test/CodeGen/AMDGPU/merge-m0.mir

# RUN: llc -march=amdgcn -amdgpu-enable-merge-m0 -verify-machineinstrs -run-pass si-fix-sgpr-copies %s -o - | FileCheck -check-prefix=GCN %s

# GCN-LABEL: name: merge-m0-many-init
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 65536
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 65536
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.2:
# GCN:      SI_INIT_M0 65536
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.3:
# GCN:      SI_INIT_M0 3

# GCN:    bb.4:
# GCN-NOT:  SI_INIT_M0
# GCN:      DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 4
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.5:
# GCN-NOT: SI_INIT_M0
# GCN:     DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 4
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.6:
# GCN:      SI_INIT_M0 -1,
# GCN-NEXT: DS_WRITE_B32
# GCN:      SI_INIT_M0 %2
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 %2
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
---
name: merge-m0-many-init
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sreg_32_xm0 }
body:             |
  bb.0.entry:
    successors: %bb.1, %bb.2

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.1:
    successors: %bb.2
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.2

  bb.2:
    successors: %bb.3
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.3

  bb.3:
    successors: %bb.4, %bb.5
    S_CBRANCH_VCCZ %bb.4, implicit undef $vcc
    S_BRANCH %bb.5

  bb.4:
    successors: %bb.6
    SI_INIT_M0 3, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 4, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.6

  bb.5:
    successors: %bb.6
    SI_INIT_M0 3, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 4, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.6

  bb.6:
    successors: %bb.0.entry, %bb.6
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    %2 = IMPLICIT_DEF
    SI_INIT_M0 %2, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 %2, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.6, implicit undef $vcc
    S_BRANCH %bb.0.entry

...

# GCN-LABEL: name: merge-m0-dont-hoist-past-init-with-different-initializer
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 65536
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN-NOT:  SI_INIT_M0 65536
# GCN-NOT:  SI_INIT_M0 -1

# GCN:    bb.2:
# GCN:      SI_INIT_M0 -1

# GCN:    bb.3:
# GCN:      SI_INIT_M0 -1
---
name: merge-m0-dont-hoist-past-init-with-different-initializer
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.2, %bb.3

    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.2, implicit undef $vcc
    S_BRANCH %bb.3

  bb.2:
    successors: %bb.4

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.4

  bb.3:
    successors: %bb.4

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.4

  bb.4:
    S_ENDPGM 0
...

# GCN-LABEL: name: merge-m0-after-prologue
# GCN:    bb.0.entry:
# GCN-NOT:  SI_INIT_M0
# GCN:      S_OR_B64
# GCN-NEXT: SI_INIT_M0

# GCN:     bb.1:
# GCN-NOT:   SI_INIT_M0 -1

# GCN:     bb.2:
# GCN-NOT:   SI_INIT_MO -1
---
name: merge-m0-after-prologue
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1, %bb.2
    liveins: $sgpr0_sgpr1

    $exec = S_OR_B64 $exec, killed $sgpr0_sgpr1, implicit-def $scc
    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.1:
    successors: %bb.3

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.3

  bb.2:
    successors: %bb.3

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.3

  bb.3:
    S_ENDPGM 0
...

# GCN-LABEL: name: move-m0-avoid-hazard
# GCN: $m0 = S_MOV_B32 -1
# GCN-NEXT: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: DS_GWS_INIT $vgpr0, 0, implicit $m0, implicit $exec
---
name: move-m0-avoid-hazard
body:             |
  bb.0:
    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
    $m0 = S_MOV_B32 -1
    DS_GWS_INIT $vgpr0, 0, implicit $m0, implicit $exec
...

# GCN-LABEL: name: move-m0-with-prologue
# GCN: $exec = S_OR_B64 $exec, killed $sgpr0_sgpr1, implicit-def $scc
# GCN: $m0 = S_MOV_B32 -1
# GCN-NEXT: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: DS_GWS_INIT $vgpr0, 0, implicit $m0, implicit $exec
---
name: move-m0-with-prologue
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1

    $exec = S_OR_B64 $exec, killed $sgpr0_sgpr1, implicit-def $scc
    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
    $m0 = S_MOV_B32 -1
    DS_GWS_INIT $vgpr0, 0, implicit $m0, implicit $exec
...

# GCN-LABEL: name: move-m0-different-initializer
# GCN: SI_INIT_M0 -1
# GCN-NEXT: %0:vgpr_32 = IMPLICIT_DEF
# GCN: SI_INIT_M0 65536
# GCN-NEXT: S_NOP
---
name: move-m0-different-initializer
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
body:             |
  bb.0:
    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_NOP 0
    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
...

# GCN-LABEL: name: move-m0-schedule-boundary
# GCN: S_SETREG
# GCN-NEXT: SI_INIT_M0 -1
---
name: move-m0-schedule-boundary
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
body:             |
  bb.0:
    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    S_SETREG_IMM32_B32 0, 1, implicit-def $mode, implicit $mode
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
...


# GCN-LABEL: name: m0-in-loop-0
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: $m0 = COPY %2

---
name: m0-in-loop-0
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-1
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN-NOT:      SI_INIT_M0 -1
# GCN: DS_WRITE_B32

---
name: m0-in-loop-1
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-2
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN: $m0 = COPY %2
# GCN-NEXT:      SENDMSG
# GCN-NEXT:      SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32

---
name: m0-in-loop-2
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-3
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN: $m0 = COPY %2
# GCN-NEXT:      SENDMSG
# GCN-NEXT:      SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32

---
name: m0-in-loop-3
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-4
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:  SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: $m0 = COPY %2
# GCN-NEXT:      SENDMSG

---
name: m0-in-loop-4
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-5
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:  SI_INIT_M0 65536
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT:  SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: $m0 = COPY %2
# GCN-NEXT:      SENDMSG

---
name: m0-in-loop-5
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.1, %bb.2

    SI_INIT_M0 65536, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.2

  bb.2:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-6
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:  SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: $m0 = COPY %2
# GCN-NEXT:      SENDMSG

---
name: m0-in-loop-6
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.2

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    S_BRANCH %bb.2

  bb.2:
    successors: %bb.3, %bb.1
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.3


  bb.3:
    S_ENDPGM 0
...

# GCN-LABEL: name: m0-in-loop-7
# GCN:    bb.0.entry:
# GCN:      SI_INIT_M0 -1
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: IMPLICIT_DEF
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.1:
# GCN:  SI_INIT_M0 -1
# GCN-NEXT: DS_WRITE_B32
# GCN-NEXT: DS_WRITE_B32

# GCN:    bb.2:
# GCN: $m0 = COPY %2
# GCN-NEXT:      SENDMSG

---
name: m0-in-loop-7
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: vgpr_32 }
  - { id: 2, class: sgpr_32 }
body:             |
  bb.0.entry:
    successors: %bb.1

    %0 = IMPLICIT_DEF
    %1 = IMPLICIT_DEF
    %2 = IMPLICIT_DEF
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.1

  bb.1:
    successors: %bb.2

    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    SI_INIT_M0 -1, implicit-def $m0
    DS_WRITE_B32 %0, %1, 0, 0, implicit $m0, implicit $exec
    S_BRANCH %bb.2

  bb.2:
    successors: %bb.3, %bb.1
    $m0 = COPY %2:sgpr_32
    S_SENDMSG 34, implicit $exec, implicit $m0
    S_CBRANCH_VCCZ %bb.1, implicit undef $vcc
    S_BRANCH %bb.3

  bb.3:
    S_ENDPGM 0
...