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

---
name: s_buffer_load_s32
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_s32
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(s32) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 4)
    ; GCN: S_ENDPGM 0, implicit [[AMDGPU_S_BUFFER_LOAD]](s32)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v3s32
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v3s32
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s32>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s32>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<3 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v3p3
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v3p3
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x p3>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x p3>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x p3>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x p3>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<3 x p3>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v6s16
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v6s16
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<8 x s16>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<6 x s16>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<8 x s16>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<6 x s16>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<6 x s16>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v6s32
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v6s32
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<8 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 24, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<6 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<8 x s32>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<6 x s32>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<6 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v3s64
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v3s64
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s64>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 24, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s64>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s64>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s64>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<3 x s64>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_v12s8
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_v12s8
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<16 x s8>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<12 x s8>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<16 x s8>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<12 x s8>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<12 x s8>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...

---
name: s_buffer_load_s96
body:             |
  bb.0:
    liveins: $sgpr0_sgpr1_sgpr2_sgpr3

    ; GCN-LABEL: name: s_buffer_load_s96
    ; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    ; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
    ; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s32>), 0
    ; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s32>)
    %0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
    %1:_(s32) = G_CONSTANT i32 0
    %2:_(<3 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
    S_ENDPGM 0, implicit %2

...