Open haeunlee99 opened 5 days ago
RS uses Hopper MMAs that source A from registers. SS uses MMAs that source A from smem
Thank you for your response. I thought in hopper SS is used by default. I have several follow up questions.
Which of RS and SS is considered to be optimal? Is there a guide to reproduce cuBLAS like near optimal performance? (e.g. shared memory swizzle, thread block size, number of threads) I saw there are a lot of mainloops under "cutlass/include/cutlass/gemm/collective" and not sure which once would give optimal performance.
Is there also a guide I can reference to find optimal swizzle layout?
This is another question, just for check up. If I want to do FP16 tensor core operation with FP32 accumulation, is it correct to use C = D = FP32 in MMA and convert to FP16 in epilogue?
Thank you again!
What is your question?
What is difference between rs and ss? For example how are those two files different?
sm90_mma_array_tma_gmma_ss_warpspecialized.hpp sm90_mma_multistage_gmma_rs_warpspecialized.hpp
Thanks!