llvm/test/CodeGen/AMDGPU/GlobalISel/regbankcombiner-umed3.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# 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_u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_min_max_ValK0_K1_u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C]], [[C1]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMAX %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMIN %3, %8
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: min_max_ValK0_K1_i32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: min_max_ValK0_K1_i32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C]], [[C1]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMAX %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMIN %3, %8
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_min_K1max_ValK0__u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_min_K1max_ValK0__u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C]], [[C1]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMAX %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMIN %8, %3
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_min_K1max_K0Val__u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_min_K1max_K0Val__u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C]], [[C1]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 12
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMAX %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 17
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMIN %8, %3
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_max_min_ValK1_K0_u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_max_min_ValK1_K0_u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C1]], [[C]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMIN %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMAX %3, %8
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_max_min_K1Val_K0_u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_max_min_K1Val_K0_u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C1]], [[C]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMIN %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMAX %3, %8
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_max_K0min_ValK1__u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_max_K0min_ValK1__u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C1]], [[C]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMIN %0, %7
    %4:sgpr(s32) = G_CONSTANT i32 12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMAX %8, %3
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_max_K0min_K1Val__u32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_max_K0min_K1Val__u32
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[AMDGPU_UMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_UMED3 [[COPY]], [[C1]], [[C]]
    ; CHECK: $vgpr0 = COPY [[AMDGPU_UMED3_]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY2]], implicit $vgpr0
    %0:vgpr(s32) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %2:sgpr(s32) = G_CONSTANT i32 17
    %7:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_UMIN %7, %0
    %4:sgpr(s32) = G_CONSTANT i32 12
    %8:vgpr(s32) = COPY %4(s32)
    %5:vgpr(s32) = G_UMAX %8, %3
    $vgpr0 = COPY %5(s32)
    %6:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %6, implicit $vgpr0
...

---
name: test_max_K0min_K1Val__v2u16
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
  bb.1:
    liveins: $vgpr0, $sgpr30_sgpr31

    ; CHECK-LABEL: name: test_max_K0min_K1Val__v2u16
    ; CHECK: liveins: $vgpr0, $sgpr30_sgpr31
    ; CHECK: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
    ; CHECK: [[COPY1:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[C]](s32), [[C]](s32)
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[C1]](s32), [[C1]](s32)
    ; CHECK: [[COPY2:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[BUILD_VECTOR_TRUNC]](<2 x s16>)
    ; CHECK: [[UMIN:%[0-9]+]]:vgpr(<2 x s16>) = G_UMIN [[COPY2]], [[COPY]]
    ; CHECK: [[COPY3:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[BUILD_VECTOR_TRUNC1]](<2 x s16>)
    ; CHECK: [[UMAX:%[0-9]+]]:vgpr(<2 x s16>) = G_UMAX [[COPY3]], [[UMIN]]
    ; CHECK: $vgpr0 = COPY [[UMAX]](<2 x s16>)
    ; CHECK: [[COPY4:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY1]]
    ; CHECK: S_SETPC_B64_return [[COPY4]], implicit $vgpr0
    %0:vgpr(<2 x s16>) = COPY $vgpr0
    %1:sgpr_64 = COPY $sgpr30_sgpr31
    %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_UMIN %11, %0
    %12:vgpr(<2 x s16>) = COPY %5(<2 x s16>)
    %7:vgpr(<2 x s16>) = G_UMAX %12, %4
    $vgpr0 = COPY %7(<2 x s16>)
    %8:ccr_sgpr_64 = COPY %1
    S_SETPC_B64_return %8, 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: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr2
    ; CHECK: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 12
    ; CHECK: [[UMAX:%[0-9]+]]:sgpr(s32) = G_UMAX [[COPY]], [[C]]
    ; CHECK: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 17
    ; CHECK: [[UMIN:%[0-9]+]]:sgpr(s32) = G_UMIN [[UMAX]], [[C1]]
    ; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[UMIN]](s32)
    ; CHECK: [[INT:%[0-9]+]]:sgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[COPY1]](s32)
    ; CHECK: $sgpr0 = COPY [[INT]](s32)
    ; CHECK: SI_RETURN_TO_EPILOG implicit $sgpr0
    %0:sgpr(s32) = COPY $sgpr2
    %3:sgpr(s32) = G_CONSTANT i32 12
    %4:sgpr(s32) = G_UMAX %0, %3
    %5:sgpr(s32) = G_CONSTANT i32 17
    %6:sgpr(s32) = G_UMIN %4, %5
    %8:vgpr(s32) = COPY %6(s32)
    %7:sgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), %8(s32)
    $sgpr0 = COPY %7(s32)
    SI_RETURN_TO_EPILOG implicit $sgpr0

...