AMDGPU: Use unsigned compare for eq/ne
For some reason there are both of these available, except
for scalar 64-bit compares which only has u64. I'm not sure
why there are both (I'm guessing it's for the one bit inputs we
don't use), but for consistency always using the
unsigned one.
llvm-svn: 282832
diff --git a/llvm/test/CodeGen/AMDGPU/spill-m0.ll b/llvm/test/CodeGen/AMDGPU/spill-m0.ll
index a4a4c11..2f99efd 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-m0.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-m0.ll
@@ -6,7 +6,7 @@
; XXX - Why does it like to use vcc?
; GCN-LABEL: {{^}}spill_m0:
-; GCN: s_cmp_lg_i32
+; GCN: s_cmp_lg_u32
; TOVGPR: s_mov_b32 vcc_hi, m0
; TOVGPR: v_writelane_b32 [[SPILL_VREG:v[0-9]+]], vcc_hi, 0