AMDGPU/GlobalISel: Basic legalize rules for G_FSHR

Only handles easy 32-bit cases.
This commit is contained in:
Matt Arsenault 2020-03-19 21:25:27 -04:00
parent fa496ce3c6
commit 4919f2e1c5
6 changed files with 490 additions and 1 deletions

View File

@ -3276,6 +3276,8 @@ LegalizerHelper::fewerElementsVector(MachineInstr &MI, unsigned TypeIdx,
case G_FMAXNUM_IEEE:
case G_FMINIMUM:
case G_FMAXIMUM:
case G_FSHL:
case G_FSHR:
return fewerElementsVectorBasic(MI, TypeIdx, NarrowTy);
case G_SHL:
case G_LSHR:

View File

@ -1313,6 +1313,11 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
.clampScalar(0, S32, S64)
.lower();
getActionDefinitionsBuilder(G_FSHR)
.legalFor({{S32, S32}})
.scalarize(0)
.lower();
getActionDefinitionsBuilder(G_READCYCLECOUNTER)
.legalFor({S64});
@ -1327,7 +1332,8 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
G_SADDO, G_SSUBO,
// TODO: Implement
G_FMINIMUM, G_FMAXIMUM
G_FMINIMUM, G_FMAXIMUM,
G_FSHL
}).lower();
getActionDefinitionsBuilder({G_VASTART, G_VAARG, G_BRJT, G_JUMP_TABLE,

View File

@ -3284,6 +3284,7 @@ AMDGPURegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
case AMDGPU::G_FCANONICALIZE:
case AMDGPU::G_INTRINSIC_TRUNC:
case AMDGPU::G_BSWAP: // TODO: Somehow expand for scalar?
case AMDGPU::G_FSHR: // TODO: Expand for scalar
case AMDGPU::G_AMDGPU_FFBH_U32:
case AMDGPU::G_AMDGPU_FMIN_LEGACY:
case AMDGPU::G_AMDGPU_FMAX_LEGACY:

View File

@ -0,0 +1,29 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
---
name: fshr_s32
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GCN-LABEL: name: fshr_s32
; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GCN: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GCN: [[V_ALIGNBIT_B32_:%[0-9]+]]:vgpr_32 = V_ALIGNBIT_B32 [[COPY]], [[COPY1]], [[COPY2]], implicit $exec
; GCN: S_ENDPGM 0, implicit [[V_ALIGNBIT_B32_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_FSHR %0, %1, %2
S_ENDPGM 0, implicit %3
...

