test/Transforms/SLPVectorizer/X86/reduction.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=i386-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s

target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32-S128"
target triple = "i386-apple-macosx10.8.0"

; int foo(double *A, int n, int m) {
;   double sum = 0, v1 = 2, v0 = 3;
;   for (int i=0; i < n; ++i)
;     sum += 7*A[i*2] + 7*A[i*2+1];
;   return sum;
; }

define i32 @reduce(double* nocapture %A, i32 %n, i32 %m) {
; CHECK-LABEL: @reduce(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP13:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP13]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_015:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[SUM_014:%.*]] = phi double [ [[ADD6:%.*]], [[FOR_BODY]] ], [ 0.000000e+00, [[ENTRY]] ]
; CHECK-NEXT:    [[MUL:%.*]] = shl nsw i32 [[I_015]], 1
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i32 [[MUL]]
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = fmul <2 x double> <double 7.000000e+00, double 7.000000e+00>, [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[TMP2]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[TMP2]], i32 1
; CHECK-NEXT:    [[ADD5:%.*]] = fadd double [[TMP3]], [[TMP4]]
; CHECK-NEXT:    [[ADD6]] = fadd double [[SUM_014]], [[ADD5]]
; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_015]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]], label [[FOR_BODY]]
; CHECK:       for.cond.for.end_crit_edge:
; CHECK-NEXT:    [[PHITMP:%.*]] = fptosi double [[ADD6]] to i32
; CHECK-NEXT:    br label [[FOR_END]]
; CHECK:       for.end:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ [[PHITMP]], [[FOR_COND_FOR_END_CRIT_EDGE]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  %cmp13 = icmp sgt i32 %n, 0
  br i1 %cmp13, label %for.body, label %for.end

for.body:                                         ; preds = %entry, %for.body
  %i.015 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %sum.014 = phi double [ %add6, %for.body ], [ 0.000000e+00, %entry ]
  %mul = shl nsw i32 %i.015, 1
  %arrayidx = getelementptr inbounds double, double* %A, i32 %mul
  %0 = load double, double* %arrayidx, align 4
  %mul1 = fmul double %0, 7.000000e+00
  %add12 = or i32 %mul, 1
  %arrayidx3 = getelementptr inbounds double, double* %A, i32 %add12
  %1 = load double, double* %arrayidx3, align 4
  %mul4 = fmul double %1, 7.000000e+00
  %add5 = fadd double %mul1, %mul4
  %add6 = fadd double %sum.014, %add5
  %inc = add nsw i32 %i.015, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.for.end_crit_edge, label %for.body

for.cond.for.end_crit_edge:                       ; preds = %for.body
  %phitmp = fptosi double %add6 to i32
  br label %for.end

for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
  %sum.0.lcssa = phi i32 [ %phitmp, %for.cond.for.end_crit_edge ], [ 0, %entry ]
  ret i32 %sum.0.lcssa
}