; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -stop-after=finalize-isel < %s | FileCheck %s

declare void @readsMem(ptr) #0
declare void @writesMem(ptr) #1

define void @fence_loads(ptr %ptr) {
  ; CHECK-LABEL: name: fence_loads
  ; CHECK: bb.0 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $vgpr0, $vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
  ; CHECK-NEXT:   ATOMIC_FENCE 5, 1, mmra !0
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !1
  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load acquire (s8) from %ir.ptr, align 4)
  ; CHECK-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !2
  ; CHECK-NEXT:   FLAT_STORE_BYTE [[COPY3]], killed [[V_MOV_B32_e32_]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (store release (s8) into %ir.ptr, align 4)
  ; CHECK-NEXT:   SI_RETURN
  fence release,                                        !mmra !0
  %ld = load atomic i8, ptr %ptr acquire, align 4,      !mmra !2
  store atomic i8 1, ptr %ptr release, align 4,         !mmra !1
  ret void
}

define void @atomicrmw_acq(ptr %ptr) {
  ; CHECK-LABEL: name: atomicrmw_acq
  ; CHECK: bb.0 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $vgpr0, $vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !1
  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE killed [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load acquire (s8) from %ir.ptr)
  ; CHECK-NEXT:   SI_RETURN
  %old.2 = atomicrmw add ptr %ptr, i8 0 acquire,        !mmra !2
  ret void
}

define void @atomicrmw_rel(ptr %ptr) {
  ; CHECK-LABEL: name: atomicrmw_rel
  ; CHECK: bb.0 (%ir-block.0):
  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
  ; CHECK-NEXT:   liveins: $vgpr0, $vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -4
  ; CHECK-NEXT:   [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY3]], killed [[S_MOV_B32_]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_AND_B32_e64_]], %subreg.sub0, killed [[COPY2]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]]
  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 3
  ; CHECK-NEXT:   [[V_AND_B32_e64_1:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY3]], [[S_MOV_B32_1]], implicit $exec
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[S_MOV_B32_1]], killed [[V_AND_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B32_2:%[0-9]+]]:sreg_32 = S_MOV_B32 255
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 killed [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_2]], implicit $exec
  ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 [[V_LSHLREV_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[REG_SEQUENCE1]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load (s32) from %ir.AlignedAddr)
  ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.atomicrmw.start:
  ; CHECK-NEXT:   successors: %bb.2(0x04000000), %bb.1(0x7c000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[PHI:%[0-9]+]]:sreg_64 = PHI [[S_MOV_B64_]], %bb.0, %7, %bb.1
  ; CHECK-NEXT:   [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[FLAT_LOAD_DWORD]], %bb.0, %6, %bb.1
  ; CHECK-NEXT:   [[V_OR_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR_B32_e64 [[V_NOT_B32_e32_]], [[V_LSHLREV_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[V_AND_B32_e64_2:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[PHI1]], killed [[V_OR_B32_e64_]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_AND_B32_e64_2]], %subreg.sub0, [[PHI1]], %subreg.sub1
  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[REG_SEQUENCE2]], 0, 1, implicit $exec, implicit $flat_scr, mmra !2 :: (load store release monotonic (s32) on %ir.AlignedAddr)
  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !2
  ; CHECK-NEXT:   [[SI_IF_BREAK:%[0-9]+]]:sreg_64 = SI_IF_BREAK killed [[V_CMP_EQ_U32_e64_]], [[PHI]], implicit-def dead $scc
  ; CHECK-NEXT:   SI_LOOP [[SI_IF_BREAK]], %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   S_BRANCH %bb.2
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.2.atomicrmw.end:
  ; CHECK-NEXT:   [[PHI2:%[0-9]+]]:sreg_64 = PHI [[SI_IF_BREAK]], %bb.1
  ; CHECK-NEXT:   SI_END_CF [[PHI2]], implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   SI_RETURN
  %old.2 = atomicrmw add ptr %ptr, i8 0 release,        !mmra !1
  ret void
}

define void @cmpxchg(ptr %ptr) {
  ; CHECK-LABEL: name: cmpxchg
  ; CHECK: bb.0 (%ir-block.0):
  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
  ; CHECK-NEXT:   liveins: $vgpr0, $vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -4
  ; CHECK-NEXT:   [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY3]], killed [[S_MOV_B32_]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_AND_B32_e64_]], %subreg.sub0, killed [[COPY2]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]]
  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 3
  ; CHECK-NEXT:   [[V_AND_B32_e64_1:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY3]], [[S_MOV_B32_1]], implicit $exec
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[S_MOV_B32_1]], killed [[V_AND_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B32_2:%[0-9]+]]:sreg_32 = S_MOV_B32 255
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_2]], implicit $exec
  ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 killed [[V_LSHLREV_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B32_3:%[0-9]+]]:sreg_32 = S_MOV_B32 1
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_2:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_3]], implicit $exec
  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[REG_SEQUENCE1]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load (s32) from %ir.AlignedAddr)
  ; CHECK-NEXT:   [[V_AND_B32_e64_2:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 killed [[FLAT_LOAD_DWORD]], [[V_NOT_B32_e32_]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.partword.cmpxchg.loop:
  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.3(0x40000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[PHI:%[0-9]+]]:sreg_64 = PHI [[DEF]], %bb.0, %12, %bb.3
  ; CHECK-NEXT:   [[PHI1:%[0-9]+]]:sreg_64 = PHI [[S_MOV_B64_]], %bb.0, %13, %bb.3
  ; CHECK-NEXT:   [[PHI2:%[0-9]+]]:vgpr_32 = PHI [[V_AND_B32_e64_2]], %bb.0, %11, %bb.3
  ; CHECK-NEXT:   [[V_OR_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR_B32_e64 [[PHI2]], [[V_LSHLREV_B32_e64_2]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_OR_B32_e64_]], %subreg.sub0, [[PHI2]], %subreg.sub1
  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[REG_SEQUENCE2]], 0, 1, implicit $exec, implicit $flat_scr, mmra !1 :: (load store acquire acquire (s32) on %ir.AlignedAddr)
  ; CHECK-NEXT:   [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_NE_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI2]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B64_1:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
  ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
  ; CHECK-NEXT:   [[S_OR_B64_:%[0-9]+]]:sreg_64 = S_OR_B64 [[PHI]], $exec, implicit-def $scc
  ; CHECK-NEXT:   [[SI_IF:%[0-9]+]]:sreg_64 = SI_IF killed [[V_CMP_NE_U32_e64_]], %bb.3, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   S_BRANCH %bb.2
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.2.partword.cmpxchg.failure:
  ; CHECK-NEXT:   successors: %bb.3(0x80000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[V_AND_B32_e64_3:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[V_NOT_B32_e32_]], implicit $exec
  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[PHI2]], [[V_AND_B32_e64_3]], implicit $exec
  ; CHECK-NEXT:   [[S_ANDN2_B64_:%[0-9]+]]:sreg_64 = S_ANDN2_B64 [[S_OR_B64_]], $exec, implicit-def $scc
  ; CHECK-NEXT:   [[S_AND_B64_:%[0-9]+]]:sreg_64 = S_AND_B64 [[V_CMP_EQ_U32_e64_]], $exec, implicit-def $scc
  ; CHECK-NEXT:   [[S_OR_B64_1:%[0-9]+]]:sreg_64 = S_OR_B64 [[S_ANDN2_B64_]], [[S_AND_B64_]], implicit-def $scc
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.3.Flow:
  ; CHECK-NEXT:   successors: %bb.4(0x04000000), %bb.1(0x7c000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[PHI3:%[0-9]+]]:sreg_64 = PHI [[S_OR_B64_]], %bb.1, [[S_OR_B64_1]], %bb.2
  ; CHECK-NEXT:   [[PHI4:%[0-9]+]]:vgpr_32 = PHI [[DEF1]], %bb.1, [[V_AND_B32_e64_3]], %bb.2
  ; CHECK-NEXT:   SI_END_CF [[SI_IF]], implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sreg_64 = COPY [[PHI3]]
  ; CHECK-NEXT:   [[SI_IF_BREAK:%[0-9]+]]:sreg_64 = SI_IF_BREAK [[COPY5]], [[PHI1]], implicit-def dead $scc
  ; CHECK-NEXT:   SI_LOOP [[SI_IF_BREAK]], %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   S_BRANCH %bb.4
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.4.partword.cmpxchg.end:
  ; CHECK-NEXT:   [[PHI5:%[0-9]+]]:sreg_64 = PHI [[SI_IF_BREAK]], %bb.3
  ; CHECK-NEXT:   [[PHI6:%[0-9]+]]:vgpr_32 = PHI [[FLAT_ATOMIC_CMPSWAP_RTN]], %bb.3
  ; CHECK-NEXT:   SI_END_CF [[PHI5]], implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   SI_RETURN
  %pair = cmpxchg ptr %ptr, i8 0, i8 1 acquire acquire, !mmra !2
  ret void
}

