biondizzle/nvfp4-megamoe-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix asm constraint typo

Browse Source
This commit is contained in:
biondizzle
2026-05-28 14:25:04 +00:00
parent 36a50962b3
commit 8cb32cabc9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/unit/test_fmha_smem_p.cu
View File

@@ -148,7 +148,7 @@ test_fmha_smem_p(const bf16_t* __restrict__ q, const bf16_t* __restrict__ k,
float tmp[8];
asm volatile("tcgen05.ld.sync.aligned.32x32b.x8.b32 {%0,%1,%2,%3,%4,%5,%6,%7},[%8];"
: "=f"(tmp[0]),"=f"(tmp[1]),"=f"(tmp[2]),"=f"(tmp[3]),
"=f"(tmp[4]),"=f"(tmp[5]),"=f"(tmp[6]),"f"(tmp[7])
"=f"(tmp[4]),"=f"(tmp[5]),"=f"(tmp[6]),"=f"(tmp[7])
: "r"(tb + n*8));
asm volatile("tcgen05.wait::ld.sync.aligned;");
if (lane == 0) for (int c=0;c<8;c++) o_vals[n*8+c] = tmp[c];