Codebase Browser
llvm
Go to App

llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankcombiner-clamp-fmed3-const.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
# RUN: llc -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1200 -run-pass=amdgpu-regbank-combiner -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=GFX12
---
name: test_fmed3_f32_known_nnan_ieee_true
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: true
    dx10-clamp: true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_f32_known_nnan_ieee_true
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; CHECK-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = nnan G_AMDGPU_CLAMP [[FMUL]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_f32_known_nnan_ieee_true
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = nnan G_AMDGPU_CLAMP [[FMUL]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    %8:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMUL %0, %8
    %6:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %9:vgpr(s32) = COPY %5(s32)
    %10:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = nnan G_AMDGPU_FMED3 %3(s32), %9(s32), %10(s32)
    $vgpr0 = COPY %4(s32)
...

---
name: test_fmed3_f16_known_nnan_ieee_false
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: false
    dx10-clamp: true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_f16_known_nnan_ieee_false
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[COPY]](s32)
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s16) = G_FCONSTANT half 0xH4000
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s16) = COPY [[C]](s16)
    ; CHECK-NEXT: [[FMUL:%[0-9]+]]:vgpr(s16) = G_FMUL [[TRUNC]], [[COPY1]]
    ; CHECK-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s16) = nnan G_AMDGPU_CLAMP [[FMUL]]
    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[AMDGPU_CLAMP]](s16)
    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_f16_known_nnan_ieee_false
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[COPY]](s32)
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s16) = G_FCONSTANT half 0xH4000
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s16) = COPY [[C]](s16)
    ; GFX12-NEXT: [[FMUL:%[0-9]+]]:vgpr(s16) = G_FMUL [[TRUNC]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s16) = nnan G_AMDGPU_CLAMP [[FMUL]]
    ; GFX12-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[AMDGPU_CLAMP]](s16)
    ; GFX12-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
    %2:vgpr(s32) = COPY $vgpr0
    %0:vgpr(s16) = G_TRUNC %2(s32)
    %3:sgpr(s16) = G_FCONSTANT half 0xH4000
    %10:vgpr(s16) = COPY %3(s16)
    %4:vgpr(s16) = G_FMUL %0, %10
    %7:sgpr(s16) = G_FCONSTANT half 0xH3C00
    %6:sgpr(s16) = G_FCONSTANT half 0xH0000
    %11:vgpr(s16) = COPY %6(s16)
    %12:vgpr(s16) = COPY %7(s16)
    %5:vgpr(s16) = nnan G_AMDGPU_FMED3 %4(s16), %11(s16), %12(s16)
    %9:vgpr(s32) = G_ANYEXT %5(s16)
    $vgpr0 = COPY %9(s32)
...

---
name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_true
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee:            true
    dx10-clamp:      true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_true
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    ; CHECK-NEXT: [[FCANONICALIZE:%[0-9]+]]:vgpr(s32) = G_FCANONICALIZE [[COPY]]
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMINNUM_IEEE:%[0-9]+]]:vgpr(s32) = G_FMINNUM_IEEE [[FCANONICALIZE]], [[COPY1]]
    ; CHECK-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMINNUM_IEEE]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_true
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    ; GFX12-NEXT: [[FCANONICALIZE:%[0-9]+]]:vgpr(s32) = G_FCANONICALIZE [[COPY]]
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMINNUM_IEEE:%[0-9]+]]:vgpr(s32) = G_FMINNUM_IEEE [[FCANONICALIZE]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMINNUM_IEEE]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    %8:vgpr(s32) = G_FCANONICALIZE %0
    %9:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMINNUM_IEEE %8, %9
    %6:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %10:vgpr(s32) = COPY %5(s32)
    %11:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = G_AMDGPU_FMED3 %3(s32), %10(s32), %11(s32)
    $vgpr0 = COPY %4(s32)
...

---
name: test_fmed3_maybe_SNaN_input_zero_third_operand_ieee_true_dx10clamp_true
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: true
    dx10-clamp: true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_maybe_SNaN_input_zero_third_operand_ieee_true_dx10clamp_true
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; CHECK-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMUL]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_maybe_SNaN_input_zero_third_operand_ieee_true_dx10clamp_true
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMUL]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    %8:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMUL %0, %8
    %6:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %9:vgpr(s32) = COPY %5(s32)
    %10:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = G_AMDGPU_FMED3 %3(s32), %9(s32), %10(s32)
    $vgpr0 = COPY %4(s32)
...

