llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=aarch64 -O0 -run-pass=legalizer -global-isel-abort=1 %s -o - | FileCheck %s
---
name:            shuffle_v4i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v4i32
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[COPY]](<4 x s32>), [[COPY1]], shufflemask(0, 0, 0, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<4 x s32>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<4 x s32>) = COPY $q0
    %1:_(<4 x s32>) = COPY $q1
    %2:_(<4 x s32>) = G_SHUFFLE_VECTOR %0(<4 x s32>), %1, shufflemask(0, 0, 0, 0)
    $q0 = COPY %2(<4 x s32>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v2i64
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v2i64
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<2 x s64>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s64>), [[COPY1]], shufflemask(0, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<2 x s64>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<2 x s64>) = COPY $q0
    %1:_(<2 x s64>) = COPY $q1
    %2:_(<2 x s64>) = G_SHUFFLE_VECTOR %0(<2 x s64>), %1, shufflemask(0, 0)
    $q0 = COPY %2(<2 x s64>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v2p0
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v2p0
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x p0>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<2 x p0>) = COPY $q1
    ; CHECK-NEXT: [[PTRTOINT:%[0-9]+]]:_(<2 x s64>) = G_PTRTOINT [[COPY]](<2 x p0>)
    ; CHECK-NEXT: [[PTRTOINT1:%[0-9]+]]:_(<2 x s64>) = G_PTRTOINT [[COPY1]](<2 x p0>)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<2 x s64>) = G_SHUFFLE_VECTOR [[PTRTOINT]](<2 x s64>), [[PTRTOINT1]], shufflemask(0, 0)
    ; CHECK-NEXT: [[INTTOPTR:%[0-9]+]]:_(<2 x p0>) = G_INTTOPTR [[SHUF]](<2 x s64>)
    ; CHECK-NEXT: $q0 = COPY [[INTTOPTR]](<2 x p0>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<2 x p0>) = COPY $q0
    %1:_(<2 x p0>) = COPY $q1
    %2:_(<2 x p0>) = G_SHUFFLE_VECTOR %0(<2 x p0>), %1, shufflemask(0, 0)
    $q0 = COPY %2(<2 x p0>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v16i8
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v16i8
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<16 x s8>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<16 x s8>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<16 x s8>) = G_SHUFFLE_VECTOR [[COPY]](<16 x s8>), [[COPY1]], shufflemask(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<16 x s8>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<16 x s8>) = COPY $q0
    %1:_(<16 x s8>) = COPY $q1
    %2:_(<16 x s8>) = G_SHUFFLE_VECTOR %0(<16 x s8>), %1, shufflemask(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
    $q0 = COPY %2(<16 x s8>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v8i16
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v8i16
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<8 x s16>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<8 x s16>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<8 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<8 x s16>), [[COPY1]], shufflemask(0, 0, 0, 0, 0, 0, 0, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<8 x s16>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<8 x s16>) = COPY $q0
    %1:_(<8 x s16>) = COPY $q1
    %2:_(<8 x s16>) = G_SHUFFLE_VECTOR %0(<8 x s16>), %1, shufflemask(0, 0, 0, 0, 0, 0, 0, 0)
    $q0 = COPY %2(<8 x s16>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_1elt_mask
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $d0, $d1

    ; CHECK-LABEL: name: shuffle_1elt_mask
    ; CHECK: liveins: $d0, $d1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $d0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $d1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY [[COPY]](s64)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY [[COPY1]](s64)
    ; CHECK-NEXT: $d0 = COPY [[COPY2]](s64)
    ; CHECK-NEXT: $d1 = COPY [[COPY3]](s64)
    ; CHECK-NEXT: RET_ReallyLR implicit $d0, implicit $d1
    %0:_(s64) = COPY $d0
    %1:_(s64) = COPY $d1
    %3:_(s64) = G_SHUFFLE_VECTOR %0:_(s64), %1:_, shufflemask(0)
    %4:_(s64) = G_SHUFFLE_VECTOR %0:_(s64), %1:_, shufflemask(1)
    $d0 = COPY %3(s64)
    $d1 = COPY %4(s64)
    RET_ReallyLR implicit $d0, implicit $d1

...
---
name:            oversize_shuffle_v4i64
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1, $q2, $q3, $x0

    ; CHECK-LABEL: name: oversize_shuffle_v4i64
    ; CHECK: liveins: $q0, $q1, $q2, $q3, $x0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(<2 x s64>) = COPY $q2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(<2 x s64>) = COPY $q3
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<2 x s64>) = G_SHUFFLE_VECTOR [[COPY1]](<2 x s64>), [[COPY2]], shufflemask(1, 2)
    ; CHECK-NEXT: [[SHUF1:%[0-9]+]]:_(<2 x s64>) = G_SHUFFLE_VECTOR [[COPY3]](<2 x s64>), [[COPY]], shufflemask(1, 2)
    ; CHECK-NEXT: G_STORE [[SHUF]](<2 x s64>), [[COPY4]](p0) :: (store (<2 x s64>), align 32)
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY4]], [[C]](s64)
    ; CHECK-NEXT: G_STORE [[SHUF1]](<2 x s64>), [[PTR_ADD]](p0) :: (store (<2 x s64>) into unknown-address + 16)
    ; CHECK-NEXT: RET_ReallyLR
    %3:_(<2 x s64>) = COPY $q0
    %4:_(<2 x s64>) = COPY $q1
    %0:_(<4 x s64>) = G_CONCAT_VECTORS %3(<2 x s64>), %4(<2 x s64>)
    %5:_(<2 x s64>) = COPY $q2
    %6:_(<2 x s64>) = COPY $q3
    %1:_(<4 x s64>) = G_CONCAT_VECTORS %5(<2 x s64>), %6(<2 x s64>)
    %2:_(p0) = COPY $x0
    %7:_(<4 x s64>) = G_SHUFFLE_VECTOR %0(<4 x s64>), %1, shufflemask(3, 4, 7, 0)
    G_STORE %7(<4 x s64>), %2(p0) :: (store (<4 x s64>))
    RET_ReallyLR

...
---
name:            oversize_shuffle_v8i32_build_vector
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1, $q2, $q3, $x0

    ; CHECK-LABEL: name: oversize_shuffle_v8i32_build_vector
    ; CHECK: liveins: $q0, $q1, $q2, $q3, $x0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $q1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $q2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $q3
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[COPY]](<4 x s32>), [[C]](s64)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK-NEXT: [[EVEC1:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[COPY1]](<4 x s32>), [[C1]](s64)
    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 2
    ; CHECK-NEXT: [[EVEC2:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[COPY2]](<4 x s32>), [[C2]](s64)
    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 3
    ; CHECK-NEXT: [[EVEC3:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[COPY3]](<4 x s32>), [[C3]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[EVEC]](s32), [[EVEC1]](s32), [[EVEC2]](s32), [[EVEC3]](s32)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[COPY1]](<4 x s32>), [[COPY]], shufflemask(2, 6, 5, 3)
    ; CHECK-NEXT: G_STORE [[BUILD_VECTOR]](<4 x s32>), [[COPY4]](p0) :: (store (<4 x s32>), align 32)
    ; CHECK-NEXT: [[C4:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY4]], [[C4]](s64)
    ; CHECK-NEXT: G_STORE [[SHUF]](<4 x s32>), [[PTR_ADD]](p0) :: (store (<4 x s32>) into unknown-address + 16)
    ; CHECK-NEXT: RET_ReallyLR
    %3:_(<4 x s32>) = COPY $q0
    %4:_(<4 x s32>) = COPY $q1
    %0:_(<8 x s32>) = G_CONCAT_VECTORS %3(<4 x s32>), %4(<4 x s32>)
    %5:_(<4 x s32>) = COPY $q2
    %6:_(<4 x s32>) = COPY $q3
    %1:_(<8 x s32>) = G_CONCAT_VECTORS %5(<4 x s32>), %6(<4 x s32>)
    %2:_(p0) = COPY $x0
    %7:_(<8 x s32>) = G_SHUFFLE_VECTOR %0(<8 x s32>), %1, shufflemask(0, 5, 10, 15, 6, 2, 1, 7)
    G_STORE %7(<8 x s32>), %2(p0) :: (store (<8 x s32>))
    RET_ReallyLR

...
---
name:            oversize_shuffle_v6i64
alignment:       4
tracksRegLiveness: true
frameInfo:
  maxAlignment:    8
fixedStack:
  - { id: 0, offset: 24, size: 8, alignment: 8, isImmutable: true }
  - { id: 1, offset: 16, size: 8, alignment: 16, isImmutable: true }
  - { id: 2, offset: 8, size: 8, alignment: 8, isImmutable: true }
  - { id: 3, size: 8, alignment: 16, isImmutable: true }
body:             |
  bb.1:
    liveins: $d0, $d1, $d2, $d3, $d4, $d5, $d6, $d7, $x0

    ; CHECK-LABEL: name: oversize_shuffle_v6i64
    ; CHECK: liveins: $d0, $d1, $d2, $d3, $d4, $d5, $d6, $d7, $x0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $d0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $d1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $d2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $d3
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(s64) = COPY $d4
    ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(s64) = COPY $d5
    ; CHECK-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY $d6
    ; CHECK-NEXT: [[COPY7:%[0-9]+]]:_(s64) = COPY $d7
    ; CHECK-NEXT: [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.2
    ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (invariant load (s64) from %fixed-stack.2, align 16)
    ; CHECK-NEXT: [[FRAME_INDEX1:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.3
    ; CHECK-NEXT: [[LOAD1:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX1]](p0) :: (invariant load (s64) from %fixed-stack.3)
    ; CHECK-NEXT: [[COPY8:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY2]](s64), [[COPY3]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY4]](s64), [[COPY5]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY]](s64), [[COPY1]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY]](s64), [[COPY1]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR4:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY6]](s64), [[COPY7]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR5:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[LOAD]](s64), [[LOAD1]](s64)
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s64) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR]](<2 x s64>), [[C]](s64)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK-NEXT: [[EVEC1:%[0-9]+]]:_(s64) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR1]](<2 x s64>), [[C1]](s64)
    ; CHECK-NEXT: [[EVEC2:%[0-9]+]]:_(s64) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR4]](<2 x s64>), [[C]](s64)
    ; CHECK-NEXT: [[EVEC3:%[0-9]+]]:_(s64) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR2]](<2 x s64>), [[C1]](s64)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<2 x s64>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR3]](<2 x s64>), [[BUILD_VECTOR5]], shufflemask(1, 3)
    ; CHECK-NEXT: [[BUILD_VECTOR6:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[EVEC]](s64), [[EVEC1]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR7:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[EVEC2]](s64), [[EVEC3]](s64)
    ; CHECK-NEXT: G_STORE [[BUILD_VECTOR6]](<2 x s64>), [[COPY8]](p0) :: (store (<2 x s64>), align 64)
    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY8]], [[C2]](s64)
    ; CHECK-NEXT: G_STORE [[BUILD_VECTOR7]](<2 x s64>), [[PTR_ADD]](p0) :: (store (<2 x s64>) into unknown-address + 16)
    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
    ; CHECK-NEXT: [[PTR_ADD1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY8]], [[C3]](s64)
    ; CHECK-NEXT: G_STORE [[SHUF]](<2 x s64>), [[PTR_ADD1]](p0) :: (store (<2 x s64>) into unknown-address + 32, align 32)
    ; CHECK-NEXT: RET_ReallyLR
    %3:_(s64) = COPY $d0
    %4:_(s64) = COPY $d1
    %5:_(s64) = COPY $d2
    %6:_(s64) = COPY $d3
    %7:_(s64) = COPY $d4
    %8:_(s64) = COPY $d5
    %0:_(<6 x s64>) = G_BUILD_VECTOR %3(s64), %4(s64), %5(s64), %6(s64), %7(s64), %8(s64)
    %9:_(s64) = COPY $d6
    %10:_(s64) = COPY $d7
    %15:_(p0) = G_FRAME_INDEX %fixed-stack.3
    %11:_(s64) = G_LOAD %15(p0) :: (invariant load (s64) from %fixed-stack.3, align 16)
    %16:_(p0) = G_FRAME_INDEX %fixed-stack.2
    %12:_(s64) = G_LOAD %16(p0) :: (invariant load (s64) from %fixed-stack.2)
    %17:_(p0) = G_FRAME_INDEX %fixed-stack.1
    %13:_(s64) = G_LOAD %17(p0) :: (invariant load 8 from %fixed-stack.1, align 16)
    %18:_(p0) = G_FRAME_INDEX %fixed-stack.0
    %14:_(s64) = G_LOAD %18(p0) :: (invariant load 8 from %fixed-stack.0)
    %1:_(<6 x s64>) = G_BUILD_VECTOR %9(s64), %10(s64), %11(s64), %12(s64), %13(s64), %14(s64)
    %2:_(p0) = COPY $x0
    %19:_(<6 x s64>) = G_SHUFFLE_VECTOR %0(<6 x s64>), %1, shufflemask(3, 4, 7, 0, 1, 11)
    G_STORE %19(<6 x s64>), %2(p0) :: (store (<6 x s64>), align 64)
    RET_ReallyLR

...
---
name:            shuffle_v4i32_v1i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $w0, $w1, $w2

    ; CHECK-LABEL: name: shuffle_v4i32_v1i32
    ; CHECK: liveins: $w0, $w1, $w2
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $w1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $w2
    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(<4 x s32>) = G_IMPLICIT_DEF
    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF]](<4 x s32>)
    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[UV]](s32)
    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[UV]](s32)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR]](<4 x s32>), [[BUILD_VECTOR1]], shufflemask(0, 1, 5, 6)
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C]](s64)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK-NEXT: [[EVEC1:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C1]](s64)
    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 2
    ; CHECK-NEXT: [[EVEC2:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C2]](s64)
    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 3
    ; CHECK-NEXT: [[EVEC3:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C3]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[EVEC]](s32), [[EVEC1]](s32), [[EVEC2]](s32), [[EVEC3]](s32)
    ; CHECK-NEXT: $q0 = COPY [[BUILD_VECTOR2]](<4 x s32>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(s32) = COPY $w0
    %1:_(s32) = COPY $w1
    %2:_(s32) = COPY $w2
    %3:_(<3 x s32>) = G_BUILD_VECTOR %0(s32), %1(s32), %2(s32)
    %4:_(<4 x s32>) = G_SHUFFLE_VECTOR %3(<3 x s32>), %3, shufflemask(0, 1, 4, 5)
    $q0 = COPY %4(<4 x s32>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v4i32_v2i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $d1

    ; CHECK-LABEL: name: shuffle_v4i32_v2i32
    ; CHECK: liveins: $q0, $d1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $d0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $d1
    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(<2 x s32>) = G_IMPLICIT_DEF
    ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[DEF]](<2 x s32>)
    ; CHECK-NEXT: [[CONCAT_VECTORS1:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY1]](<2 x s32>), [[DEF]](<2 x s32>)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[CONCAT_VECTORS]](<4 x s32>), [[CONCAT_VECTORS1]], shufflemask(0, 1, 4, 5)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<4 x s32>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<2 x s32>) = COPY $d0
    %1:_(<2 x s32>) = COPY $d1
    %2:_(<4 x s32>) = G_SHUFFLE_VECTOR %0(<2 x s32>), %1, shufflemask(0, 1, 2, 3)
    $q0 = COPY %2(<4 x s32>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v8i16_v4i16
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $d0, $d1

    ; CHECK-LABEL: name: shuffle_v8i16_v4i16
    ; CHECK: liveins: $d0, $d1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $d0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $d1
    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
    ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[COPY]](<4 x s16>), [[DEF]](<4 x s16>)
    ; CHECK-NEXT: [[CONCAT_VECTORS1:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[COPY1]](<4 x s16>), [[DEF]](<4 x s16>)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<8 x s16>) = G_SHUFFLE_VECTOR [[CONCAT_VECTORS]](<8 x s16>), [[CONCAT_VECTORS1]], shufflemask(11, 10, 9, 8, 3, 2, 1, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<8 x s16>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<4 x s16>) = COPY $d0
    %1:_(<4 x s16>) = COPY $d1
    %2:_(<8 x s16>) = G_SHUFFLE_VECTOR %0(<4 x s16>), %1, shufflemask(7, 6, 5, 4, 3, 2, 1, 0)
    $q0 = COPY %2(<8 x s16>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v16i8_v8i8
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $d0, $d1

    ; CHECK-LABEL: name: shuffle_v16i8_v8i8
    ; CHECK: liveins: $d0, $d1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<8 x s8>) = COPY $d0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<8 x s8>) = COPY $d1
    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(<8 x s8>) = G_IMPLICIT_DEF
    ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s8>) = G_CONCAT_VECTORS [[COPY]](<8 x s8>), [[DEF]](<8 x s8>)
    ; CHECK-NEXT: [[CONCAT_VECTORS1:%[0-9]+]]:_(<16 x s8>) = G_CONCAT_VECTORS [[COPY1]](<8 x s8>), [[DEF]](<8 x s8>)
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<16 x s8>) = G_SHUFFLE_VECTOR [[CONCAT_VECTORS]](<16 x s8>), [[CONCAT_VECTORS1]], shufflemask(7, 21, 6, 4, 5, 3, 0, 0, 0, 0, 0, 0, 0, 0, 23, 0)
    ; CHECK-NEXT: $q0 = COPY [[SHUF]](<16 x s8>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %0:_(<8 x s8>) = COPY $d0
    %1:_(<8 x s8>) = COPY $d1
    %2:_(<16 x s8>) = G_SHUFFLE_VECTOR %0(<8 x s8>), %1, shufflemask(7, 13, 6, 4, 5, 3, 0, 0, 0, 0, 0, 0, 0, 0, 15, 0)
    $q0 = COPY %2(<16 x s8>)
    RET_ReallyLR implicit $q0

...
---
name:            size_shuffle_v6i32_v4i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $s0, $s1, $s2, $s3, $s4, $s5, $s6, $s7, $x0

    ; CHECK-LABEL: name: size_shuffle_v6i32_v4i32
    ; CHECK: liveins: $s0, $s1, $s2, $s3, $s4, $s5, $s6, $s7, $x0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $s0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $s1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $s2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $s3
    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32)
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $s4
    ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $s5
    ; CHECK-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $s6
    ; CHECK-NEXT: [[COPY7:%[0-9]+]]:_(s32) = COPY $s7
    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY4]](s32), [[COPY5]](s32), [[COPY6]](s32), [[COPY7]](s32)
    ; CHECK-NEXT: [[COPY8:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR]](<4 x s32>), [[BUILD_VECTOR1]], shufflemask(3, 4, 7, 0)
    ; CHECK-NEXT: [[SHUF1:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR]](<4 x s32>), [[BUILD_VECTOR1]], shufflemask(1, 5, undef, undef)
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C]](s64)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK-NEXT: [[EVEC1:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C1]](s64)
    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 2
    ; CHECK-NEXT: [[EVEC2:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C2]](s64)
    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 3
    ; CHECK-NEXT: [[EVEC3:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF]](<4 x s32>), [[C3]](s64)
    ; CHECK-NEXT: [[EVEC4:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF1]](<4 x s32>), [[C]](s64)
    ; CHECK-NEXT: [[EVEC5:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[SHUF1]](<4 x s32>), [[C1]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[EVEC]](s32), [[EVEC1]](s32)
    ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[EVEC2]](s32), [[EVEC3]](s32)
    ; CHECK-NEXT: [[BUILD_VECTOR4:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[EVEC4]](s32), [[EVEC5]](s32)
    ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[BUILD_VECTOR2]](<2 x s32>), [[BUILD_VECTOR3]](<2 x s32>)
    ; CHECK-NEXT: G_STORE [[CONCAT_VECTORS]](<4 x s32>), [[COPY8]](p0) :: (store (<4 x s32>), align 32)
    ; CHECK-NEXT: [[C4:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY8]], [[C4]](s64)
    ; CHECK-NEXT: G_STORE [[BUILD_VECTOR4]](<2 x s32>), [[PTR_ADD]](p0) :: (store (<2 x s32>) into unknown-address + 16, align 16)
    ; CHECK-NEXT: RET_ReallyLR
    %3:_(s32) = COPY $s0
    %4:_(s32) = COPY $s1
    %5:_(s32) = COPY $s2
    %6:_(s32) = COPY $s3
    %0:_(<4 x s32>) = G_BUILD_VECTOR %3(s32), %4(s32), %5(s32), %6(s32)
    %7:_(s32) = COPY $s4
    %8:_(s32) = COPY $s5
    %9:_(s32) = COPY $s6
    %10:_(s32) = COPY $s7
    %1:_(<4 x s32>) = G_BUILD_VECTOR %7(s32), %8(s32), %9(s32), %10(s32)
    %2:_(p0) = COPY $x0
    %19:_(<6 x s32>) = G_SHUFFLE_VECTOR %0(<4 x s32>), %1, shufflemask(3, 4, 7, 0, 1, 5)
    G_STORE %19(<6 x s32>), %2(p0) :: (store (<6 x s32>), align 32)
    RET_ReallyLR

...
---
name:            shuffle_v3i32_v4i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v3i32_v4i32
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[COPY]](<4 x s32>), [[COPY1]], shufflemask(0, 1, 4, undef)
    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[SHUF]](<4 x s32>)
    ; CHECK-NEXT: $w0 = COPY [[UV]](s32)
    ; CHECK-NEXT: RET_ReallyLR implicit $w0
    %0:_(<4 x s32>) = COPY $q0
    %1:_(<4 x s32>) = COPY $q1
    %2:_(<3 x s32>) = G_SHUFFLE_VECTOR %0(<4 x s32>), %1, shufflemask(0, 1, 4)
    %3:_(s32), %4:_(s32), %5:_(s32) = G_UNMERGE_VALUES %2(<3 x s32>)
    $w0 = COPY %3(s32)
    RET_ReallyLR implicit $w0

...
---
name:            shuffle_v2i32_v4i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v2i32_v4i32
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s32>) = G_SHUFFLE_VECTOR [[COPY]](<4 x s32>), [[COPY1]], shufflemask(0, 4, undef, undef)
    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<2 x s32>), [[UV1:%[0-9]+]]:_(<2 x s32>) = G_UNMERGE_VALUES [[SHUF]](<4 x s32>)
    ; CHECK-NEXT: $d0 = COPY [[UV]](<2 x s32>)
    ; CHECK-NEXT: RET_ReallyLR implicit $d0
    %0:_(<4 x s32>) = COPY $q0
    %1:_(<4 x s32>) = COPY $q1
    %2:_(<2 x s32>) = G_SHUFFLE_VECTOR %0(<4 x s32>), %1, shufflemask(0, 4)
    $d0 = COPY %2(<2 x s32>)
    RET_ReallyLR implicit $d0

...
---
name:            shuffle_v4i16_v8i16
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v4i16_v8i16
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<8 x s16>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<8 x s16>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<8 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<8 x s16>), [[COPY1]], shufflemask(15, 14, 13, 4, undef, undef, undef, undef)
    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<4 x s16>), [[UV1:%[0-9]+]]:_(<4 x s16>) = G_UNMERGE_VALUES [[SHUF]](<8 x s16>)
    ; CHECK-NEXT: $d0 = COPY [[UV]](<4 x s16>)
    ; CHECK-NEXT: RET_ReallyLR implicit $d0
    %0:_(<8 x s16>) = COPY $q0
    %1:_(<8 x s16>) = COPY $q1
    %2:_(<4 x s16>) = G_SHUFFLE_VECTOR %0(<8 x s16>), %1, shufflemask(15, 14, 13, 4)
    $d0 = COPY %2(<4 x s16>)
    RET_ReallyLR implicit $d0

...
---
name:            shuffle_v8i8_v16i8
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $q0, $q1

