-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
[DOCUMENTATION] Added documentation to the code that lowers reduce to llvm #1514
Conversation
auto srcOrd = triton::gpu::getOrder(srcLayout); | ||
// The elements owned by each thread, e.g. [2, 2] means that each thread |
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.
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?
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.
I think it's clear, it wasn't confusing to me.
auto sizePerThread = triton::gpu::getSizePerThread(srcLayout); | ||
auto srcShape = srcTy.getShape(); | ||
|
||
auto llvmElemTy = getTypeConverter()->convertType(srcTy.getElementType()); | ||
auto llvmIndexTy = getTypeConverter()->getIndexType(); | ||
auto elemPtrTy = LLVM::LLVMPointerType::get(llvmElemTy, 3); | ||
auto indexPtrTy = LLVM::LLVMPointerType::get(llvmIndexTy, 3); | ||
// The shared memory base address |
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.
I don't think this comment is very useful, it just repeats the name of the function below
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.
Yea I agree.
… 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>
No description provided.