Skip to content

[Backend] Move shared memory address space to target info #7909

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

hgreving2304
Copy link
Contributor

In order to modularize downstream backends.

@@ -740,7 +740,13 @@ static FailureOr<SmallVector<Value>> lowerTMemLdStFromTypes(

struct TensorMemoryLoadOpConversion
: public ConvertOpToLLVMPattern<triton::nvidia_gpu::TMEMLoadOp> {
using ConvertOpToLLVMPattern::ConvertOpToLLVMPattern;

explicit TensorMemoryLoadOpConversion(LLVMTypeConverter &typeConverter,
Copy link
Collaborator

Choose a reason for hiding this comment

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

do we need to pass the target info for the files that are nvidia specific?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

We don't need as far as downstream is concerned, but it'll make it more consistent and have only one place where "3" is spelled out. If you don't want that, I can revert these parts

@hgreving2304 hgreving2304 force-pushed the user/hgreving/smem_targetinfo branch from 44a3100 to ed1e0b4 Compare August 20, 2025 14:25
In order to modularize downstream backends.
@hgreving2304 hgreving2304 force-pushed the user/hgreving/smem_targetinfo branch from ed1e0b4 to d286e54 Compare August 20, 2025 14:28
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