declare <32 x half> @f()

; Variant of atomicrmw_rel that provoked a crash in SelectionDAG::copyExtraInfo
define void @atomicrmw_rel_deepcopy(ptr %ptr) {
  ; CHECK-LABEL: name: atomicrmw_rel_deepcopy
  ; CHECK: bb.0 (%ir-block.0):
  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
  ; CHECK-NEXT:   liveins: $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $vgpr0, $vgpr1, $vgpr31
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr31
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr15
  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr14
  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr13
  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr12
  ; CHECK-NEXT:   [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
  ; CHECK-NEXT:   [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
  ; CHECK-NEXT:   [[COPY9:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
  ; CHECK-NEXT:   [[COPY10:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
  ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY11:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
  ; CHECK-NEXT:   [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @f, target-flags(amdgpu-gotprel32-hi) @f, implicit-def dead $scc
  ; CHECK-NEXT:   [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM killed [[SI_PC_ADD_REL_OFFSET]], 0, 0 :: (dereferenceable invariant load (s64) from got, addrspace 4)
  ; CHECK-NEXT:   [[COPY12:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3
  ; CHECK-NEXT:   $sgpr4_sgpr5 = COPY [[COPY10]]
  ; CHECK-NEXT:   $sgpr6_sgpr7 = COPY [[COPY9]]
  ; CHECK-NEXT:   $sgpr8_sgpr9 = COPY [[COPY8]]
  ; CHECK-NEXT:   $sgpr10_sgpr11 = COPY [[COPY7]]
  ; CHECK-NEXT:   $sgpr12 = COPY [[COPY6]]
  ; CHECK-NEXT:   $sgpr13 = COPY [[COPY5]]
  ; CHECK-NEXT:   $sgpr14 = COPY [[COPY4]]
  ; CHECK-NEXT:   $sgpr15 = COPY [[COPY3]]
  ; CHECK-NEXT:   $vgpr31 = COPY [[COPY]]
  ; CHECK-NEXT:   $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY12]]
  ; CHECK-NEXT:   $sgpr30_sgpr31 = SI_CALL killed [[S_LOAD_DWORDX2_IMM]], @f, csr_amdgpu, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7, implicit-def $vgpr8, implicit-def $vgpr9, implicit-def $vgpr10, implicit-def $vgpr11, implicit-def $vgpr12, implicit-def $vgpr13, implicit-def $vgpr14, implicit-def $vgpr15
  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
  ; CHECK-NEXT:   [[COPY13:%[0-9]+]]:vgpr_32 = COPY $vgpr0
  ; CHECK-NEXT:   [[COPY14:%[0-9]+]]:vgpr_32 = COPY $vgpr1
  ; CHECK-NEXT:   [[COPY15:%[0-9]+]]:vgpr_32 = COPY $vgpr2
  ; CHECK-NEXT:   [[COPY16:%[0-9]+]]:vgpr_32 = COPY $vgpr3
  ; CHECK-NEXT:   [[COPY17:%[0-9]+]]:vgpr_32 = COPY $vgpr4
  ; CHECK-NEXT:   [[COPY18:%[0-9]+]]:vgpr_32 = COPY $vgpr5
  ; CHECK-NEXT:   [[COPY19:%[0-9]+]]:vgpr_32 = COPY $vgpr6
  ; CHECK-NEXT:   [[COPY20:%[0-9]+]]:vgpr_32 = COPY $vgpr7
  ; CHECK-NEXT:   [[COPY21:%[0-9]+]]:vgpr_32 = COPY $vgpr8
  ; CHECK-NEXT:   [[COPY22:%[0-9]+]]:vgpr_32 = COPY $vgpr9
  ; CHECK-NEXT:   [[COPY23:%[0-9]+]]:vgpr_32 = COPY $vgpr10
  ; CHECK-NEXT:   [[COPY24:%[0-9]+]]:vgpr_32 = COPY $vgpr11
