diff options
Diffstat (limited to 'llvm/lib/Target/X86')
| -rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 6 | ||||
| -rw-r--r-- | llvm/lib/Target/X86/X86InstrAVX512.td | 2 | ||||
| -rw-r--r-- | llvm/lib/Target/X86/X86InstrInfo.cpp | 16 |
3 files changed, 19 insertions, 5 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 4cbffcc2f21..8cb528ec9e3 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -6554,11 +6554,11 @@ static SDValue materializeVectorConstant(SDValue Op, SelectionDAG &DAG, // vectors or broken into v4i32 operations on 256-bit vectors. AVX2 can use // vpcmpeqd on 256-bit vectors. if (Subtarget.hasSSE2() && ISD::isBuildVectorAllOnes(Op.getNode())) { - if (VT == MVT::v4i32 || (VT == MVT::v8i32 && Subtarget.hasInt256())) + if (VT == MVT::v4i32 || VT == MVT::v16i32 || + (VT == MVT::v8i32 && Subtarget.hasInt256())) return Op; - if (!VT.is512BitVector()) - return getOnesVector(VT, Subtarget, DAG, DL); + return getOnesVector(VT, Subtarget, DAG, DL); } return SDValue(); diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td index 357b5179718..0b50b82b154 100644 --- a/llvm/lib/Target/X86/X86InstrAVX512.td +++ b/llvm/lib/Target/X86/X86InstrAVX512.td @@ -416,6 +416,8 @@ let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1, isPseudo = 1, Predicates = [HasAVX512], SchedRW = [WriteZero] in { def AVX512_512_SET0 : I<0, Pseudo, (outs VR512:$dst), (ins), "", [(set VR512:$dst, (v16i32 immAllZerosV))]>; +def AVX512_512_SETALLONES : I<0, Pseudo, (outs VR512:$dst), (ins), "", + [(set VR512:$dst, (v16i32 immAllOnesV))]>; } let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1, diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp index cc0388bb0db..a6a1714c21a 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.cpp +++ b/llvm/lib/Target/X86/X86InstrInfo.cpp @@ -5547,6 +5547,15 @@ bool X86InstrInfo::expandPostRAPseudo(MachineInstr &MI) const { return Expand2AddrUndef(MIB, get(HasAVX ? X86::VPCMPEQDrr : X86::PCMPEQDrr)); case X86::AVX2_SETALLONES: return Expand2AddrUndef(MIB, get(X86::VPCMPEQDYrr)); + case X86::AVX512_512_SETALLONES: { + unsigned Reg = MIB->getOperand(0).getReg(); + MIB->setDesc(get(X86::VPTERNLOGDZrri)); + // VPTERNLOGD needs 3 register inputs and an immediate. + // 0xff will return 1s for any input. + MIB.addReg(Reg, RegState::Undef).addReg(Reg, RegState::Undef) + .addReg(Reg, RegState::Undef).addImm(0xff); + return true; + } case X86::TEST8ri_NOREX: MI.setDesc(get(X86::TEST8ri)); return true; @@ -6231,6 +6240,7 @@ MachineInstr *X86InstrInfo::foldMemoryOperandImpl( else switch (LoadMI.getOpcode()) { case X86::AVX512_512_SET0: + case X86::AVX512_512_SETALLONES: Alignment = 64; break; case X86::AVX2_SETALLONES: @@ -6281,6 +6291,7 @@ MachineInstr *X86InstrInfo::foldMemoryOperandImpl( case X86::AVX512_128_SET0: case X86::AVX512_256_SET0: case X86::AVX512_512_SET0: + case X86::AVX512_512_SETALLONES: case X86::FsFLD0SD: case X86::FsFLD0SS: { // Folding a V_SET0 or V_SETALLONES as a load, to ease register pressure. @@ -6312,7 +6323,7 @@ MachineInstr *X86InstrInfo::foldMemoryOperandImpl( Ty = Type::getFloatTy(MF.getFunction()->getContext()); else if (Opc == X86::FsFLD0SD) Ty = Type::getDoubleTy(MF.getFunction()->getContext()); - else if (Opc == X86::AVX512_512_SET0) + else if (Opc == X86::AVX512_512_SET0 || Opc == X86::AVX512_512_SETALLONES) Ty = VectorType::get(Type::getInt32Ty(MF.getFunction()->getContext()),16); else if (Opc == X86::AVX2_SETALLONES || Opc == X86::AVX_SET0 || Opc == X86::AVX512_256_SET0) @@ -6320,7 +6331,8 @@ MachineInstr *X86InstrInfo::foldMemoryOperandImpl( else Ty = VectorType::get(Type::getInt32Ty(MF.getFunction()->getContext()), 4); - bool IsAllOnes = (Opc == X86::V_SETALLONES || Opc == X86::AVX2_SETALLONES); + bool IsAllOnes = (Opc == X86::V_SETALLONES || Opc == X86::AVX2_SETALLONES || + Opc == X86::AVX512_512_SETALLONES); const Constant *C = IsAllOnes ? Constant::getAllOnesValue(Ty) : Constant::getNullValue(Ty); unsigned CPI = MCP.getConstantPoolIndex(C, Alignment); |
