Skip to content

[DOCUMENTATION] Added documentation to the code that lowers reduce to llvm#1514

Merged
ptillet merged 2 commits into
mainfrom
zahi/reduce-documentation
Apr 12, 2023
Merged

[DOCUMENTATION] Added documentation to the code that lowers reduce to llvm#1514
ptillet merged 2 commits into
mainfrom
zahi/reduce-documentation

Conversation

@zahimoud
Copy link
Copy Markdown
Contributor

No description provided.

@zahimoud zahimoud requested a review from ptillet as a code owner April 12, 2023 01:29
}
// The order of the axes for the the threads within the warp
auto srcOrd = triton::gpu::getOrder(srcLayout);
// The elements owned by each thread, e.g. [2, 2] means that each thread
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not true. getSizePerThread is just the contiguous size. Also this comment isn't very useful as it almost just repeats the function call name. Maybe getSizePerThread should be renamed getContiguousSizePerThread and comments be there?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's clear, it wasn't confusing to me.

auto llvmIndexTy = getTypeConverter()->getIndexType();
auto elemPtrTy = LLVM::LLVMPointerType::get(llvmElemTy, 3);
auto indexPtrTy = LLVM::LLVMPointerType::get(llvmIndexTy, 3);
// The shared memory base address
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think this comment is very useful, it just repeats the name of the function below

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yea I agree.

@ptillet ptillet merged commit 081f640 into main Apr 12, 2023
@ptillet ptillet deleted the zahi/reduce-documentation branch April 12, 2023 02:15
pingzhuu pushed a commit to siliconflow/triton that referenced this pull request Apr 2, 2024
ZzEeKkAa pushed a commit to ZzEeKkAa/triton that referenced this pull request Aug 5, 2024
… in tt.dot operation lowering. (triton-lang#1514)

Support the repCluster field in tt.dot operation lowering.

---------

Signed-off-by: Tiotto, Ettore <ettore.tiotto@intel.com>
Co-authored-by: Tiotto, Ettore <ettore.tiotto@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants