Codebase Browser
llvm
Go to App

llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.mfma.gfx940.mir 

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx940 -run-pass=amdgpu-regbankselect -regbankselect-fast -verify-machineinstrs %s -o - | FileCheck %s -check-prefix=FAST
# RUN: llc -mtriple=amdgcn -mcpu=gfx940 -run-pass=amdgpu-regbankselect -regbankselect-greedy -verify-machineinstrs %s -o - | FileCheck %s -check-prefix=GREEDY

---
name: mfma_i32_16x16x32_i8_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3

    ; FAST-LABEL: name: mfma_i32_16x16x32_i8_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.16x16x32.i8), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<4 x s32>), 0, 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    ; GREEDY-LABEL: name: mfma_i32_16x16x32_i8_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.16x16x32.i8), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<4 x s32>), 0, 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s64) = COPY $vgpr2_vgpr3
    %2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    %3:_(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.16x16x32.i8), %0, %1, %2, 0, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...

---
name: mfma_i32_32x32x16_i8_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15

    ; FAST-LABEL: name: mfma_i32_32x32x16_i8_vva
    ; FAST: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.32x32x16.i8), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<16 x s32>), 0, 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    ; GREEDY-LABEL: name: mfma_i32_32x32x16_i8_vva
    ; GREEDY: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.32x32x16.i8), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<16 x s32>), 0, 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s64) = COPY $vgpr2_vgpr3
    %2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    %3:_(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.i32.32x32x16.i8), %0, %1, %2, 0, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
...

---
name: mfma_f32_16x16x8_xf32_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3

    ; FAST-LABEL: name: mfma_f32_16x16x8_xf32_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.16x16x8.xf32), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<4 x s32>), 0, 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    ; GREEDY-LABEL: name: mfma_f32_16x16x8_xf32_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.16x16x8.xf32), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<4 x s32>), 0, 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s64) = COPY $vgpr2_vgpr3
    %2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    %3:_(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.16x16x8.xf32), %0, %1, %2, 0, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...

---
name: mfma_f32_32x32x4_xf32_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15

    ; FAST-LABEL: name: mfma_f32_32x32x4_xf32_vva
    ; FAST: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.32x32x4.xf32), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<16 x s32>), 0, 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    ; GREEDY-LABEL: name: mfma_f32_32x32x4_xf32_vva
    ; GREEDY: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.32x32x4.xf32), [[COPY]](s64), [[COPY1]](s64), [[COPY2]](<16 x s32>), 0, 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s64) = COPY $vgpr2_vgpr3
    %2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    %3:_(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.mfma.f32.32x32x4.xf32), %0, %1, %2, 0, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %3
...

---
name: smfmac_f32_16x16x32_f16_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20

    ; FAST-LABEL: name: smfmac_f32_16x16x32_f16_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.f16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    ; GREEDY-LABEL: name: smfmac_f32_16x16x32_f16_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.f16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    %3:_(s32) = COPY $vgpr20
    %4:_(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.f16), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...

---
name: smfmac_f32_32x32x16_f16_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20

    ; FAST-LABEL: name: smfmac_f32_32x32x16_f16_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.f16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    ; GREEDY-LABEL: name: smfmac_f32_32x32x16_f16_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.f16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    %3:_(s32) = COPY $vgpr20
    %4:_(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.f16), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %4
...

---
name: smfmac_f32_16x16x32_bf16_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20

    ; FAST-LABEL: name: smfmac_f32_16x16x32_bf16_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.bf16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    ; GREEDY-LABEL: name: smfmac_f32_16x16x32_bf16_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.bf16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    %3:_(s32) = COPY $vgpr20
    %4:_(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.16x16x32.bf16), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...

---
name: smfmac_f32_32x32x16_bf16_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20

    ; FAST-LABEL: name: smfmac_f32_32x32x16_bf16_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.bf16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    ; GREEDY-LABEL: name: smfmac_f32_32x32x16_bf16_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.bf16), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    %3:_(s32) = COPY $vgpr20
    %4:_(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.f32.32x32x16.bf16), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %4
...

---
name: smfmac_i32_16x16x64_i8_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20

    ; FAST-LABEL: name: smfmac_i32_16x16x64_i8_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.16x16x64.i8), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    ; GREEDY-LABEL: name: smfmac_i32_16x16x64_i8_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.16x16x64.i8), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<4 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[INT]](<4 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<4 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3
    %3:_(s32) = COPY $vgpr20
    %4:_(<4 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.16x16x64.i8), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...

---
name: smfmac_i32_32x32x32_i8_vva
legalized: true
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20

    ; FAST-LABEL: name: smfmac_i32_32x32x32_i8_vva
    ; FAST: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; FAST-NEXT: {{  $}}
    ; FAST-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; FAST-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; FAST-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; FAST-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; FAST-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.32x32x32.i8), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; FAST-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    ; GREEDY-LABEL: name: smfmac_i32_32x32x32_i8_vva
    ; GREEDY: liveins: $vgpr1_vgpr2, $vgpr2_vgpr3_vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, $vgpr20
    ; GREEDY-NEXT: {{  $}}
    ; GREEDY-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
    ; GREEDY-NEXT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    ; GREEDY-NEXT: [[COPY2:%[0-9]+]]:agpr(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    ; GREEDY-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY $vgpr20
    ; GREEDY-NEXT: [[INT:%[0-9]+]]:agpr(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.32x32x32.i8), [[COPY]](s64), [[COPY1]](s128), [[COPY2]](<16 x s32>), [[COPY3]](s32), 0, 0
    ; GREEDY-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY [[INT]](<16 x s32>)
    %0:_(s64) = COPY $vgpr0_vgpr1
    %1:_(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
    %2:_(<16 x s32>) = COPY $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
    %3:_(s32) = COPY $vgpr20
    %4:_(<16 x s32>) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.smfmac.i32.32x32x32.i8), %0, %1, %2, %3, 0, 0
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY %4
...