Skip to content
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.

Sign up for GitHub

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

Jump to bottom

how does the threadblock_tile_offset read the global memory in gemm_splitk_parallel.h ? #1957

Open
pily1 opened this issue Nov 21, 2024 · 0 comments
Open

how does the threadblock_tile_offset read the global memory in gemm_splitk_parallel.h ? #1957

pily1 opened this issue Nov 21, 2024 · 0 comments
Labels
? - Needs Triage question Question

Comments

@pily1
Copy link

pily1 commented Nov 21, 2024

What is your question?
I test the example 06_splitK_gemm in 2080ti gpu,I want to know how does the threadblock read the global memory,I debug into the cutlass/include/cutlass/gemm/kernel/gemm_splitk_parallel.h file,I find the typename Mma::IteratorA iterator_A and the mma(gemm_k_iterations,accumulators,iterator_A,iterator_B,accumulators),but I can't find the mma‘s code implementation .
where can I find the mma code implementation ?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
? - Needs Triage question Question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@pily1