diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86InstrInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86InstrInfo.cpp | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp index c07add60e24..6f374ad9ead 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.cpp +++ b/llvm/lib/Target/X86/X86InstrInfo.cpp @@ -1569,6 +1569,28 @@ MachineInstr *X86InstrInfo::commuteInstructionImpl(MachineInstr &MI, bool NewMI, return TargetInstrInfo::commuteInstructionImpl(WorkingMI, /*NewMI=*/false, OpIdx1, OpIdx2); } + case X86::INSERTPSrr: + case X86::VINSERTPSrr: + case X86::VINSERTPSZrr: { + unsigned Imm = MI.getOperand(MI.getNumOperands() - 1).getImm(); + unsigned ZMask = Imm & 15; + unsigned DstIdx = (Imm >> 4) & 3; + unsigned SrcIdx = (Imm >> 6) & 3; + + // We can commute insertps if we zero 2 of the elements, the insertion is + // "inline" and we don't override the insertion with a zero. + if (DstIdx == SrcIdx && (ZMask & (1 << DstIdx)) == 0 && + countPopulation(ZMask) == 2) { + unsigned AltIdx = findFirstSet((ZMask | (1 << DstIdx)) ^ 15); + assert(0 <= AltIdx && AltIdx < 4 && "Illegal insertion index"); + unsigned AltImm = (AltIdx << 6) | (AltIdx << 4) | ZMask; + auto &WorkingMI = cloneIfNew(MI); + WorkingMI.getOperand(MI.getNumOperands() - 1).setImm(AltImm); + return TargetInstrInfo::commuteInstructionImpl(WorkingMI, /*NewMI=*/false, + OpIdx1, OpIdx2); + } + return nullptr; + } case X86::MOVSDrr: case X86::MOVSSrr: case X86::VMOVSDrr: |
