# RUN: llc -o /dev/null %s -mtriple=arm-eabi -mcpu=cortex-r52 -run-pass  machine-scheduler  -enable-misched -debug-only=machine-scheduler -misched-topdown 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=TOPDOWN
# RUN: llc -o /dev/null %s -mtriple=arm-eabi -mcpu=cortex-r52 -run-pass  machine-scheduler  -enable-misched -debug-only=machine-scheduler -misched-bottomup 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=BOTTOMUP
# REQUIRES: asserts
--- |
  ; ModuleID = 'foo.ll'
  source_filename = "foo.ll"
  target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
  target triple = "arm---eabi"

  %struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> }
  ; Function Attrs: nounwind
  define <8 x i8> @foo(i8* %A) {
    %tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8.p0i8(i8* %A, i32 8)
    %tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0
    %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 1
    %tmp4 = add <8 x i8> %tmp2, %tmp3
    ret <8 x i8> %tmp4
  }
  declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8.p0i8(i8*, i32)

# CHECK: ********** MI Scheduling **********
# CHECK: ScheduleDAGMILive::schedule starting
# CHECK: SU(1):   %1:qqpr = VLD4d8Pseudo %0:gpr, 8, 14, $noreg :: (load (s256) from %ir.A, align 8)
# CHECK: Latency            : 8
# CHECK: Single Issue       : true;
# CHECK: SU(2):   %4:dpr = VADDv8i8 %1.dsub_0:qqpr, %1.dsub_1:qqpr, 14, $noreg
# CHECK: Latency            : 5
# CHECK: Single Issue       : false;
# CHECK: SU(3):   %5:gpr, %6:gpr = VMOVRRD %4:dpr, 14, $noreg
# CHECK: Latency            : 4
# CHECK: Single Issue       : false;

# TOPDOWN: Scheduling SU(1) %1:qqpr = VLD4d8Pseudo
# TOPDOWN: Bump cycle to end group
# TOPDOWN: Scheduling SU(2) %4:dpr = VADDv8i8

# BOTTOMUP: Scheduling SU(2) %4:dpr = VADDv8i8
# BOTTOMUP: Scheduling SU(1) %1:qqpr = VLD4d8Pseudo
# BOTTOMUP: Bump cycle to begin group

...
---
name:            foo
alignment:       4
exposesReturnsTwice: false
legalized:       false
regBankSelected: false
selected:        false
tracksRegLiveness: true
registers:
  - { id: 0, class: gpr }
  - { id: 1, class: qqpr }
  - { id: 2, class: dpr }
  - { id: 3, class: dpr }
  - { id: 4, class: dpr }
  - { id: 5, class: gpr }
  - { id: 6, class: gpr }
liveins:
  - { reg: '$r0', virtual-reg: '%0' }
frameInfo:
  isFrameAddressTaken: false
  isReturnAddressTaken: false
  hasStackMap:     false
  hasPatchPoint:   false
  stackSize:       0
  offsetAdjustment: 0
  maxAlignment:    0
  adjustsStack:    false
  hasCalls:        false
  maxCallFrameSize: 0
  hasOpaqueSPAdjustment: false
  hasVAStart:      false
  hasMustTailInVarArgFunc: false
body:             |
  bb.0 (%ir-block.0):
    liveins: $r0

    %0 = COPY $r0
    %1 = VLD4d8Pseudo %0, 8, 14, $noreg :: (load (s256) from %ir.A, align 8)
    %4 = VADDv8i8 %1.dsub_0, %1.dsub_1, 14, $noreg
    %5, %6 = VMOVRRD %4, 14, $noreg
    $r0 = COPY %5
    $r1 = COPY %6
    BX_RET 14, $noreg, implicit $r0, implicit killed $r1

...