Index: llvm/test/Transforms/SLPVectorizer/X86/slp-reduc-fma-loss.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/SLPVectorizer/X86/slp-reduc-fma-loss.ll
@@ -0,0 +1,46 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -S -mcpu=core-avx2 < %s | FileCheck %s
+
+; This test checks for a case when a horizontal reduction of floating-point
+; adds may look profitable, but is not because it eliminates generation of
+; floating-point FMAs that would be more profitable.
+; FIXME: We currently generate the horizontal reduction.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @foo() #0 {
+; CHECK-LABEL: @foo(
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[X_544:%.*]] = phi double [ 0.000000e+00, [[TMP0:%.*]] ], [ [[OP_EXTRA:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[X_557:%.*]] = uitofp i16 undef to double
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> poison, double [[X_557]], i32 0
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <4 x double> [[TMP1]], <4 x double> poison, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 0>
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul fast <4 x double> poison, [[SHUFFLE]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast double @llvm.vector.reduce.fadd.v4f64(double -0.000000e+00, <4 x double> [[TMP2]])
+; CHECK-NEXT:    [[OP_EXTRA]] = fadd fast double [[TMP3]], [[X_544]]
+; CHECK-NEXT:    br i1 undef, label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+  br label %loop
+
+loop:                                             ; preds = %loop, %0
+  %x.544 = phi double [ 0.000000e+00, %0 ], [ %x.616, %loop ]
+  %x.557 = uitofp i16 undef to double
+  %x.558 = fmul fast double undef, %x.557
+  %x.559 = fadd fast double %x.558, %x.544
+  %x.577 = fmul fast double undef, undef
+  %x.578 = fadd fast double %x.577, %x.559
+  %x.596 = fmul fast double undef, undef
+  %x.597 = fadd fast double %x.596, %x.578
+  %x.615 = fmul fast double undef, undef
+  %x.616 = fadd fast double %x.615, %x.597
+  br i1 undef, label %exit, label %loop
+
+exit:                                             ; preds = %loop
+  ret void
+}
+
+attributes #0 = { "unsafe-fp-math"="true" }