View File

@ -0,0 +1,299 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -O0 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=SI %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=VI %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -O0 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=GFX9 %s
---
name: test_fshr_s32_s32
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; SI-LABEL: name: test_fshr_s32_s32
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; SI: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s32)
; SI: $vgpr0 = COPY [[FSHR]](s32)
; VI-LABEL: name: test_fshr_s32_s32
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; VI: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s32)
; VI: $vgpr0 = COPY [[FSHR]](s32)
; GFX9-LABEL: name: test_fshr_s32_s32
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX9: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s32)
; GFX9: $vgpr0 = COPY [[FSHR]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = G_FSHR %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fshr_v2s32_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; SI-LABEL: name: test_fshr_v2s32_v2s32
; SI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; SI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; SI: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; SI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; SI: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[UV]], [[UV2]], [[UV4]](s32)
; SI: [[FSHR1:%[0-9]+]]:_(s32) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s32)
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FSHR]](s32), [[FSHR1]](s32)
; SI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; VI-LABEL: name: test_fshr_v2s32_v2s32
; VI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; VI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; VI: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; VI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; VI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; VI: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[UV]], [[UV2]], [[UV4]](s32)
; VI: [[FSHR1:%[0-9]+]]:_(s32) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s32)
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FSHR]](s32), [[FSHR1]](s32)
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX9-LABEL: name: test_fshr_v2s32_v2s32
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX9: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX9: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX9: [[FSHR:%[0-9]+]]:_(s32) = G_FSHR [[UV]], [[UV2]], [[UV4]](s32)
; GFX9: [[FSHR1:%[0-9]+]]:_(s32) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s32)
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FSHR]](s32), [[FSHR1]](s32)
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<2 x s32>) = COPY $vgpr4_vgpr5
%3:_(<2 x s32>) = G_FSHR %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fshr_s16_s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; SI-LABEL: name: test_fshr_s16_s16
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; SI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
; SI: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s16)
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s16)
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
; VI-LABEL: name: test_fshr_s16_s16
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
; VI: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s16)
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s16)
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_fshr_s16_s16
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; GFX9: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
; GFX9: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s16)
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s16)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s16) = G_TRUNC %0
%4:_(s16) = G_TRUNC %1
%5:_(s16) = G_TRUNC %2
%6:_(s16) = G_FSHR %3, %4, %5
%7:_(s32) = G_ANYEXT %6
$vgpr0 = COPY %7
...
---
name: test_fshr_v2s16_v2s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; SI-LABEL: name: test_fshr_v2s16_v2s16
; SI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; SI: [[COPY2:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr2
; SI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<2 x s16>)
; SI: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<2 x s16>)
; SI: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY2]](<2 x s16>)
; SI: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[UV]], [[UV2]], [[UV4]](s16)
; SI: [[FSHR1:%[0-9]+]]:_(s16) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s16)
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[FSHR]](s16), [[FSHR1]](s16)
; SI: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
; VI-LABEL: name: test_fshr_v2s16_v2s16
; VI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; VI: [[COPY2:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr2
; VI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<2 x s16>)
; VI: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<2 x s16>)
; VI: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY2]](<2 x s16>)
; VI: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[UV]], [[UV2]], [[UV4]](s16)
; VI: [[FSHR1:%[0-9]+]]:_(s16) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s16)
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[FSHR]](s16), [[FSHR1]](s16)
; VI: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
; GFX9-LABEL: name: test_fshr_v2s16_v2s16
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr2
; GFX9: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<2 x s16>)
; GFX9: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<2 x s16>)
; GFX9: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY2]](<2 x s16>)
; GFX9: [[FSHR:%[0-9]+]]:_(s16) = G_FSHR [[UV]], [[UV2]], [[UV4]](s16)
; GFX9: [[FSHR1:%[0-9]+]]:_(s16) = G_FSHR [[UV1]], [[UV3]], [[UV5]](s16)
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[FSHR]](s16), [[FSHR1]](s16)
; GFX9: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1
%2:_(<2 x s16>) = COPY $vgpr2
%3:_(<2 x s16>) = G_FSHR %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fshr_s64_s64
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; SI-LABEL: name: test_fshr_s64_s64
; SI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; SI: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; SI: [[COPY2:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
; SI: [[FSHR:%[0-9]+]]:_(s64) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s64)
; SI: $vgpr0_vgpr1 = COPY [[FSHR]](s64)
; VI-LABEL: name: test_fshr_s64_s64
; VI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; VI: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; VI: [[COPY2:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
; VI: [[FSHR:%[0-9]+]]:_(s64) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s64)
; VI: $vgpr0_vgpr1 = COPY [[FSHR]](s64)
; GFX9-LABEL: name: test_fshr_s64_s64
; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; GFX9: [[COPY2:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
; GFX9: [[FSHR:%[0-9]+]]:_(s64) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s64)
; GFX9: $vgpr0_vgpr1 = COPY [[FSHR]](s64)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s64) = COPY $vgpr2_vgpr3
%2:_(s64) = COPY $vgpr4_vgpr5
%3:_(s64) = G_FSHR %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fshr_s8_s8
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; SI-LABEL: name: test_fshr_s8_s8
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; SI: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
; SI: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
; SI: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[COPY2]](s32)
; SI: [[FSHR:%[0-9]+]]:_(s8) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s8)
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s8)
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
; VI-LABEL: name: test_fshr_s8_s8
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; VI: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
; VI: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[COPY2]](s32)
; VI: [[FSHR:%[0-9]+]]:_(s8) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s8)
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s8)
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_fshr_s8_s8
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX9: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY]](s32)
; GFX9: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
; GFX9: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[COPY2]](s32)
; GFX9: [[FSHR:%[0-9]+]]:_(s8) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s8)
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s8)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s8) = G_TRUNC %0
%4:_(s8) = G_TRUNC %1
%5:_(s8) = G_TRUNC %2
%6:_(s8) = G_FSHR %3, %4, %5
%7:_(s32) = G_ANYEXT %6
$vgpr0 = COPY %7
...
---
name: test_fshr_s24_s24
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; SI-LABEL: name: test_fshr_s24_s24
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; SI: [[TRUNC:%[0-9]+]]:_(s24) = G_TRUNC [[COPY]](s32)
; SI: [[TRUNC1:%[0-9]+]]:_(s24) = G_TRUNC [[COPY1]](s32)
; SI: [[TRUNC2:%[0-9]+]]:_(s24) = G_TRUNC [[COPY2]](s32)
; SI: [[FSHR:%[0-9]+]]:_(s24) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s24)
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s24)
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
; VI-LABEL: name: test_fshr_s24_s24
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; VI: [[TRUNC:%[0-9]+]]:_(s24) = G_TRUNC [[COPY]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s24) = G_TRUNC [[COPY1]](s32)
; VI: [[TRUNC2:%[0-9]+]]:_(s24) = G_TRUNC [[COPY2]](s32)
; VI: [[FSHR:%[0-9]+]]:_(s24) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s24)
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s24)
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_fshr_s24_s24
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX9: [[TRUNC:%[0-9]+]]:_(s24) = G_TRUNC [[COPY]](s32)
; GFX9: [[TRUNC1:%[0-9]+]]:_(s24) = G_TRUNC [[COPY1]](s32)
; GFX9: [[TRUNC2:%[0-9]+]]:_(s24) = G_TRUNC [[COPY2]](s32)
; GFX9: [[FSHR:%[0-9]+]]:_(s24) = G_FSHR [[TRUNC]], [[TRUNC1]], [[TRUNC2]](s24)
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FSHR]](s24)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s24) = G_TRUNC %0
%4:_(s24) = G_TRUNC %1
%5:_(s24) = G_TRUNC %2
%6:_(s24) = G_FSHR %3, %4, %5
%7:_(s32) = G_ANYEXT %6
$vgpr0 = COPY %7
...

