search

NVIDIA / cutlass

CUDA Templates for Linear Algebra Subroutines
Other
5.35k stars 903 forks source link

[QST]Why we have two consumer in WASP? #1678

Open ziyuhuang123 opened 1 month ago

ziyuhuang123 commented 1 month ago

I am learning https://github.com/NVIDIA/cutlass/blob/06b21349bcf6ddf6a1686a47a137ad1446579db9/include/cutlass/gemm/collective/sm90_mma_tma_gmma_ss_warpspecialized.hpp#L73 I am curious that why we have two consumer here? Just have one maybe better?

thakkarV commented 1 month ago

the file you point to does not have any information about number of consumers in it.

ziyuhuang123 commented 1 month ago

Sorry, here https://github.com/NVIDIA/cutlass/blob/06b21349bcf6ddf6a1686a47a137ad1446579db9/include/cutlass/gemm/kernel/sm90_gemm_tma_warpspecialized_cooperative.hpp#L321

github-actions[bot] commented 1 week ago

This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.