fix: fence_proxy for async global

This commit is contained in:
2026-05-24 03:44:26 +00:00
parent 3b6f19043f
commit 7b0b3ad1fc

View File

@@ -394,7 +394,8 @@ class FmhaKernel:
gP_flat = cute.make_tensor(tCgP.iterator, cute.coalesce(tCgP.layout))
for idx in cutlass.range(cute.size(rP_flat), vectorize=True):
gP_flat[idx] = rP_flat[idx]
cute.arch.fence_proxy("async.global", space="cta")
# Ensure gP writes are visible before TMA reads
cute.arch.fence_proxy("async", space="cta")
cute.arch.fence_proxy("async.shared", space="cta")
if kt > 0:
for i in range(n_corr_tiles):