diff options
Diffstat (limited to 'llvm/lib')
-rw-r--r-- | llvm/lib/Target/X86/X86FastISel.cpp | 3 | ||||
-rw-r--r-- | llvm/lib/Target/X86/X86InstrInfo.cpp | 155 | ||||
-rw-r--r-- | llvm/lib/Target/X86/X86InstrInfo.h | 3 |
3 files changed, 102 insertions, 59 deletions
diff --git a/llvm/lib/Target/X86/X86FastISel.cpp b/llvm/lib/Target/X86/X86FastISel.cpp index 70eec08cce2..4c9fef5c3b2 100644 --- a/llvm/lib/Target/X86/X86FastISel.cpp +++ b/llvm/lib/Target/X86/X86FastISel.cpp @@ -3337,7 +3337,8 @@ bool X86FastISel::tryToFoldLoadIntoMI(MachineInstr *MI, unsigned OpNo, AM.getFullAddress(AddrOps); MachineInstr *Result = - XII.foldMemoryOperandImpl(*FuncInfo.MF, MI, OpNo, AddrOps, Size, Alignment); + XII.foldMemoryOperandImpl(*FuncInfo.MF, MI, OpNo, AddrOps, + Size, Alignment, /*AllowCommute=*/true); if (!Result) return false; diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp index a7637f9e65d..ff41e48c8f2 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.cpp +++ b/llvm/lib/Target/X86/X86InstrInfo.cpp @@ -3907,10 +3907,10 @@ optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2, /// operand at the use. We fold the load instructions if load defines a virtual /// register, the virtual register is used once in the same BB, and the /// instructions in-between do not load or store, and have no side effects. -MachineInstr* X86InstrInfo:: -optimizeLoadInstr(MachineInstr *MI, const MachineRegisterInfo *MRI, - unsigned &FoldAsLoadDefReg, - MachineInstr *&DefMI) const { +MachineInstr *X86InstrInfo::optimizeLoadInstr(MachineInstr *MI, + const MachineRegisterInfo *MRI, + unsigned &FoldAsLoadDefReg, + MachineInstr *&DefMI) const { if (FoldAsLoadDefReg == 0) return nullptr; // To be conservative, if there exists another load, clear the load candidate. @@ -3926,55 +3926,35 @@ optimizeLoadInstr(MachineInstr *MI, const MachineRegisterInfo *MRI, if (!DefMI->isSafeToMove(this, nullptr, SawStore)) return nullptr; - // We try to commute MI if possible. - unsigned IdxEnd = (MI->isCommutable()) ? 2 : 1; - for (unsigned Idx = 0; Idx < IdxEnd; Idx++) { - // Collect information about virtual register operands of MI. - unsigned SrcOperandId = 0; - bool FoundSrcOperand = false; - for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) { - MachineOperand &MO = MI->getOperand(i); - if (!MO.isReg()) - continue; - unsigned Reg = MO.getReg(); - if (Reg != FoldAsLoadDefReg) - continue; - // Do not fold if we have a subreg use or a def or multiple uses. - if (MO.getSubReg() || MO.isDef() || FoundSrcOperand) - return nullptr; - - SrcOperandId = i; - FoundSrcOperand = true; - } - if (!FoundSrcOperand) return nullptr; - - // Check whether we can fold the def into SrcOperandId. - SmallVector<unsigned, 8> Ops; - Ops.push_back(SrcOperandId); - MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI); - if (FoldMI) { - FoldAsLoadDefReg = 0; - return FoldMI; - } - - if (Idx == 1) { - // MI was changed but it didn't help, commute it back! - commuteInstruction(MI, false); + // Collect information about virtual register operands of MI. + unsigned SrcOperandId = 0; + bool FoundSrcOperand = false; + for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) { + MachineOperand &MO = MI->getOperand(i); + if (!MO.isReg()) + continue; + unsigned Reg = MO.getReg(); + if (Reg != FoldAsLoadDefReg) + continue; + // Do not fold if we have a subreg use or a def or multiple uses. + if (MO.getSubReg() || MO.isDef() || FoundSrcOperand) return nullptr; - } - // Check whether we can commute MI and enable folding. - if (MI->isCommutable()) { - MachineInstr *NewMI = commuteInstruction(MI, false); - // Unable to commute. - if (!NewMI) return nullptr; - if (NewMI != MI) { - // New instruction. It doesn't need to be kept. - NewMI->eraseFromParent(); - return nullptr; - } - } + SrcOperandId = i; + FoundSrcOperand = true; } + if (!FoundSrcOperand) + return nullptr; + + // Check whether we can fold the def into SrcOperandId. + SmallVector<unsigned, 8> Ops; + Ops.push_back(SrcOperandId); + MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI); + if (FoldMI) { + FoldAsLoadDefReg = 0; + return FoldMI; + } + return nullptr; } @@ -4134,7 +4114,8 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI, unsigned i, const SmallVectorImpl<MachineOperand> &MOs, - unsigned Size, unsigned Align) const { + unsigned Size, unsigned Align, + bool AllowCommute) const { const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = nullptr; bool isCallRegIndirect = Subtarget.callRegIndirect(); @@ -4202,8 +4183,8 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, if (Opcode != X86::MOV64rm || RCSize != 8 || Size != 4) return nullptr; // If this is a 64-bit load, but the spill slot is 32, then we can do - // a 32-bit load which is implicitly zero-extended. This likely is due - // to liveintervalanalysis remat'ing a load from stack slot. + // a 32-bit load which is implicitly zero-extended. This likely is + // due to live interval analysis remat'ing a load from stack slot. if (MI->getOperand(0).getSubReg() || MI->getOperand(1).getSubReg()) return nullptr; Opcode = X86::MOV32rm; @@ -4222,8 +4203,7 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, // to a 32-bit one. unsigned DstReg = NewMI->getOperand(0).getReg(); if (TargetRegisterInfo::isPhysicalRegister(DstReg)) - NewMI->getOperand(0).setReg(RI.getSubReg(DstReg, - X86::sub_32bit)); + NewMI->getOperand(0).setReg(RI.getSubReg(DstReg, X86::sub_32bit)); else NewMI->getOperand(0).setSubReg(X86::sub_32bit); } @@ -4231,6 +4211,65 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, } } + // If the instruction and target operand are commutable, commute the + // instruction and try again. + if (AllowCommute) { + unsigned OriginalOpIdx = i, CommuteOpIdx1, CommuteOpIdx2; + if (findCommutedOpIndices(MI, CommuteOpIdx1, CommuteOpIdx2)) { + bool HasDef = MI->getDesc().getNumDefs(); + unsigned Reg0 = HasDef ? MI->getOperand(0).getReg() : 0; + unsigned Reg1 = MI->getOperand(CommuteOpIdx1).getReg(); + unsigned Reg2 = MI->getOperand(CommuteOpIdx2).getReg(); + bool Tied0 = + 0 == MI->getDesc().getOperandConstraint(CommuteOpIdx1, MCOI::TIED_TO); + bool Tied1 = + 0 == MI->getDesc().getOperandConstraint(CommuteOpIdx2, MCOI::TIED_TO); + + // If either of the commutable operands are tied to the destination + // then we can not commute + fold. + if ((HasDef && Reg0 == Reg1 && Tied0) || + (HasDef && Reg0 == Reg2 && Tied1)) + return nullptr; + + if ((CommuteOpIdx1 == OriginalOpIdx) || + (CommuteOpIdx2 == OriginalOpIdx)) { + MachineInstr *CommutedMI = commuteInstruction(MI, false); + if (!CommutedMI) { + // Unable to commute. + return nullptr; + } + if (CommutedMI != MI) { + // New instruction. We can't fold from this. + CommutedMI->eraseFromParent(); + return nullptr; + } + + // Attempt to fold with the commuted version of the instruction. + unsigned CommuteOp = + (CommuteOpIdx1 == OriginalOpIdx ? CommuteOpIdx2 : CommuteOpIdx1); + NewMI = foldMemoryOperandImpl(MF, MI, CommuteOp, MOs, Size, Align, + /*AllowCommute=*/false); + if (NewMI) + return NewMI; + + // Folding failed again - undo the commute before returning. + MachineInstr *UncommutedMI = commuteInstruction(MI, false); + if (!UncommutedMI) { + // Unable to commute. + return nullptr; + } + if (UncommutedMI != MI) { + // New instruction. It doesn't need to be kept. + UncommutedMI->eraseFromParent(); + return nullptr; + } + + // Return here to prevent duplicate fuse failure report. + return nullptr; + } + } + } + // No fusion if (PrintFailedFusing && !MI->isCopy()) dbgs() << "We failed to fuse operand " << i << " in " << *MI; @@ -4440,7 +4479,8 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI, SmallVector<MachineOperand,4> MOs; MOs.push_back(MachineOperand::CreateFI(FrameIndex)); - return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Size, Alignment); + return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, + Size, Alignment, /*AllowCommute=*/true); } static bool isPartialRegisterLoad(const MachineInstr &LoadMI, @@ -4593,7 +4633,8 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, break; } } - return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, 0, Alignment); + return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, + /*Size=*/0, Alignment, /*AllowCommute=*/true); } diff --git a/llvm/lib/Target/X86/X86InstrInfo.h b/llvm/lib/Target/X86/X86InstrInfo.h index ca90976a83a..f3f54ae5664 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.h +++ b/llvm/lib/Target/X86/X86InstrInfo.h @@ -404,7 +404,8 @@ public: MachineInstr* MI, unsigned OpNum, const SmallVectorImpl<MachineOperand> &MOs, - unsigned Size, unsigned Alignment) const; + unsigned Size, unsigned Alignment, + bool AllowCommute) const; void getUnconditionalBranch(MCInst &Branch, |