# FixMe: add tests with attributes #3 = {"no-nans-fp-math"="true"}

---
name: test_fmed3_f32_maybe_NaN_ieee_false
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: false
    dx10-clamp: true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_f32_maybe_NaN_ieee_false
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    ; CHECK-NEXT: [[C2:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C2]](s32)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_FMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_FMED3 [[FMUL]], [[COPY2]], [[COPY3]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_FMED3_]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_f32_maybe_NaN_ieee_false
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMUL]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    %8:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMUL %0, %8
    %6:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %9:vgpr(s32) = COPY %5(s32)
    %10:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = G_AMDGPU_FMED3 %3(s32), %9(s32), %10(s32)
    $vgpr0 = COPY %4(s32)
...

---
name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_false
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: true
    dx10-clamp: false
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_false
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    ; CHECK-NEXT: [[FCANONICALIZE:%[0-9]+]]:vgpr(s32) = G_FCANONICALIZE [[COPY]]
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMINNUM_IEEE:%[0-9]+]]:vgpr(s32) = G_FMINNUM_IEEE [[FCANONICALIZE]], [[COPY1]]
    ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    ; CHECK-NEXT: [[C2:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[C2]](s32)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[C1]](s32)
    ; CHECK-NEXT: [[AMDGPU_FMED3_:%[0-9]+]]:vgpr(s32) = G_AMDGPU_FMED3 [[FMINNUM_IEEE]], [[COPY2]], [[COPY3]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_FMED3_]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_non_SNaN_input_ieee_true_dx10clamp_false
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    ; GFX12-NEXT: [[FCANONICALIZE:%[0-9]+]]:vgpr(s32) = G_FCANONICALIZE [[COPY]]
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMINNUM_IEEE:%[0-9]+]]:vgpr(s32) = G_FMINNUM_IEEE [[FCANONICALIZE]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMINNUM_IEEE]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 1.000000e+01
    %8:vgpr(s32) = G_FCANONICALIZE %0
    %9:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMINNUM_IEEE %8, %9
    %6:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %10:vgpr(s32) = COPY %5(s32)
    %11:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = G_AMDGPU_FMED3 %3(s32), %10(s32), %11(s32)
    $vgpr0 = COPY %4(s32)
...

---
name: test_fmed3_maybe_SNaN_input_ieee_true_dx10clamp_true
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
  mode:
    ieee: true
    dx10-clamp: true
body: |
  bb.1 :
    liveins: $vgpr0

    ; CHECK-LABEL: name: test_fmed3_maybe_SNaN_input_ieee_true_dx10clamp_true
    ; CHECK: liveins: $vgpr0
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; CHECK-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; CHECK-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMUL]]
    ; CHECK-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    ;
    ; GFX12-LABEL: name: test_fmed3_maybe_SNaN_input_ieee_true_dx10clamp_true
    ; GFX12: liveins: $vgpr0
    ; GFX12-NEXT: {{  $}}
    ; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
    ; GFX12-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    ; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
    ; GFX12-NEXT: [[FMUL:%[0-9]+]]:vgpr(s32) = G_FMUL [[COPY]], [[COPY1]]
    ; GFX12-NEXT: [[AMDGPU_CLAMP:%[0-9]+]]:vgpr(s32) = G_AMDGPU_CLAMP [[FMUL]]
    ; GFX12-NEXT: $vgpr0 = COPY [[AMDGPU_CLAMP]](s32)
    %0:vgpr(s32) = COPY $vgpr0
    %2:sgpr(s32) = G_FCONSTANT float 2.000000e+00
    %8:vgpr(s32) = COPY %2(s32)
    %3:vgpr(s32) = G_FMUL %0, %8
    %6:sgpr(s32) = G_FCONSTANT float 1.000000e+00
    %5:sgpr(s32) = G_FCONSTANT float 0.000000e+00
    %9:vgpr(s32) = COPY %5(s32)
    %10:vgpr(s32) = COPY %6(s32)
    %4:vgpr(s32) = G_AMDGPU_FMED3 %3(s32), %9(s32), %10(s32)
    $vgpr0 = COPY %4(s32)
...