+/// OptimizeAndOrXor - Optimize a series of operands to an 'and', 'or', or 'xor'
+/// instruction. This optimizes based on identities. If it can be reduced to
+/// a single Value, it is returned, otherwise the Ops list is mutated as
+/// necessary.
+static Value *OptimizeAndOrXor(unsigned Opcode,
+ SmallVectorImpl<ValueEntry> &Ops) {
+ // Scan the operand lists looking for X and ~X pairs, along with X,X pairs.
+ // If we find any, we can simplify the expression. X&~X == 0, X|~X == -1.
+ for (unsigned i = 0, e = Ops.size(); i != e; ++i) {
+ // First, check for X and ~X in the operand list.
+ assert(i < Ops.size());
+ if (BinaryOperator::isNot(Ops[i].Op)) { // Cannot occur for ^.
+ Value *X = BinaryOperator::getNotArgument(Ops[i].Op);
+ unsigned FoundX = FindInOperandList(Ops, i, X);
+ if (FoundX != i) {
+ if (Opcode == Instruction::And) // ...&X&~X = 0
+ return Constant::getNullValue(X->getType());
+
+ if (Opcode == Instruction::Or) // ...|X|~X = -1
+ return Constant::getAllOnesValue(X->getType());
+ }
+ }
+
+ // Next, check for duplicate pairs of values, which we assume are next to
+ // each other, due to our sorting criteria.
+ assert(i < Ops.size());
+ if (i+1 != Ops.size() && Ops[i+1].Op == Ops[i].Op) {
+ if (Opcode == Instruction::And || Opcode == Instruction::Or) {
+ // Drop duplicate values for And and Or.
+ Ops.erase(Ops.begin()+i);
+ --i; --e;
+ ++NumAnnihil;
+ continue;
+ }
+
+ // Drop pairs of values for Xor.
+ assert(Opcode == Instruction::Xor);
+ if (e == 2)
+ return Constant::getNullValue(Ops[0].Op->getType());
+
+ // Y ^ X^X -> Y
+ Ops.erase(Ops.begin()+i, Ops.begin()+i+2);
+ i -= 1; e -= 2;
+ ++NumAnnihil;
+ }
+ }
+ return 0;
+}
+
+/// OptimizeAdd - Optimize a series of operands to an 'add' instruction. This
+/// optimizes based on identities. If it can be reduced to a single Value, it
+/// is returned, otherwise the Ops list is mutated as necessary.
+Value *Reassociate::OptimizeAdd(Instruction *I,
+ SmallVectorImpl<ValueEntry> &Ops) {
+ // Scan the operand lists looking for X and -X pairs. If we find any, we
+ // can simplify the expression. X+-X == 0. While we're at it, scan for any
+ // duplicates. We want to canonicalize Y+Y+Y+Z -> 3*Y+Z.
+ //
+ // TODO: We could handle "X + ~X" -> "-1" if we wanted, since "-X = ~X+1".
+ //
+ for (unsigned i = 0, e = Ops.size(); i != e; ++i) {
+ Value *TheOp = Ops[i].Op;
+ // Check to see if we've seen this operand before. If so, we factor all
+ // instances of the operand together. Due to our sorting criteria, we know
+ // that these need to be next to each other in the vector.
+ if (i+1 != Ops.size() && Ops[i+1].Op == TheOp) {
+ // Rescan the list, remove all instances of this operand from the expr.
+ unsigned NumFound = 0;
+ do {
+ Ops.erase(Ops.begin()+i);
+ ++NumFound;
+ } while (i != Ops.size() && Ops[i].Op == TheOp);
+
+ DEBUG(errs() << "\nFACTORING [" << NumFound << "]: " << *TheOp << '\n');
+ ++NumFactor;
+
+ // Insert a new multiply.
+ Value *Mul = ConstantInt::get(cast<IntegerType>(I->getType()), NumFound);
+ Mul = BinaryOperator::CreateMul(TheOp, Mul, "factor", I);
+
+ // Now that we have inserted a multiply, optimize it. This allows us to
+ // handle cases that require multiple factoring steps, such as this:
+ // (X*2) + (X*2) + (X*2) -> (X*2)*3 -> X*6
+ RedoInsts.push_back(Mul);
+
+ // If every add operand was a duplicate, return the multiply.