  ; CHECK-NEXT:   [[COPY25:%[0-9]+]]:vgpr_32 = COPY $vgpr12
  ; CHECK-NEXT:   [[COPY26:%[0-9]+]]:vgpr_32 = COPY $vgpr13
  ; CHECK-NEXT:   [[COPY27:%[0-9]+]]:vgpr_32 = COPY $vgpr14
  ; CHECK-NEXT:   [[COPY28:%[0-9]+]]:vgpr_32 = COPY $vgpr15
  ; CHECK-NEXT:   [[COPY29:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -4
  ; CHECK-NEXT:   [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY29]], killed [[S_MOV_B32_]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_AND_B32_e64_]], %subreg.sub0, killed [[COPY11]], %subreg.sub1
  ; CHECK-NEXT:   [[COPY30:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]]
  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 3
  ; CHECK-NEXT:   [[V_AND_B32_e64_1:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY29]], [[S_MOV_B32_1]], implicit $exec
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[S_MOV_B32_1]], killed [[V_AND_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[S_MOV_B32_2:%[0-9]+]]:sreg_32 = S_MOV_B32 255
  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 killed [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_2]], implicit $exec
  ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 [[V_LSHLREV_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[REG_SEQUENCE1]], 0, 0, implicit $exec, implicit $flat_scr, mmra !0 :: (load (s32) from %ir.AlignedAddr)
  ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1.atomicrmw.start:
  ; CHECK-NEXT:   successors: %bb.2(0x04000000), %bb.1(0x7c000000)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[PHI:%[0-9]+]]:sreg_64 = PHI [[S_MOV_B64_]], %bb.0, %7, %bb.1
  ; CHECK-NEXT:   [[PHI1:%[0-9]+]]:vgpr_32 = PHI [[FLAT_LOAD_DWORD]], %bb.0, %6, %bb.1
  ; CHECK-NEXT:   [[V_OR_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR_B32_e64 [[V_NOT_B32_e32_]], [[V_LSHLREV_B32_e64_1]], implicit $exec
  ; CHECK-NEXT:   [[V_AND_B32_e64_2:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[PHI1]], killed [[V_OR_B32_e64_]], implicit $exec
  ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE killed [[V_AND_B32_e64_2]], %subreg.sub0, [[PHI1]], %subreg.sub1
  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY30]], killed [[REG_SEQUENCE2]], 0, 1, implicit $exec, implicit $flat_scr, mmra !0 :: (load store release monotonic (s32) on %ir.AlignedAddr)
  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !0
  ; CHECK-NEXT:   [[SI_IF_BREAK:%[0-9]+]]:sreg_64 = SI_IF_BREAK killed [[V_CMP_EQ_U32_e64_]], [[PHI]], implicit-def dead $scc
  ; CHECK-NEXT:   SI_LOOP [[SI_IF_BREAK]], %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   S_BRANCH %bb.2
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.2.atomicrmw.end:
  ; CHECK-NEXT:   [[PHI2:%[0-9]+]]:sreg_64 = PHI [[SI_IF_BREAK]], %bb.1
  ; CHECK-NEXT:   SI_END_CF [[PHI2]], implicit-def dead $exec, implicit-def dead $scc, implicit $exec
  ; CHECK-NEXT:   SI_RETURN
  %C = call <32 x half> @f()
  %old.2 = atomicrmw add ptr %ptr, i8 0 release, align 1, !mmra !0
  ret void
}

attributes #0 = { memory(read) }
attributes #1 = { memory(write) }

!0 = !{!"foo", !"bar"}
!1 = !{!"bux", !"baz"}
!2 = !{!0, !1}