yes, NativeAOT approach is a lot simpler. I’d like try porting it.

@mangod9
Copy link
Member

mangod9 commented Mar 13, 2024

assume the indirection isn't arm64 specific? But in theory it might help with cache locality?

@jkotas
Copy link
Member Author

jkotas commented Mar 13, 2024

assume the indirection isn't arm64 specific? But in theory it might help with cache locality?

Right

@VSadov VSadov self-assigned this Mar 13, 2024
@VSadov VSadov mentioned this issue Mar 13, 2024
Merged
@EgorBo EgorBo mentioned this issue Mar 20, 2024
Merged
@mangod9 mangod9 removed the untriaged New issue has not been triaged by the area owner label May 2, 2024
@mangod9 mangod9 added this to the 9.0.0 milestone May 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@VSadov VSadov

Labels
area-VM-coreclr tenet-performance Performance related issue
Projects
None yet
Milestone
9.0.0
Development

No branches or pull requests
3 participants
@jkotas @VSadov @mangod9