llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-shuffle-vector.s16.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer -o - %s | FileCheck -check-prefix=GFX8 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -run-pass=legalizer -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -run-pass=legalizer -o - %s | FileCheck -check-prefix=GFX9 %s

---
name: shufflevector_v2s16_v2s16_undef_undef
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_undef_undef
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[C]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[C]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_undef_undef
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[DEF]](s16), [[DEF]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, undef)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_0_undef
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_0_undef
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_0_undef
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[DEF]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, undef)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_undef_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_undef_0
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[COPY2]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_undef_0
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[DEF]](s16), [[TRUNC]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_0_1
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_0_1
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_0_1
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, 1)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_1_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_1_0
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_1_0
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_0_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_0_0
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_0_0
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_1_1
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_1_1
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_1_1
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1, 1)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_2_2
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_2_2
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_2_2
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(2, 2)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_2_undef
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_2_undef
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_2_undef
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[DEF]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(2, undef)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_undef_2
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_undef_2
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[COPY2]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_undef_2
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[DEF]](s16), [[TRUNC]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 2)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_2_3
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_2_3
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_2_3
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(2, 3)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_3_2
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_3_2
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_3_2
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(3, 2)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_undef_3
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_undef_3
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[C1]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_undef_3
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[DEF]](s16), [[TRUNC]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 3)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_3_undef
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_3_undef
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[C1]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_3_undef
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[DEF:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[DEF]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(3, undef)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_3_3
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_3_3
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_3_3
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(3, 3)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_0_2
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_0_2
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_0_2
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, 2)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_2_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_2_0
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C1]]
    ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C1]]
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C2]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_2_0
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_3_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_3_0
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_3_0
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(3, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_0_3
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_0_3
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_0_3
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0, 3)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_1_2
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_1_2
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_1_2
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1, 2)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v2s16_2_1
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1

    ; GFX8-LABEL: name: shufflevector_v2s16_v2s16_2_1
    ; GFX8: liveins: $vgpr0, $vgpr1
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v2s16_2_1
    ; GFX9: liveins: $vgpr0, $vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<2 x s16>) = COPY $vgpr0
    %1:_(<2 x s16>) = COPY $vgpr1
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(2, 1)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v4s16_v3s16_2_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX8-LABEL: name: shufflevector_v4s16_v3s16_2_0
    ; GFX8: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX8-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX8-NEXT: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[BITCAST2]], [[C1]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST3:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[BITCAST1]], [[C1]]
    ; GFX8-NEXT: [[AND2:%[0-9]+]]:_(s32) = G_AND [[BITCAST]], [[C1]]
    ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND2]], [[C]](s32)
    ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL1]]
    ; GFX8-NEXT: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
    ; GFX8-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST3]](<2 x s16>), [[BITCAST4]](<2 x s16>)
    ; GFX8-NEXT: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v4s16_v3s16_2_0
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
    ; GFX9-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
    ; GFX9-NEXT: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
    ; GFX9-NEXT: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC3]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC2]](s16), [[TRUNC]](s16)
    ; GFX9-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR]](<2 x s16>), [[BUILD_VECTOR1]](<2 x s16>)
    ; GFX9-NEXT: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
    %0:_(<4 x s16>) = COPY $vgpr0_vgpr1
    %1:_(<4 x s16>) = COPY $vgpr2_vgpr3
    %2:_(<3 x s16>) = G_EXTRACT %0, 0
    %3:_(<3 x s16>) = G_EXTRACT %1, 0
    %4:_(<4 x s16>) = G_SHUFFLE_VECTOR %2, %3, shufflemask(5, 1, 3, 0)
    $vgpr0_vgpr1 = COPY %4

...

---
name: shufflevector_v2s16_v4s16_1_0
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX8-LABEL: name: shufflevector_v2s16_v4s16_1_0
    ; GFX8: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX8-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](<2 x s32>)
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
    ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY2]], [[C1]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX8-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST1]](<2 x s32>)
    ; GFX8-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY3]], [[C]](s32)
    ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
    ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[LSHR1]], [[C2]]
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v4s16_1_0
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](<2 x s32>)
    ; GFX9-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
    ; GFX9-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY2]], [[C1]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX9-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST1]](<2 x s32>)
    ; GFX9-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY3]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<4 x s16>) = COPY $vgpr0_vgpr1
    %1:_(<4 x s16>) = COPY $vgpr2_vgpr3
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1, 0)
    $vgpr0 = COPY %2

...

---
name: shufflevector_v2s16_v4s16_1_3
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX8-LABEL: name: shufflevector_v2s16_v4s16_1_3
    ; GFX8: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX8-NEXT: {{  $}}
    ; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX8-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX8-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](<2 x s32>)
    ; GFX8-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
    ; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY2]], [[C]](s32)
    ; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX8-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST1]](<2 x s32>)
    ; GFX8-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
    ; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY3]], [[C]](s32)
    ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[LSHR1]], [[C]](s32)
    ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[LSHR]], [[SHL]]
    ; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
    ; GFX8-NEXT: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
    ;
    ; GFX9-LABEL: name: shufflevector_v2s16_v4s16_1_3
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[BITCAST:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](<2 x s32>)
    ; GFX9-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
    ; GFX9-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY2]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
    ; GFX9-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](<4 x s16>)
    ; GFX9-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST1]](<2 x s32>)
    ; GFX9-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
    ; GFX9-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY3]], [[C]](s32)
    ; GFX9-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
    ; GFX9-NEXT: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
    %0:_(<4 x s16>) = COPY $vgpr0_vgpr1
    %1:_(<4 x s16>) = COPY $vgpr2_vgpr3
    %2:_(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1, 3)
    $vgpr0 = COPY %2

...