-
Notifications
You must be signed in to change notification settings - Fork 74
[XPU][TritonGEN] Revamp SIMD block memory access operations #2756
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
Merged
victor-eds
merged 4 commits into
intel:main
from
victor-eds:triton-gen-sub-group-block-memaccess
Nov 20, 2024
Merged
[XPU][TritonGEN] Revamp SIMD block memory access operations #2756
victor-eds
merged 4 commits into
intel:main
from
victor-eds:triton-gen-sub-group-block-memaccess
Nov 20, 2024
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Revamp `tritongen.simdblock[read|write]` operations: - Rename to `tritongen.sub_group_block_[read|write]` - Implement type verification in signature - Represent scalar block memory accesses with a scalar type instead of `vector<1xty>` - Revamp assembly format Signed-off-by: victor-eds <[email protected]>
0abb7b4 to
a0ea9f6
Compare
victor-eds
commented
Nov 19, 2024
sommerlukas
approved these changes
Nov 19, 2024
mfrancepillois
approved these changes
Nov 19, 2024
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.
LGTM
victor-eds
commented
Nov 19, 2024
Comment on lines
317
to
342
| def TritonGEN_SubGroupBlockMemoryAccessElementType | ||
| : AnyTypeOf<[I8, I16, I32, I64], | ||
| "Valid sub-group block memory access element type">; | ||
|
|
||
| def TritonGEN_SubGroupBlockMemoryAccessType | ||
| : AnyTypeOf<[TritonGEN_SubGroupBlockMemoryAccessElementType, | ||
| FixedVectorOfLengthAndType< | ||
| [2, 4, 8], | ||
| [TritonGEN_SubGroupBlockMemoryAccessElementType]>, | ||
| // Vectors of length 16 only allowed for i8 for now. | ||
| FixedVectorOfLengthAndType<[16], [I8]>], | ||
| "Valid sub-group block memory access type">; | ||
|
|
||
| def TritonGEN_SubGroupBlockMemoryAccessPointerType | ||
| : Type<And<[LLVM_AnyPointer.predicate, | ||
| Or<[CPred<"::llvm::cast<::mlir::LLVM::LLVMPointerType>($_self)" # | ||
| ".getAddressSpace() == " # | ||
| "static_cast<unsigned>(kCrossWorkgroup)">, | ||
| CPred<"::llvm::cast<::mlir::LLVM::LLVMPointerType>($_self)" # | ||
| ".getAddressSpace() == " # | ||
| "static_cast<unsigned>(kWorkgroup)">]>]>, | ||
| "LLVM pointer in local or global OpenCL address space", | ||
| "::mlir::LLVM::LLVMPointerType">; | ||
|
|
||
| def TritonGEN_SubGroupBlockReadOp: TritonGEN_Op<"sub_group_block_read"> { | ||
| let summary = "Sub-group block read."; |
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.
Reminder before merge: use spaces instead of tabs for indentation.
whitneywhtsang
approved these changes
Nov 19, 2024
chengjunlu
approved these changes
Nov 20, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Revamp
tritongen.simdblock[read|write]operations:tritongen.sub_group_block_[read|write]vector<1xty>Closes #2750