fix cp.async L2 prefetch typo (#1187)

This commit is contained in:
reed
2023-11-28 16:58:04 -05:00
committed by GitHub
parent 8098336d51
commit eb01d5449d
+1 -1
View File
@@ -86,7 +86,7 @@ struct SM80_CP_ASYNC_CACHEGLOBAL
#if defined(CUTE_ARCH_CP_ASYNC_SM80_ENABLED)
TS const* gmem_ptr = &gmem_src;
uint32_t smem_int_ptr = cast_smem_ptr_to_uint(&smem_dst);
asm volatile("cp.async.cg.shared.global.L2::128BB [%0], [%1], %2;\n"
asm volatile("cp.async.cg.shared.global.L2::128B [%0], [%1], %2;\n"
:: "r"(smem_int_ptr),
"l"(gmem_ptr),
"n"(sizeof(TS)));