llvm/test/Transforms/SLPVectorizer/X86/align.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -slp-vectorizer -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"

; Simple 3-pair chain with loads and stores
define void @test1(double* %a, double* %b, double* %c) {
; CHECK-LABEL: @test1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[AGG_TMP_I_I_SROA_0:%.*]] = alloca [3 x double], align 16
; CHECK-NEXT:    [[STORE1:%.*]] = getelementptr inbounds [3 x double], [3 x double]* [[AGG_TMP_I_I_SROA_0]], i64 0, i64 1
; CHECK-NEXT:    [[STORE2:%.*]] = getelementptr inbounds [3 x double], [3 x double]* [[AGG_TMP_I_I_SROA_0]], i64 0, i64 2
; CHECK-NEXT:    [[ARRAYIDX3:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[A]] to <2 x double>*
; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast double* [[B]] to <2 x double>*
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[STORE1]] to <2 x double>*
; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %agg.tmp.i.i.sroa.0 = alloca [3 x double], align 16
  %i0 = load double, double* %a
  %i1 = load double, double* %b
  %mul = fmul double %i0, %i1
  %store1 = getelementptr inbounds [3 x double], [3 x double]* %agg.tmp.i.i.sroa.0, i64 0, i64 1
  %store2 = getelementptr inbounds [3 x double], [3 x double]* %agg.tmp.i.i.sroa.0, i64 0, i64 2
  %arrayidx3 = getelementptr inbounds double, double* %a, i64 1
  %i3 = load double, double* %arrayidx3, align 8
  %arrayidx4 = getelementptr inbounds double, double* %b, i64 1
  %i4 = load double, double* %arrayidx4, align 8
  %mul5 = fmul double %i3, %i4
  store double %mul, double* %store1
  store double %mul5, double* %store2, align 16
  ret void
}

; Float has 4 byte abi alignment on x86_64. We must use the alignment of the
; value being loaded/stored not the alignment of the pointer type.

define void @test2(float * %a, float * %b) {
; CHECK-LABEL: @test2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[A1:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 1
; CHECK-NEXT:    [[A2:%.*]] = getelementptr inbounds float, float* [[A]], i64 2
; CHECK-NEXT:    [[A3:%.*]] = getelementptr inbounds float, float* [[A]], i64 3
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[A]] to <4 x float>*
; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT:    [[B1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 1
; CHECK-NEXT:    [[B2:%.*]] = getelementptr inbounds float, float* [[B]], i64 2
; CHECK-NEXT:    [[B3:%.*]] = getelementptr inbounds float, float* [[B]], i64 3
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast float* [[B]] to <4 x float>*
; CHECK-NEXT:    store <4 x float> [[TMP1]], <4 x float>* [[TMP2]], align 4
; CHECK-NEXT:    ret void
;
entry:
  %l0 = load float, float* %a
  %a1 = getelementptr inbounds float, float* %a, i64 1
  %l1 = load float, float* %a1
  %a2 = getelementptr inbounds float, float* %a, i64 2
  %l2 = load float, float* %a2
  %a3 = getelementptr inbounds float, float* %a, i64 3
  %l3 = load float, float* %a3
  store float %l0, float* %b
  %b1 = getelementptr inbounds float, float* %b, i64 1
  store float %l1, float* %b1
  %b2 = getelementptr inbounds float, float* %b, i64 2
  store float %l2, float* %b2
  %b3 = getelementptr inbounds float, float* %b, i64 3
  store float %l3, float* %b3
  ret void
}