llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-mad_64_32.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX10 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX1100 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1150 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX1150 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs %s -o - 2>%t | FileCheck -check-prefix=GFX12 %s

---
name: mad_u64_u32_vvv
legalized: true
regBankSelected: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-LABEL: name: mad_u64_u32_vvv
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX10-NEXT: [[V_MAD_U64_U32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_e64_]], implicit [[V_MAD_U64_U32_e64_1]]
    ;
    ; GFX1100-LABEL: name: mad_u64_u32_vvv
    ; GFX1100: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX1100-NEXT: {{  $}}
    ; GFX1100-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX1100-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX1100-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX1100-NEXT: [[V_MAD_U64_U32_gfx11_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_gfx11_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_gfx11_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX1100-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_gfx11_e64_]], implicit [[V_MAD_U64_U32_gfx11_e64_1]]
    ;
    ; GFX1150-LABEL: name: mad_u64_u32_vvv
    ; GFX1150: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX1150-NEXT: {{  $}}
    ; GFX1150-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX1150-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX1150-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX1150-NEXT: [[V_MAD_U64_U32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX1150-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_e64_]], implicit [[V_MAD_U64_U32_e64_1]]
    ;
    ; GFX12-LABEL: name: mad_u64_u32_vvv
    ; GFX12: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX12-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX12-NEXT: [[V_MAD_U64_U32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_U64_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_U64_U32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX12-NEXT: S_ENDPGM 0, implicit [[V_MAD_U64_U32_e64_]], implicit [[V_MAD_U64_U32_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = COPY $vgpr3
    %4:vgpr(s64) = G_MERGE_VALUES %2, %3
    %5:vgpr(s64), %6:vcc(s1) = G_AMDGPU_MAD_U64_U32 %0, %1, %3
    S_ENDPGM 0, implicit %5, implicit %6
...

---
name: mad_i64_i32_vvv
legalized: true
regBankSelected: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-LABEL: name: mad_i64_i32_vvv
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX10-NEXT: [[V_MAD_I64_I32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX10-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_e64_]], implicit [[V_MAD_I64_I32_e64_1]]
    ;
    ; GFX1100-LABEL: name: mad_i64_i32_vvv
    ; GFX1100: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX1100-NEXT: {{  $}}
    ; GFX1100-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX1100-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX1100-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX1100-NEXT: [[V_MAD_I64_I32_gfx11_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_gfx11_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_gfx11_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX1100-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_gfx11_e64_]], implicit [[V_MAD_I64_I32_gfx11_e64_1]]
    ;
    ; GFX1150-LABEL: name: mad_i64_i32_vvv
    ; GFX1150: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX1150-NEXT: {{  $}}
    ; GFX1150-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX1150-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX1150-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX1150-NEXT: [[V_MAD_I64_I32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX1150-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_e64_]], implicit [[V_MAD_I64_I32_e64_1]]
    ;
    ; GFX12-LABEL: name: mad_i64_i32_vvv
    ; GFX12: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX12-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3
    ; GFX12-NEXT: [[V_MAD_I64_I32_e64_:%[0-9]+]]:vreg_64, [[V_MAD_I64_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_MAD_I64_I32_e64 [[COPY]], [[COPY1]], [[COPY2]], 0, implicit $exec
    ; GFX12-NEXT: S_ENDPGM 0, implicit [[V_MAD_I64_I32_e64_]], implicit [[V_MAD_I64_I32_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = COPY $vgpr3
    %4:vgpr(s64) = G_MERGE_VALUES %2, %3
    %5:vgpr(s64), %6:vcc(s1) = G_AMDGPU_MAD_I64_I32 %0, %1, %3
    S_ENDPGM 0, implicit %5, implicit %6
...