View File

@ -0,0 +1,152 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=regbankselect -regbankselect-fast -verify-machineinstrs -o - %s | FileCheck %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=regbankselect -regbankselect-greedy -verify-machineinstrs -o - %s | FileCheck %s
---
name: fshr_sss
legalized: true
body: |
bb.0:
liveins: $sgpr0, $sgpr1, $sgpr2
; CHECK-LABEL: name: fshr_sss
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK: [[COPY2:%[0-9]+]]:sgpr(s32) = COPY $sgpr2
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[COPY5:%[0-9]+]]:vgpr(s32) = COPY [[COPY2]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY3]], [[COPY4]], [[COPY5]](s32)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $sgpr1
%2:_(s32) = COPY $sgpr2
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_vss
legalized: true
body: |
bb.0:
liveins: $vgpr0, $sgpr0, $sgpr1
; CHECK-LABEL: name: fshr_vss
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY2:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY2]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY]], [[COPY3]], [[COPY4]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr0
%2:_(s32) = COPY $sgpr1
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_svs
legalized: true
body: |
bb.0:
liveins: $sgpr0, $vgpr0, $sgpr1
; CHECK-LABEL: name: fshr_svs
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY2:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY2]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY3]], [[COPY1]], [[COPY4]](s32)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0
%2:_(s32) = COPY $sgpr1
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_ssv
legalized: true
body: |
bb.0:
liveins: $sgpr0, $sgpr1, $vgpr0
; CHECK-LABEL: name: fshr_ssv
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[COPY4:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY3]], [[COPY4]], [[COPY2]](s32)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $sgpr1
%2:_(s32) = COPY $vgpr0
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_vvs
legalized: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $sgpr0
; CHECK-LABEL: name: fshr_vvs
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY2]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY]], [[COPY1]], [[COPY3]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $sgpr0
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_vsv
legalized: true
body: |
bb.0:
liveins: $vgpr0, $sgpr0, $vgpr1
; CHECK-LABEL: name: fshr_vsv
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY]], [[COPY3]], [[COPY2]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr1
%2:_(s32) = COPY $vgpr1
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_svv
legalized: true
body: |
bb.0:
liveins: $sgpr0, $vgpr0, $vgpr1
; CHECK-LABEL: name: fshr_svv
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[COPY3:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY3]], [[COPY1]], [[COPY2]](s32)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0
%2:_(s32) = COPY $vgpr1
%3:_(s32) = G_FSHR %0, %1, %2
...
---
name: fshr_vvv
legalized: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; CHECK-LABEL: name: fshr_vvv
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
; CHECK: [[FSHR:%[0-9]+]]:vgpr(s32) = G_FSHR [[COPY]], [[COPY1]], [[COPY2]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = G_FSHR %0, %1, %2
...