Index: llvm/trunk/include/llvm/Target/TargetLowering.h =================================================================== --- llvm/trunk/include/llvm/Target/TargetLowering.h +++ llvm/trunk/include/llvm/Target/TargetLowering.h @@ -2388,30 +2388,39 @@ New = N; return true; } - - /// Check to see if the specified operand of the specified instruction is a - /// constant integer. If so, check to see if there are any bits set in the - /// constant that are not demanded. If so, shrink the constant and return - /// true. - bool ShrinkDemandedConstant(SDValue Op, const APInt &Demanded); - - /// Convert x+y to (VT)((SmallVT)x+(SmallVT)y) if the casts are free. This - /// uses isZExtFree and ZERO_EXTEND for the widening cast, but it could be - /// generalized for targets with other types of implicit widening casts. - bool ShrinkDemandedOp(SDValue Op, unsigned BitWidth, const APInt &Demanded, - const SDLoc &dl); - - /// Helper for SimplifyDemandedBits that can simplify an operation with - /// multiple uses. This function uses TLI.SimplifyDemandedBits to - /// simplify Operand \p OpIdx of \p User and then updated \p User with - /// the simplified version. No other uses of \p OpIdx are updated. - /// If \p User is the only user of \p OpIdx, this function behaves exactly - /// like TLI.SimplifyDemandedBits except that it also updates the DAG by - /// calling DCI.CommitTargetLoweringOpt. - bool SimplifyDemandedBits(SDNode *User, unsigned OpIdx, - const APInt &Demanded, DAGCombinerInfo &DCI); }; + /// Check to see if the specified operand of the specified instruction is a + /// constant integer. If so, check to see if there are any bits set in the + /// constant that are not demanded. If so, shrink the constant and return + /// true. + bool ShrinkDemandedConstant(SDValue Op, const APInt &Demanded, + TargetLoweringOpt &TLO) const; + + // Target hook to do target-specific const optimization, which is called by + // ShrinkDemandedConstant. This function should return true if the target + // doesn't want ShrinkDemandedConstant to further optimize the constant. + virtual bool targetShrinkDemandedConstant(SDValue Op, const APInt &Demanded, + TargetLoweringOpt &TLO) const { + return false; + } + + /// Convert x+y to (VT)((SmallVT)x+(SmallVT)y) if the casts are free. This + /// uses isZExtFree and ZERO_EXTEND for the widening cast, but it could be + /// generalized for targets with other types of implicit widening casts. + bool ShrinkDemandedOp(SDValue Op, unsigned BitWidth, const APInt &Demanded, + TargetLoweringOpt &TLO) const; + + /// Helper for SimplifyDemandedBits that can simplify an operation with + /// multiple uses. This function simplifies operand \p OpIdx of \p User and + /// then updates \p User with the simplified version. No other uses of + /// \p OpIdx are updated. If \p User is the only user of \p OpIdx, this + /// function behaves exactly like function SimplifyDemandedBits declared + /// below except that it also updates the DAG by calling + /// DCI.CommitTargetLoweringOpt. + bool SimplifyDemandedBits(SDNode *User, unsigned OpIdx, const APInt &Demanded, + DAGCombinerInfo &DCI, TargetLoweringOpt &TLO) const; + /// Look at Op. At this point, we know that only the DemandedMask bits of the /// result of Op are ever used downstream. If we can use this information to /// simplify Op, create a new simplified DAG node and return true, returning Index: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp =================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -342,11 +342,16 @@ /// If the specified instruction has a constant integer operand and there are /// bits set in that constant that are not demanded, then clear those bits and /// return true. -bool TargetLowering::TargetLoweringOpt::ShrinkDemandedConstant( - SDValue Op, const APInt &Demanded) { +bool TargetLowering::ShrinkDemandedConstant(SDValue Op, const APInt &Demanded, + TargetLoweringOpt &TLO) const { + SelectionDAG &DAG = TLO.DAG; SDLoc DL(Op); unsigned Opcode = Op.getOpcode(); + // Do target-specific constant optimization. + if (targetShrinkDemandedConstant(Op, Demanded, TLO)) + return TLO.New.getNode(); + // FIXME: ISD::SELECT, ISD::SELECT_CC switch (Opcode) { default: @@ -367,7 +372,7 @@ EVT VT = Op.getValueType(); SDValue NewC = DAG.getConstant(Demanded & C, DL, VT); SDValue NewOp = DAG.getNode(Opcode, DL, VT, Op.getOperand(0), NewC); - return CombineTo(Op, NewOp); + return TLO.CombineTo(Op, NewOp); } break; @@ -380,15 +385,17 @@ /// Convert x+y to (VT)((SmallVT)x+(SmallVT)y) if the casts are free. /// This uses isZExtFree and ZERO_EXTEND for the widening cast, but it could be /// generalized for targets with other types of implicit widening casts. -bool TargetLowering::TargetLoweringOpt::ShrinkDemandedOp(SDValue Op, - unsigned BitWidth, - const APInt &Demanded, - const SDLoc &dl) { +bool TargetLowering::ShrinkDemandedOp(SDValue Op, unsigned BitWidth, + const APInt &Demanded, + TargetLoweringOpt &TLO) const { assert(Op.getNumOperands() == 2 && "ShrinkDemandedOp only supports binary operators!"); assert(Op.getNode()->getNumValues() == 1 && "ShrinkDemandedOp only supports nodes with one result!"); + SelectionDAG &DAG = TLO.DAG; + SDLoc dl(Op); + // Early return, as this function cannot handle vector types. if (Op.getValueType().isVector()) return false; @@ -418,23 +425,22 @@ bool NeedZext = DemandedSize > SmallVTBits; SDValue Z = DAG.getNode(NeedZext ? ISD::ZERO_EXTEND : ISD::ANY_EXTEND, dl, Op.getValueType(), X); - return CombineTo(Op, Z); + return TLO.CombineTo(Op, Z); } } return false; } bool -TargetLowering::TargetLoweringOpt::SimplifyDemandedBits(SDNode *User, - unsigned OpIdx, - const APInt &Demanded, - DAGCombinerInfo &DCI) { - const TargetLowering &TLI = DAG.getTargetLoweringInfo(); +TargetLowering::SimplifyDemandedBits(SDNode *User, unsigned OpIdx, + const APInt &Demanded, + DAGCombinerInfo &DCI, + TargetLoweringOpt &TLO) const { SDValue Op = User->getOperand(OpIdx); APInt KnownZero, KnownOne; - if (!TLI.SimplifyDemandedBits(Op, Demanded, KnownZero, KnownOne, - *this, 0, true)) + if (!SimplifyDemandedBits(Op, Demanded, KnownZero, KnownOne, + TLO, 0, true)) return false; @@ -446,9 +452,9 @@ // with the value 'x', which will give us: // Old = i32 and x, 0xffffff // New = x - if (Old.hasOneUse()) { + if (TLO.Old.hasOneUse()) { // For the one use case, we just commit the change. - DCI.CommitTargetLoweringOpt(*this); + DCI.CommitTargetLoweringOpt(TLO); return true; } @@ -456,17 +462,17 @@ // AssumeSingleUse flag is not propogated to recursive calls of // SimplifyDemanded bits, so the only node with multiple use that // it will attempt to combine will be opt. - assert(Old == Op); + assert(TLO.Old == Op); SmallVector NewOps; for (unsigned i = 0, e = User->getNumOperands(); i != e; ++i) { if (i == OpIdx) { - NewOps.push_back(New); + NewOps.push_back(TLO.New); continue; } NewOps.push_back(User->getOperand(i)); } - DAG.UpdateNodeOperands(User, NewOps); + TLO.DAG.UpdateNodeOperands(User, NewOps); // Op has less users now, so we may be able to perform additional combines // with it. DCI.AddToWorklist(Op.getNode()); @@ -585,7 +591,7 @@ // If any of the set bits in the RHS are known zero on the LHS, shrink // the constant. - if (TLO.ShrinkDemandedConstant(Op, ~LHSZero & NewMask)) + if (ShrinkDemandedConstant(Op, ~LHSZero & NewMask, TLO)) return true; // Bitwise-not (xor X, -1) is a special case: we don't usually shrink its @@ -620,10 +626,10 @@ if ((NewMask & (KnownZero|KnownZero2)) == NewMask) return TLO.CombineTo(Op, TLO.DAG.getConstant(0, dl, Op.getValueType())); // If the RHS is a constant, see if we can simplify it. - if (TLO.ShrinkDemandedConstant(Op, ~KnownZero2 & NewMask)) + if (ShrinkDemandedConstant(Op, ~KnownZero2 & NewMask, TLO)) return true; // If the operation can be done in a smaller type, do so. - if (TLO.ShrinkDemandedOp(Op, BitWidth, NewMask, dl)) + if (ShrinkDemandedOp(Op, BitWidth, NewMask, TLO)) return true; // Output known-1 bits are only known if set in both the LHS & RHS. @@ -654,10 +660,10 @@ if ((NewMask & ~KnownZero2 & KnownOne) == (~KnownZero2 & NewMask)) return TLO.CombineTo(Op, Op.getOperand(1)); // If the RHS is a constant, see if we can simplify it. - if (TLO.ShrinkDemandedConstant(Op, NewMask)) + if (ShrinkDemandedConstant(Op, NewMask, TLO)) return true; // If the operation can be done in a smaller type, do so. - if (TLO.ShrinkDemandedOp(Op, BitWidth, NewMask, dl)) + if (ShrinkDemandedOp(Op, BitWidth, NewMask, TLO)) return true; // Output known-0 bits are only known if clear in both the LHS & RHS. @@ -682,7 +688,7 @@ if ((KnownZero2 & NewMask) == NewMask) return TLO.CombineTo(Op, Op.getOperand(1)); // If the operation can be done in a smaller type, do so. - if (TLO.ShrinkDemandedOp(Op, BitWidth, NewMask, dl)) + if (ShrinkDemandedOp(Op, BitWidth, NewMask, TLO)) return true; // If all of the unknown bits are known to be zero on one side or the other @@ -727,7 +733,7 @@ } // If it already has all the bits set, nothing to change // but don't shrink either! - } else if (TLO.ShrinkDemandedConstant(Op, NewMask)) { + } else if (ShrinkDemandedConstant(Op, NewMask, TLO)) { return true; } } @@ -746,7 +752,7 @@ assert((KnownZero2 & KnownOne2) == 0 && "Bits known to be one AND zero?"); // If the operands are constants, see if we can simplify them. - if (TLO.ShrinkDemandedConstant(Op, NewMask)) + if (ShrinkDemandedConstant(Op, NewMask, TLO)) return true; // Only known if known in both the LHS and RHS. @@ -764,7 +770,7 @@ assert((KnownZero2 & KnownOne2) == 0 && "Bits known to be one AND zero?"); // If the operands are constants, see if we can simplify them. - if (TLO.ShrinkDemandedConstant(Op, NewMask)) + if (ShrinkDemandedConstant(Op, NewMask, TLO)) return true; // Only known if known in both the LHS and RHS. @@ -1284,7 +1290,7 @@ SimplifyDemandedBits(Op.getOperand(1), LoMask, KnownZero2, KnownOne2, TLO, Depth+1) || // See if the operation should be performed at a smaller bit width. - TLO.ShrinkDemandedOp(Op, BitWidth, NewMask, dl)) { + ShrinkDemandedOp(Op, BitWidth, NewMask, TLO)) { const SDNodeFlags *Flags = Op.getNode()->getFlags(); if (Flags->hasNoSignedWrap() || Flags->hasNoUnsignedWrap()) { // Disable the nsw and nuw flags. We can no longer guarantee that we Index: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h =================================================================== --- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h +++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h @@ -255,6 +255,9 @@ const SelectionDAG &DAG, unsigned Depth = 0) const override; + bool targetShrinkDemandedConstant(SDValue Op, const APInt &Demanded, + TargetLoweringOpt &TLO) const override; + MVT getScalarShiftAmountTy(const DataLayout &DL, EVT) const override; /// Returns true if the target allows unaligned memory accesses of the Index: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp +++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp @@ -91,6 +91,7 @@ STATISTIC(NumTailCalls, "Number of tail calls"); STATISTIC(NumShiftInserts, "Number of vector shift inserts"); +STATISTIC(NumOptimizedImms, "Number of times immediates were optimized"); static cl::opt EnableAArch64SlrGeneration("aarch64-shift-insert-generation", cl::Hidden, @@ -105,6 +106,12 @@ cl::desc("Allow AArch64 Local Dynamic TLS code generation"), cl::init(false)); +static cl::opt +EnableOptimizeLogicalImm("aarch64-enable-logical-imm", cl::Hidden, + cl::desc("Enable AArch64 logical imm instruction " + "optimization"), + cl::init(true)); + /// Value type used for condition codes. static const MVT MVT_CC = MVT::i32; @@ -787,6 +794,138 @@ return VT.changeVectorElementTypeToInteger(); } +static bool optimizeLogicalImm(SDValue Op, unsigned Size, uint64_t Imm, + const APInt &Demanded, + TargetLowering::TargetLoweringOpt &TLO, + unsigned NewOpc) { + uint64_t OldImm = Imm, NewImm, Enc; + uint64_t Mask = ((uint64_t)(-1LL) >> (64 - Size)); + + // Return if the immediate is already a bimm32 or bimm64. + if (AArch64_AM::isLogicalImmediate(Imm & Mask, Size)) + return false; + + unsigned EltSize = Size; + uint64_t DemandedBits = Demanded.getZExtValue(); + + // Clear bits that are not demanded. + Imm &= DemandedBits; + + while (true) { + // The goal here is to set the non-demanded bits in a way that minimizes + // the number of switching between 0 and 1. In order to achieve this goal, + // we set the non-demanded bits to the value of the preceding demanded bits. + // For example, if we have an immediate 0bx10xx0x1 ('x' indicates a + // non-demanded bit), we copy bit0 (1) to the least significant 'x', + // bit2 (0) to 'xx', and bit6 (1) to the most significant 'x'. + // The final result is 0b11000011. + uint64_t NonDemandedBits = ~DemandedBits; + uint64_t InvertedImm = ~Imm & DemandedBits; + uint64_t RotatedImm = + ((InvertedImm << 1) | (InvertedImm >> (EltSize - 1) & 1)) & + NonDemandedBits; + uint64_t Sum = RotatedImm + NonDemandedBits; + bool Carry = NonDemandedBits & ~Sum & (1 << (EltSize - 1)); + uint64_t Ones = (Sum + Carry) & NonDemandedBits; + NewImm = (Imm | Ones) & Mask; + + // If NewImm or its bitwise NOT is a shifted mask, it is a bitmask immediate + // or all-ones or all-zeros, in which case we can stop searching. Otherwise, + // we halve the element size and continue the search. + if (isShiftedMask_64(NewImm) || isShiftedMask_64(~(NewImm | ~Mask))) + break; + + // We cannot shrink the element size any further if it is 2-bits. + if (EltSize == 2) + return false; + + EltSize /= 2; + Mask >>= EltSize; + uint64_t Hi = Imm >> EltSize, DemandedBitsHi = DemandedBits >> EltSize; + + // Return if there is mismatch in any of the demanded bits of Imm and Hi. + if (((Imm ^ Hi) & (DemandedBits & DemandedBitsHi) & Mask) != 0) + return false; + + // Merge the upper and lower halves of Imm and DemandedBits. + Imm |= Hi; + DemandedBits |= DemandedBitsHi; + } + + ++NumOptimizedImms; + + // Replicate the element across the register width. + while (EltSize < Size) { + NewImm |= NewImm << EltSize; + EltSize *= 2; + } + + (void)OldImm; + assert(((OldImm ^ NewImm) & Demanded.getZExtValue()) == 0 && + "demanded bits should never be altered"); + + // Create the new constant immediate node. + EVT VT = Op.getValueType(); + unsigned Population = countPopulation(NewImm); + SDLoc DL(Op); + + // If the new constant immediate is all-zeros or all-ones, let the target + // independent DAG combine optimize this node. + if (Population == 0 || Population == Size) + return TLO.CombineTo(Op.getOperand(1), TLO.DAG.getConstant(NewImm, DL, VT)); + + // Otherwise, create a machine node so that target independent DAG combine + // doesn't undo this optimization. + Enc = AArch64_AM::encodeLogicalImmediate(NewImm, Size); + SDValue EncConst = TLO.DAG.getTargetConstant(Enc, DL, VT); + SDValue New( + TLO.DAG.getMachineNode(NewOpc, DL, VT, Op.getOperand(0), EncConst), 0); + + return TLO.CombineTo(Op, New); +} + +bool AArch64TargetLowering::targetShrinkDemandedConstant( + SDValue Op, const APInt &Demanded, TargetLoweringOpt &TLO) const { + // Delay this optimization to as late as possible. + if (!TLO.LegalOps) + return false; + + if (!EnableOptimizeLogicalImm) + return false; + + EVT VT = Op.getValueType(); + if (VT.isVector()) + return false; + + unsigned Size = VT.getSizeInBits(); + assert((Size == 32 || Size == 64) && + "i32 or i64 is expected after legalization."); + + // Exit early if we demand all bits. + if (Demanded.countPopulation() == Size) + return false; + + unsigned NewOpc; + switch (Op.getOpcode()) { + default: + return false; + case ISD::AND: + NewOpc = Size == 32 ? AArch64::ANDWri : AArch64::ANDXri; + break; + case ISD::OR: + NewOpc = Size == 32 ? AArch64::ORRWri : AArch64::ORRXri; + break; + case ISD::XOR: + NewOpc = Size == 32 ? AArch64::EORWri : AArch64::EORXri; + break; + } + ConstantSDNode *C = dyn_cast(Op.getOperand(1)); + if (!C) + return false; + uint64_t Imm = C->getZExtValue(); + return optimizeLogicalImm(Op, Size, Imm, Demanded, TLO, NewOpc); +} + /// computeKnownBitsForTargetNode - Determine which of the bits specified in /// Mask are known to be either zero or one and return them in the /// KnownZero/KnownOne bitsets. Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp +++ llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp @@ -2315,12 +2315,13 @@ SelectionDAG &DAG = DCI.DAG; SDValue Op = Node24->getOperand(OpIdx); + const TargetLowering &TLI = DAG.getTargetLoweringInfo(); EVT VT = Op.getValueType(); APInt Demanded = APInt::getLowBitsSet(VT.getSizeInBits(), 24); APInt KnownZero, KnownOne; TargetLowering::TargetLoweringOpt TLO(DAG, true, true); - if (TLO.SimplifyDemandedBits(Node24, OpIdx, Demanded, DCI)) + if (TLI.SimplifyDemandedBits(Node24, OpIdx, Demanded, DCI, TLO)) return true; return false; @@ -3361,7 +3362,7 @@ TargetLowering::TargetLoweringOpt TLO(DAG, !DCI.isBeforeLegalize(), !DCI.isBeforeLegalizeOps()); const TargetLowering &TLI = DAG.getTargetLoweringInfo(); - if (TLO.ShrinkDemandedConstant(BitsFrom, Demanded) || + if (TLI.ShrinkDemandedConstant(BitsFrom, Demanded, TLO) || TLI.SimplifyDemandedBits(BitsFrom, Demanded, KnownZero, KnownOne, TLO)) { DCI.CommitTargetLoweringOpt(TLO); Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp @@ -30207,7 +30207,7 @@ APInt KnownZero, KnownOne; TargetLowering::TargetLoweringOpt TLO(DAG, DCI.isBeforeLegalize(), DCI.isBeforeLegalizeOps()); - if (TLO.ShrinkDemandedConstant(Cond, DemandedMask) || + if (TLI.ShrinkDemandedConstant(Cond, DemandedMask, TLO) || TLI.SimplifyDemandedBits(Cond, DemandedMask, KnownZero, KnownOne, TLO)) { // If we changed the computation somewhere in the DAG, this change will @@ -33777,7 +33777,7 @@ TargetLowering::TargetLoweringOpt TLO(DAG, !DCI.isBeforeLegalize(), !DCI.isBeforeLegalizeOps()); const TargetLowering &TLI = DAG.getTargetLoweringInfo(); - if (TLO.ShrinkDemandedConstant(Op1, DemandedMask) || + if (TLI.ShrinkDemandedConstant(Op1, DemandedMask, TLO) || TLI.SimplifyDemandedBits(Op1, DemandedMask, KnownZero, KnownOne, TLO)) DCI.CommitTargetLoweringOpt(TLO); } Index: llvm/trunk/lib/Target/XCore/XCoreISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/XCore/XCoreISelLowering.cpp +++ llvm/trunk/lib/Target/XCore/XCoreISelLowering.cpp @@ -1605,7 +1605,7 @@ TargetLowering::TargetLoweringOpt TLO(DAG, !DCI.isBeforeLegalize(), !DCI.isBeforeLegalizeOps()); const TargetLowering &TLI = DAG.getTargetLoweringInfo(); - if (TLO.ShrinkDemandedConstant(OutVal, DemandedMask) || + if (TLI.ShrinkDemandedConstant(OutVal, DemandedMask, TLO) || TLI.SimplifyDemandedBits(OutVal, DemandedMask, KnownZero, KnownOne, TLO)) DCI.CommitTargetLoweringOpt(TLO); @@ -1622,7 +1622,7 @@ TargetLowering::TargetLoweringOpt TLO(DAG, !DCI.isBeforeLegalize(), !DCI.isBeforeLegalizeOps()); const TargetLowering &TLI = DAG.getTargetLoweringInfo(); - if (TLO.ShrinkDemandedConstant(Time, DemandedMask) || + if (TLI.ShrinkDemandedConstant(Time, DemandedMask, TLO) || TLI.SimplifyDemandedBits(Time, DemandedMask, KnownZero, KnownOne, TLO)) DCI.CommitTargetLoweringOpt(TLO); Index: llvm/trunk/test/CodeGen/AArch64/optimize-imm.ll =================================================================== --- llvm/trunk/test/CodeGen/AArch64/optimize-imm.ll +++ llvm/trunk/test/CodeGen/AArch64/optimize-imm.ll @@ -0,0 +1,64 @@ +; RUN: llc -o - %s -mtriple=aarch64-- | FileCheck %s + +; CHECK-LABEL: and1: +; CHECK: and {{w[0-9]+}}, w0, #0xfffffffd + +define void @and1(i32 %a, i8* nocapture %p) { +entry: + %and = and i32 %a, 253 + %conv = trunc i32 %and to i8 + store i8 %conv, i8* %p, align 1 + ret void +} + +; (a & 0x3dfd) | 0xffffc000 +; +; CHECK-LABEL: and2: +; CHECK: and {{w[0-9]+}}, w0, #0xfdfdfdfd + +define i32 @and2(i32 %a) { +entry: + %and = and i32 %a, 15869 + %or = or i32 %and, -16384 + ret i32 %or +} + +; (a & 0x19) | 0xffffffc0 +; +; CHECK-LABEL: and3: +; CHECK: and {{w[0-9]+}}, w0, #0x99999999 + +define i32 @and3(i32 %a) { +entry: + %and = and i32 %a, 25 + %or = or i32 %and, -64 + ret i32 %or +} + +; (a & 0xc5600) | 0xfff1f1ff +; +; CHECK-LABEL: and4: +; CHECK: and {{w[0-9]+}}, w0, #0xfffc07ff + +define i32 @and4(i32 %a) { +entry: + %and = and i32 %a, 787968 + %or = or i32 %and, -921089 + ret i32 %or +} + +; Make sure we don't shrink or optimize an XOR's immediate operand if the +; immediate is -1. Instruction selection turns (and ((xor $mask, -1), $v0)) into +; a BIC. + +; CHECK-LABEL: xor1: +; CHECK: orr [[R0:w[0-9]+]], wzr, #0x38 +; CHECK: bic {{w[0-9]+}}, [[R0]], w0, lsl #3 + +define i32 @xor1(i32 %a) { +entry: + %shl = shl i32 %a, 3 + %xor = and i32 %shl, 56 + %and = xor i32 %xor, 56 + ret i32 %and +}