diff options
Diffstat (limited to 'llvm/lib/Target/AMDGPU/SIInstrInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/SIInstrInfo.cpp | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp index adf114e02d6..9a85a1d515f 100644 --- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp +++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp @@ -2412,6 +2412,11 @@ void SIInstrInfo::moveToVALU(MachineInstr &TopInst) const { } break; + case AMDGPU::S_ABS_I32: + lowerScalarAbs(Worklist, Inst); + Inst->eraseFromParent(); + continue; + case AMDGPU::S_BFE_U64: case AMDGPU::S_BFM_B64: llvm_unreachable("Moving this op to VALU not implemented"); @@ -2497,6 +2502,30 @@ const TargetRegisterClass *SIInstrInfo::getIndirectAddrRegClass() const { return &AMDGPU::VGPR_32RegClass; } +void SIInstrInfo::lowerScalarAbs(SmallVectorImpl<MachineInstr *> &Worklist, + MachineInstr *Inst) const { + MachineBasicBlock &MBB = *Inst->getParent(); + MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo(); + MachineBasicBlock::iterator MII = Inst; + DebugLoc DL = Inst->getDebugLoc(); + + MachineOperand &Dest = Inst->getOperand(0); + MachineOperand &Src = Inst->getOperand(1); + unsigned TmpReg = MRI.createVirtualRegister(&AMDGPU::VGPR_32RegClass); + unsigned ResultReg = MRI.createVirtualRegister(&AMDGPU::VGPR_32RegClass); + + BuildMI(MBB, MII, DL, get(AMDGPU::V_SUB_I32_e32), TmpReg) + .addImm(0) + .addReg(Src.getReg()); + + BuildMI(MBB, MII, DL, get(AMDGPU::V_MAX_I32_e64), ResultReg) + .addReg(Src.getReg()) + .addReg(TmpReg); + + MRI.replaceRegWith(Dest.getReg(), ResultReg); + addUsersToMoveToVALUWorklist(ResultReg, MRI, Worklist); +} + void SIInstrInfo::splitScalar64BitUnaryOp( SmallVectorImpl<MachineInstr *> &Worklist, MachineInstr *Inst, |
