-
Notifications
You must be signed in to change notification settings - Fork 75
[LoadStoreOpToLLVM] Improve rewriteTensorPointerStore
#4667
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR improves the rewriteTensorPointerStore function in the LoadStoreOpToLLVM conversion by removing a restrictive early check and refactoring the code for better clarity and maintainability. The changes enhance support for 2D block store operations with proper size constraints.
- Removes early failure condition that only allowed DPAS layout encoding
- Adds proper validation for 2D block store constraints (8 rows max, 64 bytes per row max)
- Refactors variable names and reorganizes code structure for better readability
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| LoadStoreOpToLLVM.cpp | Removes DPAS-only restriction, adds 2D block store constraints, and refactors variable naming |
| blockptr_store.mlir | Updates test expectations to match the reordered variable declarations |
third_party/intel/lib/TritonIntelGPUToLLVM/LoadStoreOpToLLVM.cpp
Outdated
Show resolved
Hide resolved
third_party/intel/lib/TritonIntelGPUToLLVM/LoadStoreOpToLLVM.cpp
Outdated
Show resolved
Hide resolved
Signed-off-by: Whitney Tsang <[email protected]>
6cba681 to
848cdaa
Compare
third_party/intel/lib/TritonIntelGPUToLLVM/LoadStoreOpToLLVM.cpp
Outdated
Show resolved
Hide resolved
Signed-off-by: Whitney Tsang <[email protected]>
This PR improves the
rewriteTensorPointerStore: