llvm/test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-build-vector.mir

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

# The G_ZEXT and G_SHL will be scalarized, introducing a
# G_UNMERGE_VALUES of G_BUILD_VECTOR. The artifact combiner should
# eliminate the pair.
---
name: revisit_build_vector_unmerge_user
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0_vgpr1

    ; GFX9-LABEL: name: revisit_build_vector_unmerge_user
    ; GFX9: liveins: $vgpr0_vgpr1
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
    ; GFX9-NEXT: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[UV]](s32)
    ; GFX9-NEXT: [[ZEXT1:%[0-9]+]]:_(s64) = G_ZEXT [[UV1]](s32)
    ; GFX9-NEXT: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[ZEXT]], [[C]](s32)
    ; GFX9-NEXT: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[ZEXT1]], [[C]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[SHL]](s64), [[SHL1]](s64)
    ; GFX9-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32) = G_CONSTANT i32 2
    %2:_(<2 x s32>) = G_BUILD_VECTOR %1, %1
    %3:_(<2 x s64>) = G_ZEXT %0
    %4:_(<2 x s64>) = G_SHL %3, %2
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...

---
name: copy_scalar
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX9-LABEL: name: copy_scalar
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[COPY]](s64)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0(s64)
    %3:_(s64) = G_MERGE_VALUES %1, %2
    $vgpr2_vgpr3= COPY %3
...

---
name: copy_vector_using_elements
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX9-LABEL: name: copy_vector_using_elements
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[COPY]](<2 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %3:_(<2 x s32>) = G_BUILD_VECTOR %1, %2
    $vgpr2_vgpr3= COPY %3
...

---
name: copy_vector_using_subvectors
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX9-LABEL: name: copy_vector_using_subvectors
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[COPY]](<4 x s16>)
    %0:_(<4 x s16>) = COPY $vgpr0_vgpr1
    %1:_(<2 x s16>), %2:_(<2 x s16>) = G_UNMERGE_VALUES %0(<4 x s16>)
    %3:_(<4 x s16>) = G_CONCAT_VECTORS %1, %2
    $vgpr2_vgpr3= COPY %3
...

---
name: shuffle_vector_elements
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX9-LABEL: name: shuffle_vector_elements
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV1]](s32), [[UV]](s32)
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %3:_(<2 x s32>) = G_BUILD_VECTOR %2, %1
    $vgpr2_vgpr3= COPY %3
...

---
name: insert_element
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2, $vgpr3_vgpr4

    ; GFX9-LABEL: name: insert_element
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2, $vgpr3_vgpr4
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr2
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV]](s32), [[COPY1]](s32)
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32) = COPY $vgpr2
    %2:_(s32), %3:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %4:_(<2 x s32>) = G_BUILD_VECTOR %2, %1
    $vgpr2_vgpr3= COPY %4
...

---
name: unmerge_to_sub_vectors
body: |
  bb.0:
    liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5, $vgpr6_vgpr7

    ; GFX9-LABEL: name: unmerge_to_sub_vectors
    ; GFX9: liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5, $vgpr6_vgpr7
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(<2 x s32>), [[UV1:%[0-9]+]]:_(<2 x s32>) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
    ; GFX9-NEXT: $vgpr4_vgpr5 = COPY [[UV]](<2 x s32>)
    ; GFX9-NEXT: $vgpr6_vgpr7 = COPY [[UV1]](<2 x s32>)
    %0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
    %1:_(s32), %2:_(s32), %3:_(s32), %4:_(s32) = G_UNMERGE_VALUES %0(<4 x s32>)
    %5:_(<2 x s32>) = G_BUILD_VECTOR %1, %2
    %6:_(<2 x s32>) = G_BUILD_VECTOR %3, %4
    $vgpr4_vgpr5= COPY %5
    $vgpr6_vgpr7= COPY %6
...

