1 ; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
3 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
4 target triple = "x86_64-apple-macosx10.8.0"
6 ; We will keep trying to vectorize the basic block even we already find vectorized store.
8 ; CHECK: store <2 x double>
10 define void @test1(double* %a, double* %b, double* %c, double* %d) {
12 %i0 = load double* %a, align 8
13 %i1 = load double* %b, align 8
14 %mul = fmul double %i0, %i1
15 %arrayidx3 = getelementptr inbounds double, double* %a, i64 1
16 %i3 = load double* %arrayidx3, align 8
17 %arrayidx4 = getelementptr inbounds double, double* %b, i64 1
18 %i4 = load double* %arrayidx4, align 8
19 %mul5 = fmul double %i3, %i4
20 store double %mul, double* %c, align 8
21 %arrayidx5 = getelementptr inbounds double, double* %c, i64 1
22 store double %mul5, double* %arrayidx5, align 8
23 %0 = bitcast double* %a to <4 x i32>*
24 %1 = load <4 x i32>* %0, align 8
25 %2 = bitcast double* %b to <4 x i32>*
26 %3 = load <4 x i32>* %2, align 8
27 %4 = mul <4 x i32> %1, %3
28 %5 = bitcast double* %d to <4 x i32>*
29 store <4 x i32> %4, <4 x i32>* %5, align 8