Skip to content

Add sm121 (GB10) to the wide_n_simt 4-bit GEMM dispatch rule #2039

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

Open
yashb98 wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −2
Open

Add sm121 (GB10) to the wide_n_simt 4-bit GEMM dispatch rule #2039

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions csrc/gemm_4bit.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,11 +87,12 @@ static void gemm_4bit(
const bool undersubscribed =
(M <= 8 && mma_blocks * 3 <= num_sms * 2) || (hbm_arch && M == 4 && mma_blocks <= num_sms);

// sm89 (>=60 SMs) and sm120 (>=48 SMs): at M<=6 with wide N, SIMT saturates
// sm89 (>=60 SMs) and sm120/sm121 (>=48 SMs): at M<=6 with wide N, SIMT saturates
// bandwidth more efficiently than blocked MMA.
const bool wide_n_simt =
M <= 6 && mma_blocks >= num_sms &&
((cc_maj == 8 && cc_min == 9 && num_sms >= 60) || (cc_maj == 12 && cc_min == 0 && num_sms >= 48));
((cc_maj == 8 && cc_min == 9 && num_sms >= 60) || (cc_maj == 12 && cc_min == 0 && num_sms >= 48) ||
(cc_maj == 12 && cc_min == 1 && num_sms >= 48));

// GDDR tall-K (K>N): K-loop too long relative to output tile at small M.
const bool tall_k_simt = gddr_arch && K > N && M <= 17 && mma_blocks * 3 < num_sms;
Expand Down