[llvm] [VectorCombine] foldShuffleChainsToReduce - add FADD/FMUL handling (PR #201302)

[Simon Pilgrim via llvm-commits]

================
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=vector-combine -mtriple=x86_64-unknown-linux-gnu -S | FileCheck %s
+
+; Verify that FP reduction folding works correctly with the X86 cost model.
+
+define float @test_reduce_v8f32_fadd_x86(<8 x float> %a0) {
+; CHECK-LABEL: define float @test_reduce_v8f32_fadd_x86(
+; CHECK-SAME: <8 x float> [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call reassoc float @llvm.vector.reduce.fadd.v8f32(float -0.000000e+00, <8 x float> [[A0]])
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %1 = shufflevector <8 x float> %a0, <8 x float> poison, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison>
+  %2 = fadd reassoc <8 x float> %a0, %1
+  %3 = shufflevector <8 x float> %2, <8 x float> poison, <8 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+  %4 = fadd reassoc <8 x float> %2, %3
+  %5 = shufflevector <8 x float> %4, <8 x float> poison, <8 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+  %6 = fadd reassoc <8 x float> %4, %5
+  %7 = extractelement <8 x float> %6, i64 0
+  ret float %7
+}
+
+define float @test_reduce_v4f32_fmul_x86(<4 x float> %a0) {
+; CHECK-LABEL: define float @test_reduce_v4f32_fmul_x86(
+; CHECK-SAME: <4 x float> [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call reassoc float @llvm.vector.reduce.fmul.v4f32(float 1.000000e+00, <4 x float> [[A0]])
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %1 = shufflevector <4 x float> %a0, <4 x float> poison, <4 x i32> <i32 2, i32 3, i32 poison, i32 poison>
+  %2 = fmul reassoc <4 x float> %a0, %1
+  %3 = shufflevector <4 x float> %2, <4 x float> poison, <4 x i32> <i32 1, i32 poison, i32 poison, i32 poison>
+  %4 = fmul reassoc <4 x float> %2, %3
----------------
RKSimon wrote:

add one negative test with bad fmf

https://github.com/llvm/llvm-project/pull/201302