inst-select-pattern-add3.mir 13.4 KB
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s  | FileCheck -check-prefix=GFX8 %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s  | FileCheck -check-prefix=GFX9 %s
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s  | FileCheck -check-prefix=GFX10 %s

---

name:            add_s32_sgpr_sgpr_sgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $sgpr0, $sgpr1, $sgpr2
    ; GFX8-LABEL: name: add_s32_sgpr_sgpr_sgpr
    ; GFX8: liveins: $sgpr0, $sgpr1, $sgpr2
    ; GFX8: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
    ; GFX8: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], [[COPY1]], implicit-def $scc
    ; GFX8: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 [[S_ADD_I32_]], [[COPY2]], implicit-def $scc
    ; GFX8: S_ENDPGM 0, implicit [[S_ADD_I32_1]]
    ; GFX9-LABEL: name: add_s32_sgpr_sgpr_sgpr
    ; GFX9: liveins: $sgpr0, $sgpr1, $sgpr2
    ; GFX9: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
    ; GFX9: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], [[COPY1]], implicit-def $scc
    ; GFX9: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 [[S_ADD_I32_]], [[COPY2]], implicit-def $scc
    ; GFX9: S_ENDPGM 0, implicit [[S_ADD_I32_1]]
    ; GFX10-LABEL: name: add_s32_sgpr_sgpr_sgpr
    ; GFX10: liveins: $sgpr0, $sgpr1, $sgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
    ; GFX10: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], [[COPY1]], implicit-def $scc
    ; GFX10: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 [[S_ADD_I32_]], [[COPY2]], implicit-def $scc
    ; GFX10: S_ENDPGM 0, implicit [[S_ADD_I32_1]]
    %0:sgpr(s32) = COPY $sgpr0
    %1:sgpr(s32) = COPY $sgpr1
    %2:sgpr(s32) = COPY $sgpr2
    %3:sgpr(s32) = G_ADD %0, %1
    %4:sgpr(s32) = G_ADD %3, %2
    S_ENDPGM 0, implicit %4
...

---

name:            add_s32_vgpr_vgpr_vgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8-LABEL: name: add_s32_vgpr_vgpr_vgpr
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, [[COPY2]], 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4
    ; GFX9-LABEL: name: add_s32_vgpr_vgpr_vgpr
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD3_U32_:%[0-9]+]]:vgpr_32 = V_ADD3_U32 [[COPY]], [[COPY1]], [[COPY2]], implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD3_U32_]]
    ; GFX10-LABEL: name: add_s32_vgpr_vgpr_vgpr
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD3_U32_:%[0-9]+]]:vgpr_32 = V_ADD3_U32 [[COPY]], [[COPY1]], [[COPY2]], implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD3_U32_]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = G_ADD %0, %1
    %4:vgpr(s32) = G_ADD %3, %2
    S_ENDPGM 0, implicit %4
...

---

name:            add_s32_vgpr_vgpr_vgpr_multi_use
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8-LABEL: name: add_s32_vgpr_vgpr_vgpr_multi_use
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, [[COPY2]], 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4, implicit %3
    ; GFX9-LABEL: name: add_s32_vgpr_vgpr_vgpr_multi_use
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX9: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_]]
    ; GFX10-LABEL: name: add_s32_vgpr_vgpr_vgpr_multi_use
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX10: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(s32) = G_ADD %0, %1
    %4:vgpr(s32) = G_ADD %3, %2
    S_ENDPGM 0, implicit %4, implicit %3
...

---

name:            add_p3_vgpr_vgpr_vgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2

    ; GFX8-LABEL: name: add_p3_vgpr_vgpr_vgpr
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, [[COPY2]], 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4
    ; GFX9-LABEL: name: add_p3_vgpr_vgpr_vgpr
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX9: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    ; GFX10-LABEL: name: add_p3_vgpr_vgpr_vgpr
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX10: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    %0:vgpr(p3) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(p3) = G_PTR_ADD %0, %1
    %4:vgpr(p3) = G_PTR_ADD %3, %2
    S_ENDPGM 0, implicit %4
...

---

name:            add_p5_vgpr_vgpr_vgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2

    ; GFX8-LABEL: name: add_p5_vgpr_vgpr_vgpr
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, [[COPY2]], 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4
    ; GFX9-LABEL: name: add_p5_vgpr_vgpr_vgpr
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX9: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    ; GFX10-LABEL: name: add_p5_vgpr_vgpr_vgpr
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX10: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_ADD_U32_e64_]], [[COPY2]], 0, implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    %0:vgpr(p5) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(s32) = COPY $vgpr2
    %3:vgpr(p5) = G_PTR_ADD %0, %1
    %4:vgpr(p5) = G_PTR_ADD %3, %2
    S_ENDPGM 0, implicit %4
...

---

name:            add_p3_s32_vgpr_vgpr_vgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2

    ; GFX8-LABEL: name: add_p3_s32_vgpr_vgpr_vgpr
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY2]], %3, 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4
    ; GFX9-LABEL: name: add_p3_s32_vgpr_vgpr_vgpr
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX9: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY2]], [[V_ADD_U32_e64_]], 0, implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    ; GFX10-LABEL: name: add_p3_s32_vgpr_vgpr_vgpr
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX10: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY2]], [[V_ADD_U32_e64_]], 0, implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(p3) = COPY $vgpr2
    %3:vgpr(s32) = G_ADD %0, %1
    %4:vgpr(p3) = G_PTR_ADD %2, %3
    S_ENDPGM 0, implicit %4
...

---

name:            add_p5_s32_vgpr_vgpr_vgpr
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2

    ; GFX8-LABEL: name: add_p5_s32_vgpr_vgpr_vgpr
    ; GFX8: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX8: %3:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX8: %4:vgpr_32, dead %5:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY2]], %3, 0, implicit $exec
    ; GFX8: S_ENDPGM 0, implicit %4
    ; GFX9-LABEL: name: add_p5_s32_vgpr_vgpr_vgpr
    ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX9: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY2]], [[V_ADD_U32_e64_]], 0, implicit $exec
    ; GFX9: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    ; GFX10-LABEL: name: add_p5_s32_vgpr_vgpr_vgpr
    ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
    ; GFX10: $vcc_hi = IMPLICIT_DEF
    ; GFX10: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[COPY1]], 0, implicit $exec
    ; GFX10: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY2]], [[V_ADD_U32_e64_]], 0, implicit $exec
    ; GFX10: S_ENDPGM 0, implicit [[V_ADD_U32_e64_1]]
    %0:vgpr(s32) = COPY $vgpr0
    %1:vgpr(s32) = COPY $vgpr1
    %2:vgpr(p5) = COPY $vgpr2
    %3:vgpr(s32) = G_ADD %0, %1
    %4:vgpr(p5) = G_PTR_ADD %2, %3
    S_ENDPGM 0, implicit %4
...