Codebase Browser
llvm
Go to App

llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankcombiner-smed3.mir 

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -run-pass=amdgpu-regbank-combiner -verify-machineinstrs %s -o - | FileCheck %s
# RUN: llc -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -run-pass=amdgpu-regbank-combiner -verify-machineinstrs %s -o - | FileCheck %s

---
name: test_min_max_ValK0_K1_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_min_max_ValK0_K1_i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY1]], [[COPY2]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 -12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMAX %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMIN %3, %8
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: min_max_ValK0_K1_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: min_max_ValK0_K1_i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY1]], [[COPY2]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 -12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMAX %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMIN %3, %8
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_min_K1max_ValK0__i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_min_K1max_ValK0__i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY1]], [[COPY2]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 -12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMAX %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMIN %8, %3
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_min_K1max_K0Val__i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_min_K1max_K0Val__i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY1]], [[COPY2]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 -12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMAX %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMIN %8, %3
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_max_min_ValK1_K0_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_max_min_ValK1_K0_i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY2]], [[COPY1]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMIN %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 -12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMAX %3, %8
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_max_min_K1Val_K0_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_max_min_K1Val_K0_i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY2]], [[COPY1]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMIN %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 -12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMAX %3, %8
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_max_K0min_ValK1__i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_max_K0min_ValK1__i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY2]], [[COPY1]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMIN %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 -12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMAX %8, %3
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_max_K0min_K1Val__i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_max_K0min_K1Val__i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY2]], [[COPY1]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMIN %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 -12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMAX %8, %3
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_max_K0min_K1Val__v2i16
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_max_K0min_K1Val__v2i16
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[C]](s32), [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[C1]](s32), [[C1]](s32)
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[BUILD_VECTOR_TRUNC]](<2 x s16>)
    ; CHECK-NEXT: [[SMIN:%[0-9]+]]:vgpr(<2 x s16>) = G_SMIN [[COPY1]], [[COPY]]
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[BUILD_VECTOR_TRUNC1]](<2 x s16>)
    ; CHECK-NEXT: [[SMAX:%[0-9]+]]:vgpr(<2 x s16>) = G_SMAX [[COPY2]], [[SMIN]]
    ; CHECK-NEXT: $vgpr0 = COPY [[SMAX]](<2 x s16>)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(<2 x s16>) = COPY $vgpr0
    %9:sgpr(s32) = G_CONSTANT i32 17
    %2:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC %9(s32), %9(s32)
    %10:sgpr(s32) = G_CONSTANT i32 -12
    %5:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC %10(s32), %10(s32)
    %11:vgpr(<2 x s16>) = COPY %2(<2 x s16>)
    %4:vgpr(<2 x s16>) = G_SMIN %11, %0
    %12:vgpr(<2 x s16>) = COPY %5(<2 x s16>)
    %7:vgpr(<2 x s16>) = G_SMAX %12, %4
    $vgpr0 = COPY %7(<2 x s16>)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...

---
name: test_uniform_min_max
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $sgpr2

    ; CHECK-LABEL: name: test_uniform_min_max
    ; CHECK: liveins: $sgpr2
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr2
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[SMAX:%[0-9]+]]:sgpr(s32) = G_SMAX [[COPY]], [[C]]
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK-NEXT: [[SMIN:%[0-9]+]]:sgpr(s32) = G_SMIN [[SMAX]], [[C1]]
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[SMIN]](s32)
    ; CHECK-NEXT: [[INT:%[0-9]+]]:sgpr(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[COPY1]](s32)
    ; CHECK-NEXT: $sgpr0 = COPY [[INT]](s32)
    ; CHECK-NEXT: SI_RETURN_TO_EPILOG implicit $sgpr0
    %0:sgpr(s32) = COPY $sgpr2
    %3:sgpr(s32) = G_CONSTANT i32 -12
    %4:sgpr(s32) = G_SMAX %0, %3
    %5:sgpr(s32) = G_CONSTANT i32 17
    %6:sgpr(s32) = G_SMIN %4, %5
    %8:vgpr(s32) = COPY %6(s32)
    %7:sgpr(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), %8(s32)
    $sgpr0 = COPY %7(s32)
    SI_RETURN_TO_EPILOG implicit $sgpr0
...

---
name: test_non_inline_constant_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_non_inline_constant_i32
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 -12
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 65
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_SMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_SMED3 [[COPY]], [[COPY1]], [[COPY2]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_SMED3_]](s32)
    ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_CONSTANT i32 -12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_SMAX %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 65
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_SMIN %3, %8
    $vgpr0 = COPY %5(s32)
    S_SETPC_B64_return undef $sgpr30_sgpr31, implicit $vgpr0
...