llvm/llvm/test/CodeGen/ARM/2013-07-29-vector-or-combine.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc < %s -mcpu=cortex-a8 -arm-atomic-cfg-tidy=0 | FileCheck %s
; ModuleID = 'bugpoint-reduced-simplified.bc'
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:64:128-a0:0:64-n32-S64"
target triple = "armv7--linux-gnueabi"

; CHECK-LABEL: function
define void @function() {
; CHECK-LABEL: function:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    mov r0, #0
; CHECK-NEXT:    cmp r0, #0
; CHECK-NEXT:    bxne lr
; CHECK-NEXT:  .LBB0_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vld1.32 {d16, d17}, [r0]
; CHECK-NEXT:    adr r0, .LCPI0_0
; CHECK-NEXT:    vbic.i32 q8, #0xff
; CHECK-NEXT:    vld1.64 {d18, d19}, [r0:128]
; CHECK-NEXT:    vorr q8, q8, q9
; CHECK-NEXT:    vst1.32 {d16, d17}, [r0]
; CHECK-NEXT:    b .LBB0_1
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:  .LCPI0_0:
; CHECK-NEXT:    .long 1 @ 0x1
; CHECK-NEXT:    .long 2 @ 0x2
; CHECK-NEXT:    .long 3 @ 0x3
; CHECK-NEXT:    .long 4 @ 0x4
entry:
  br i1 undef, label %vector.body, label %for.end

vector.body:
  %wide.load = load <4 x i32>, ptr undef, align 4
  %0 = and <4 x i32> %wide.load, <i32 -16711936, i32 -16711936, i32 -16711936, i32 -16711936>
  %1 = sub <4 x i32> %wide.load, zeroinitializer
  %2 = and <4 x i32> %1, <i32 16711680, i32 16711680, i32 16711680, i32 16711680>
  %3 = or <4 x i32> %0, <i32 1, i32 2, i32 3, i32 4>
  %4 = or <4 x i32> %3, %2
  store <4 x i32> %4, ptr undef, align 4
  br label %vector.body

for.end:
  ret void
}