[SLP][NFC] Test for a follow-up fix of the the vector min/max instrinsic cost calculation.

[vporpo]

Summary

The code in this test should not have been vectorized.
It looks worse than the scalar code.

[ABataev]

LG

[vporpo]

Fixed function name in checks.

[fhahn]

Should this go into one of the existing max tests we already have for X86 (e.g. llvm/test/Transforms/SLPVectorizer/X86/arith-smax.ll). Also, do we need the same case for unsigned?

[vporpo]

Good point. I tried adding this function to arith-smax.ll but the issue is that the test maps multiple RUN lines to the same check-prefix and for this particular function that I am adding the output is actually different. I could fix this by adding a few more check-prefixes in arith-small.ll to avoid this conflict. But I think that arith-smax.ll is already quite a large test with four check-prefixes, so we should probably avoid making it even larger? I could rename this test to arith-smax-cost.ll and add the unsigned case? What do you think?

[fhahn]

t. But I think that arith-smax.ll is already quite a large test with four check-prefixes, so we should probably avoid making it even larger? I could rename this test to arith-smax-cost.ll and add the unsigned case? What do you think?

Yeah sounds not worth extending the existing test if it requires more surgery to the check lines. Renaming the file to be in line with the existing tests should be fine. Maybe arith-max-cost.ll so the unsigned test can also be included?

[vporpo]

Renamed test to arirth-max-cost.ll and included unsigned case.

[fhahn]

Lgtm thanks

llvm/test/Transforms/SLPVectorizer/X86/arith-max-cost.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -slp-vectorizer -mcpu=corei7-avx -mtriple=x86_64-unknown-linux -S | FileCheck %s
+
+; This test checks whether the cost of the vector max intrinsic is calculated
+; correctly. A max vector intrinsic combines the select and icmp instructions.
+; This maps to a single PMAX instruction in x86.
+define void @smax_intrinsic_cost(i64 %arg0, i64 %arg1) {
+; CHECK-LABEL: @smax_intrinsic_cost(
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> poison, i64 [[ARG0:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[ARG1:%.*]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp sgt <2 x i64> [[TMP2]], <i64 123, i64 456>
+; CHECK-NEXT:    [[TMP4:%.*]] = select <2 x i1> [[TMP3]], <2 x i64> [[TMP2]], <2 x i64> <i64 123, i64 456>
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i64> [[TMP4]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i64> [[TMP4]], i32 1
+; CHECK-NEXT:    [[ROOT:%.*]] = icmp sle i64 [[TMP5]], [[TMP6]]
+; CHECK-NEXT:    ret void
+;
+  %icmp0 = icmp sgt i64 %arg0, 123
+  %icmp1 = icmp sgt i64 %arg1, 456
+  %select0 = select i1 %icmp0, i64 %arg0, i64 123
+  %select1 = select i1 %icmp1, i64 %arg1, i64 456
+  %root = icmp sle i64 %select0, %select1
+  ret void
+}
+
+
+define void @umax_intrinsic_cost(i64 %arg0, i64 %arg1) {
+; CHECK-LABEL: @umax_intrinsic_cost(
+; CHECK-NEXT:    [[ICMP0:%.*]] = icmp ugt i64 [[ARG0:%.*]], 123
+; CHECK-NEXT:    [[ICMP1:%.*]] = icmp ugt i64 [[ARG1:%.*]], 456
+; CHECK-NEXT:    [[SELECT0:%.*]] = select i1 [[ICMP0]], i64 [[ARG0]], i64 123
+; CHECK-NEXT:    [[SELECT1:%.*]] = select i1 [[ICMP1]], i64 [[ARG1]], i64 456
+; CHECK-NEXT:    [[ROOT:%.*]] = icmp sle i64 [[SELECT0]], [[SELECT1]]
+; CHECK-NEXT:    ret void
+;
+  %icmp0 = icmp ugt i64 %arg0, 123
+  %icmp1 = icmp ugt i64 %arg1, 456
+  %select0 = select i1 %icmp0, i64 %arg0, i64 123
+  %select1 = select i1 %icmp1, i64 %arg1, i64 456
+  %root = icmp sle i64 %select0, %select1
+  ret void
+}