; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -vector-library=MASSV -force-vector-interleave=1 \
; RUN:   -vectorizer-maximize-bandwidth -passes='default<O2>,inject-tli-mappings,loop-vectorize' \
; RUN:   -mtriple=powerpc64le-unknown-linux -S -mcpu=pwr9 2>&1 | FileCheck %s

define dso_local double @test(ptr %Arr) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <2 x double> [ zeroinitializer, [[ENTRY]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds nuw float, ptr [[ARR:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = fpext <2 x float> [[WIDE_LOAD]] to <2 x double>
; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast <2 x double> @__sind2(<2 x double> [[TMP1]])
; CHECK-NEXT:    [[TMP3]] = fadd fast <2 x double> [[TMP2]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 128
; CHECK-NEXT:    br i1 [[TMP4]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[DOTLCSSA:%.*]] = phi <2 x double> [ [[TMP3]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP5:%.*]] = tail call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> [[DOTLCSSA]])
; CHECK-NEXT:    ret double [[TMP5]]
;
entry:
  br label %for.cond

for.cond:
  %Sum.0 = phi double [ 0.000000e+00, %entry ], [ %add, %for.inc ]
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
  %cmp = icmp slt i32 %i.0, 128
  br i1 %cmp, label %for.body, label %for.cond.cleanup

for.cond.cleanup:
  br label %for.end

for.body:
  %idxprom = sext i32 %i.0 to i64
  %arrayidx = getelementptr inbounds float, ptr %Arr, i64 %idxprom
  %0 = load float, ptr %arrayidx, align 4
  %conv = fpext float %0 to double
  %1 = call fast double @llvm.sin.f64(double %conv)
  %add = fadd fast double %Sum.0, %1
  br label %for.inc

for.inc:
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:
  ret double %Sum.0
}

declare double @llvm.sin.f64(double)