    ; CHECK-LABEL: name: shuffle_v8i8_v16i8
    ; CHECK: liveins: $q0, $q1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<16 x s8>) = COPY $q0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<16 x s8>) = COPY $q1
    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<16 x s8>) = G_SHUFFLE_VECTOR [[COPY]](<16 x s8>), [[COPY1]], shufflemask(7, 13, 6, 4, 17, 3, 0, 0, undef, undef, undef, undef, undef, undef, undef, undef)
    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(<8 x s8>), [[UV1:%[0-9]+]]:_(<8 x s8>) = G_UNMERGE_VALUES [[SHUF]](<16 x s8>)
    ; CHECK-NEXT: $d0 = COPY [[UV]](<8 x s8>)
    ; CHECK-NEXT: RET_ReallyLR implicit $d0
    %0:_(<16 x s8>) = COPY $q0
    %1:_(<16 x s8>) = COPY $q1
    %2:_(<8 x s8>) = G_SHUFFLE_VECTOR %0(<16 x s8>), %1, shufflemask(7, 13, 6, 4, 17, 3, 0, 0)
    $d0 = COPY %2(<8 x s8>)
    RET_ReallyLR implicit $d0

...
---
name:            size_shuffle_v4i32_v6i32
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $s0, $s1, $s2, $s3, $s4, $s5

    ; CHECK-LABEL: name: size_shuffle_v4i32_v6i32
    ; CHECK: liveins: $s0, $s1, $s2, $s3, $s4, $s5
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $s0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $s1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $s2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $s3
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $s4
    ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $s5
    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32)
    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY4]](s32), [[COPY5]](s32), [[DEF]](s32), [[DEF]](s32)
    ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32)
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 3
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR]](<4 x s32>), [[C]](s64)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK-NEXT: [[EVEC1:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR1]](<4 x s32>), [[C1]](s64)
    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK-NEXT: [[EVEC2:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR2]](<4 x s32>), [[C2]](s64)
    ; CHECK-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY [[C1]](s64)
    ; CHECK-NEXT: [[EVEC3:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s64)
    ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[EVEC]](s32), [[EVEC1]](s32), [[EVEC2]](s32), [[EVEC3]](s32)
    ; CHECK-NEXT: $q0 = COPY [[BUILD_VECTOR3]](<4 x s32>)
    ; CHECK-NEXT: RET_ReallyLR implicit $q0
    %3:_(s32) = COPY $s0
    %4:_(s32) = COPY $s1
    %5:_(s32) = COPY $s2
    %6:_(s32) = COPY $s3
    %7:_(s32) = COPY $s4
    %8:_(s32) = COPY $s5
    %0:_(<6 x s32>) = G_BUILD_VECTOR %3(s32), %4(s32), %5(s32), %6(s32), %7(s32), %8(s32)
    %19:_(<4 x s32>) = G_SHUFFLE_VECTOR %0(<6 x s32>), %0, shufflemask(3, 4, 7, 0)
    $q0 = COPY %19(<4 x s32>)
    RET_ReallyLR implicit $q0

...
---
name:            shuffle_v8i1_v1i8
alignment:       4
tracksRegLiveness: true
body:             |
  bb.1:
    liveins: $d0, $d1
    ; CHECK-LABEL: name: shuffle_v8i1_v1i8
    ; CHECK: liveins: $d0, $d1
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<8 x s8>) = COPY $d1
    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[COPY]](<8 x s8>)
    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s16) = G_EXTRACT_VECTOR_ELT [[ANYEXT]](<8 x s16>), [[C]](s64)
    ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[EVEC]](s16)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
    ; CHECK-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[ANYEXT1]], [[C1]]
    ; CHECK-NEXT: $w0 = COPY [[AND]](s32)
    ; CHECK-NEXT: RET_ReallyLR implicit $w0
    %2:_(<8 x s8>) = COPY $d0
    %0:_(<8 x s1>) = G_TRUNC %2:_(<8 x s8>)
    %3:_(<8 x s8>) = COPY $d1
    %1:_(<8 x s1>) = G_TRUNC %3:_(<8 x s8>)
    %4:_(s1) = G_SHUFFLE_VECTOR %0:_(<8 x s1>), %1:_, shufflemask(12)
    %5:_(s8) = G_ZEXT %4:_(s1)
    %6:_(s32) = G_ANYEXT %5:_(s8)
    $w0 = COPY %6:_(s32)
    RET_ReallyLR implicit $w0
...