---
name: cant_unmerge_to_sub_vectors
body: |
  bb.0:
    liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5, $vgpr6_vgpr7

    ; GFX9-LABEL: name: cant_unmerge_to_sub_vectors
    ; GFX9: liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5, $vgpr6_vgpr7
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV]](s32), [[UV3]](s32)
    ; GFX9-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV1]](s32), [[UV2]](s32)
    ; GFX9-NEXT: $vgpr4_vgpr5 = COPY [[BUILD_VECTOR]](<2 x s32>)
    ; GFX9-NEXT: $vgpr6_vgpr7 = COPY [[BUILD_VECTOR1]](<2 x s32>)
    %0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
    %1:_(s32), %2:_(s32), %3:_(s32), %4:_(s32) = G_UNMERGE_VALUES %0(<4 x s32>)
    %5:_(<2 x s32>) = G_BUILD_VECTOR %1, %4
    %6:_(<2 x s32>) = G_BUILD_VECTOR %2, %3
    $vgpr4_vgpr5= COPY %5
    $vgpr6_vgpr7= COPY %6
...

---
name: concat
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7

    ; GFX9-LABEL: name: concat
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>)
    ; GFX9-NEXT: $vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<4 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
    %2:_(s32), %3:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %4:_(s32), %5:_(s32) = G_UNMERGE_VALUES %1(<2 x s32>)
    %6:_(<4 x s32>) = G_BUILD_VECTOR %2, %3, %4, %5
    $vgpr4_vgpr5_vgpr6_vgpr7= COPY %6
...

---
name: concat_same_vector
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5

    ; GFX9-LABEL: name: concat_same_vector
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY]](<2 x s32>)
    ; GFX9-NEXT: $vgpr2_vgpr3_vgpr4_vgpr5 = COPY [[CONCAT_VECTORS]](<4 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %3:_(<4 x s32>) = G_BUILD_VECTOR %1, %2, %1, %2
    $vgpr2_vgpr3_vgpr4_vgpr5= COPY %3
...

---
name: shuffle_not_concat
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7

    ; GFX9-LABEL: name: shuffle_not_concat
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
    ; GFX9-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[UV2]](s32), [[UV]](s32), [[UV1]](s32), [[UV3]](s32)
    ; GFX9-NEXT: $vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[BUILD_VECTOR]](<4 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
    %2:_(s32), %3:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %4:_(s32), %5:_(s32) = G_UNMERGE_VALUES %1(<2 x s32>)
    %6:_(<4 x s32>) = G_BUILD_VECTOR %4, %2, %3, %5
    $vgpr4_vgpr5_vgpr6_vgpr7= COPY %6
...

---
name: not_a_concat
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4, $vgpr5_vgpr6_vgpr7_vgpr8_vgpr9

    ; GFX9-LABEL: name: not_a_concat
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4, $vgpr5_vgpr6_vgpr7_vgpr8_vgpr9
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
    ; GFX9-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr4
    ; GFX9-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
    ; GFX9-NEXT: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
    ; GFX9-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<5 x s32>) = G_BUILD_VECTOR [[UV]](s32), [[UV1]](s32), [[UV2]](s32), [[UV3]](s32), [[COPY2]](s32)
    ; GFX9-NEXT: $vgpr5_vgpr6_vgpr7_vgpr8_vgpr9 = COPY [[BUILD_VECTOR]](<5 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
    %2:_(s32) = COPY $vgpr4
    %3:_(s32), %4:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %5:_(s32), %6:_(s32) = G_UNMERGE_VALUES %1(<2 x s32>)
    %7:_(<5 x s32>) = G_BUILD_VECTOR %3, %4, %5, %6, %2
    $vgpr5_vgpr6_vgpr7_vgpr8_vgpr9= COPY %7
...

---
name: value_finder_look_through_copy
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3

    ; GFX9-LABEL: name: value_finder_look_through_copy
    ; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
    ; GFX9-NEXT: $vgpr2_vgpr3 = COPY [[COPY]](<2 x s32>)
    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
    %1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0(<2 x s32>)
    %3:_(s32) = COPY %1
    %4:_(<2 x s32>) = G_BUILD_VECTOR %3, %2
    $vgpr2_vgpr3= COPY %4
...