// split, we may need an expensive shuffle to get two in sync. This has the
// effect of making larger than legal compares (v8i32 for example)
// expensive.
- if (LT.second.getVectorNumElements() > 2) {
+ if (LT.second.isVector() && LT.second.getVectorNumElements() > 2) {
if (LT.first > 1)
return LT.first * BaseCost +
BaseT::getScalarizationOverhead(VecCondTy, true, false);
; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %v2i64 = icmp slt <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %v4i64 = icmp slt <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %v8i64 = icmp slt <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %v2i128 = icmp slt <2 x i128> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %v4i128 = icmp slt <4 x i128> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp slt <2 x i8> undef, undef
%v4i64 = icmp slt <4 x i64> undef, undef
%v8i64 = icmp slt <8 x i64> undef, undef
+ %v2i128 = icmp slt <2 x i128> undef, undef
+ %v4i128 = icmp slt <4 x i128> undef, undef
+
ret void
}