; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -passes=slp-vectorizer,dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s 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" target triple = "x86_64-apple-macosx10.8.0" define i32 @foo(ptr nocapture %A, i32 %n, i32 %m) { ; CHECK-LABEL: @foo( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[N:%.*]], i32 0 ; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i32> [[SHUFFLE]], ; CHECK-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[TMP3]], splat (i32 9) ; CHECK-NEXT: store <4 x i32> [[TMP4]], ptr [[A:%.*]], align 4 ; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[TMP4]], i32 0 ; CHECK-NEXT: [[EXTERNALUSE1:%.*]] = add nsw i32 [[TMP6]], [[M:%.*]] ; CHECK-NEXT: [[EXTERNALUSE2:%.*]] = mul nsw i32 [[TMP6]], [[M]] ; CHECK-NEXT: [[ADD10:%.*]] = add nsw i32 [[EXTERNALUSE1]], [[EXTERNALUSE2]] ; CHECK-NEXT: ret i32 [[ADD10]] ; entry: %mul = mul nsw i32 %n, 5 %add = add nsw i32 %mul, 9 store i32 %add, ptr %A, align 4 %mul1 = mul nsw i32 %n, 9 %add2 = add nsw i32 %mul1, 9 %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 1 store i32 %add2, ptr %arrayidx3, align 4 %mul4 = shl i32 %n, 3 %add5 = add nsw i32 %mul4, 9 %arrayidx6 = getelementptr inbounds i32, ptr %A, i64 2 store i32 %add5, ptr %arrayidx6, align 4 %mul7 = mul nsw i32 %n, 10 %add8 = add nsw i32 %mul7, 9 %arrayidx9 = getelementptr inbounds i32, ptr %A, i64 3 store i32 %add8, ptr %arrayidx9, align 4 %externaluse1 = add nsw i32 %add, %m %externaluse2 = mul nsw i32 %add, %m ; we should add the extract cost only once and the store will be vectorized %add10 = add nsw i32 %externaluse1, %externaluse2 ret i32 %add10 }