llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-zextload-local.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs  -o - %s | FileCheck -check-prefix=GFX6 %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs  -o - %s | FileCheck -check-prefix=GFX7 %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs  -o - %s | FileCheck -check-prefix=GFX7 %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX9 %s

---
name: zextload_local_s32_from_s8_align1
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins:  $vgpr0

    ; GFX6-LABEL: name: zextload_local_s32_from_s8_align1
    ; GFX6: liveins: $vgpr0
    ; GFX6-NEXT: {{  $}}
    ; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX6-NEXT: $m0 = S_MOV_B32 -1
    ; GFX6-NEXT: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX6-NEXT: $vgpr0 = COPY [[DS_READ_U8_]]
    ;
    ; GFX7-LABEL: name: zextload_local_s32_from_s8_align1
    ; GFX7: liveins: $vgpr0
    ; GFX7-NEXT: {{  $}}
    ; GFX7-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX7-NEXT: $m0 = S_MOV_B32 -1
    ; GFX7-NEXT: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX7-NEXT: $vgpr0 = COPY [[DS_READ_U8_]]
    ;
    ; GFX9-LABEL: name: zextload_local_s32_from_s8_align1
    ; GFX9: liveins: $vgpr0
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9-NEXT: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[COPY]], 0, 0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX9-NEXT: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
    %0:vgpr(p3) = COPY $vgpr0
    %1:vgpr(s32) = G_ZEXTLOAD %0 :: (load (s8), align 1, addrspace 3)
    $vgpr0 = COPY %1

...

---
name: zextload_local_s32_from_s16_align2
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins:  $vgpr0

    ; GFX6-LABEL: name: zextload_local_s32_from_s16_align2
    ; GFX6: liveins: $vgpr0
    ; GFX6-NEXT: {{  $}}
    ; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX6-NEXT: $m0 = S_MOV_B32 -1
    ; GFX6-NEXT: [[DS_READ_U16_:%[0-9]+]]:vgpr_32 = DS_READ_U16 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load (s16), addrspace 3)
    ; GFX6-NEXT: $vgpr0 = COPY [[DS_READ_U16_]]
    ;
    ; GFX7-LABEL: name: zextload_local_s32_from_s16_align2
    ; GFX7: liveins: $vgpr0
    ; GFX7-NEXT: {{  $}}
    ; GFX7-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX7-NEXT: $m0 = S_MOV_B32 -1
    ; GFX7-NEXT: [[DS_READ_U16_:%[0-9]+]]:vgpr_32 = DS_READ_U16 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load (s16), addrspace 3)
    ; GFX7-NEXT: $vgpr0 = COPY [[DS_READ_U16_]]
    ;
    ; GFX9-LABEL: name: zextload_local_s32_from_s16_align2
    ; GFX9: liveins: $vgpr0
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9-NEXT: [[DS_READ_U16_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[COPY]], 0, 0, implicit $exec :: (load (s16), addrspace 3)
    ; GFX9-NEXT: $vgpr0 = COPY [[DS_READ_U16_gfx9_]]
    %0:vgpr(p3) = COPY $vgpr0
    %1:vgpr(s32) = G_ZEXTLOAD %0 :: (load (s16), align 2, addrspace 3)
    $vgpr0 = COPY %1

...

# ---
# name: zextload_local_s16_from_s8_align1
# legalized:       true
# regBankSelected: true
# tracksRegLiveness: true

# body: |
#   bb.0:
#     liveins:  $vgpr0

#     %0:vgpr(p3) = COPY $vgpr0
#     %1:vgpr(s16) = G_ZEXTLOAD %0 :: (load (s8), align 1, addrspace 3)
#     %2:vgpr(s32) = G_ANYEXT %1
#     $vgpr0 = COPY %2

# ...

---
name: zextload_local_s32_from_s8_align1_offset4095
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins:  $vgpr0

    ; GFX6-LABEL: name: zextload_local_s32_from_s8_align1_offset4095
    ; GFX6: liveins: $vgpr0
    ; GFX6-NEXT: {{  $}}
    ; GFX6-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX6-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
    ; GFX6-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, dead [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
    ; GFX6-NEXT: $m0 = S_MOV_B32 -1
    ; GFX6-NEXT: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[V_ADD_CO_U32_e64_]], 0, 0, implicit $m0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX6-NEXT: $vgpr0 = COPY [[DS_READ_U8_]]
    ;
    ; GFX7-LABEL: name: zextload_local_s32_from_s8_align1_offset4095
    ; GFX7: liveins: $vgpr0
    ; GFX7-NEXT: {{  $}}
    ; GFX7-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX7-NEXT: $m0 = S_MOV_B32 -1
    ; GFX7-NEXT: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 4095, 0, implicit $m0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX7-NEXT: $vgpr0 = COPY [[DS_READ_U8_]]
    ;
    ; GFX9-LABEL: name: zextload_local_s32_from_s8_align1_offset4095
    ; GFX9: liveins: $vgpr0
    ; GFX9-NEXT: {{  $}}
    ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9-NEXT: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[COPY]], 4095, 0, implicit $exec :: (load (s8), addrspace 3)
    ; GFX9-NEXT: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
    %0:vgpr(p3) = COPY $vgpr0
    %1:vgpr(s32) = G_CONSTANT i32 4095
    %2:vgpr(p3) = G_PTR_ADD %0, %1
    %3:vgpr(s32) = G_ZEXTLOAD %2 :: (load (s8), align 1, addrspace 3)
    $vgpr0 = COPY %3

...