================
@@ -183,10 +183,10 @@ define <2 x half> @local_atomic_fadd_v2f16_rtn(ptr
addrspace(3) %ptr, <2 x half>
define amdgpu_kernel void @local_atomic_fadd_v2bf16_noret(ptr addrspace(3)
%ptr, <2 x i16> %data) {
; GFX940-LABEL: local_atomic_fadd_v2bf16_noret:
; GFX940: ; %bb.0:
-; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
+; GFX940-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x24
----------------
arsenm wrote:
Why does this patch have so many test diffs? Before this patch, we would have
just missed out on a few folds after the _ec variants were introduced?
https://github.com/llvm/llvm-project/pull/96162
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
