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

[XeGPU] SLM support for scattered tensors. #801

Open
akroviakov opened this issue Jul 5, 2024 · 0 comments
Open

[XeGPU] SLM support for scattered tensors. #801

akroviakov opened this issue Jul 5, 2024 · 0 comments

Comments

@akroviakov
Copy link
Contributor

akroviakov commented Jul 5, 2024 •
edited
Loading

Currently, scattered tensors in slm are not supported for load/store ops:
#xegpu.tdesc_attr<scattered = true, memory_scope=slm>>
They can only load/store to global memory (ugm), as indicated by the hardcoded sfid argument of the intrinsic call which is set to 15. Changing it to 14 should allow loads/stores to be performed upon shared local memory (slm).
fschlimb pushed a commit to fschlimb/mlir-extensions that referenced this issue Nov 15, 2024
@Garra1980
[Innersource] Switch to latest FS sim (and using latest option set) (i…
96761b0 
…ntel#801)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@akroviakov