+ if (Ops.empty())
+ return Mul;
+
+ // Otherwise, we had some input that didn't have the dupe, such as
+ // "A + A + B" -> "A*2 + B". Add the new multiply to the list of
+ // things being added by this operation.
+ Ops.insert(Ops.begin(), ValueEntry(getRank(Mul), Mul));
+
+ --i;
+ e = Ops.size();
+ continue;
+ }
+
+ // Check for X and -X in the operand list.
+ if (!BinaryOperator::isNeg(TheOp))
+ continue;
+
+ Value *X = BinaryOperator::getNegArgument(TheOp);
+ unsigned FoundX = FindInOperandList(Ops, i, X);
+ if (FoundX == i)
+ continue;
+
+ // Remove X and -X from the operand list.
+ if (Ops.size() == 2)
+ return Constant::getNullValue(X->getType());
+
+ Ops.erase(Ops.begin()+i);
+ if (i < FoundX)
+ --FoundX;
+ else
+ --i; // Need to back up an extra one.
+ Ops.erase(Ops.begin()+FoundX);
+ ++NumAnnihil;
+ --i; // Revisit element.
+ e -= 2; // Removed two elements.
+ }
+
+ // Scan the operand list, checking to see if there are any common factors
+ // between operands. Consider something like A*A+A*B*C+D. We would like to
+ // reassociate this to A*(A+B*C)+D, which reduces the number of multiplies.
+ // To efficiently find this, we count the number of times a factor occurs
+ // for any ADD operands that are MULs.
+ DenseMap<Value*, unsigned> FactorOccurrences;
+
+ // Keep track of each multiply we see, to avoid triggering on (X*4)+(X*4)
+ // where they are actually the same multiply.
+ unsigned MaxOcc = 0;
+ Value *MaxOccVal = 0;
+ for (unsigned i = 0, e = Ops.size(); i != e; ++i) {
+ BinaryOperator *BOp = dyn_cast<BinaryOperator>(Ops[i].Op);
+ if (BOp == 0 || BOp->getOpcode() != Instruction::Mul || !BOp->use_empty())
+ continue;
+
+ // Compute all of the factors of this added value.
+ SmallVector<Value*, 8> Factors;
+ FindSingleUseMultiplyFactors(BOp, Factors, Ops, true);
+ assert(Factors.size() > 1 && "Bad linearize!");
+
+ // Add one to FactorOccurrences for each unique factor in this op.
+ SmallPtrSet<Value*, 8> Duplicates;
+ for (unsigned i = 0, e = Factors.size(); i != e; ++i) {
+ Value *Factor = Factors[i];
+ if (!Duplicates.insert(Factor)) continue;
+
+ unsigned Occ = ++FactorOccurrences[Factor];
+ if (Occ > MaxOcc) { MaxOcc = Occ; MaxOccVal = Factor; }
+
+ // If Factor is a negative constant, add the negated value as a factor
+ // because we can percolate the negate out. Watch for minint, which
+ // cannot be positivified.
+ if (ConstantInt *CI = dyn_cast<ConstantInt>(Factor))
+ if (CI->isNegative() && !CI->isMinValue(true)) {
+ Factor = ConstantInt::get(CI->getContext(), -CI->getValue());
+ assert(!Duplicates.count(Factor) &&
+ "Shouldn't have two constant factors, missed a canonicalize");
+
+ unsigned Occ = ++FactorOccurrences[Factor];
+ if (Occ > MaxOcc) { MaxOcc = Occ; MaxOccVal = Factor; }
+ }
+ }
+ }
+
+ // If any factor occurred more than one time, we can pull it out.
+ if (MaxOcc > 1) {
+ DEBUG(errs() << "\nFACTORING [" << MaxOcc << "]: " << *MaxOccVal << '\n');
+ ++NumFactor;
+
+ // Create a new instruction that uses the MaxOccVal twice. If we don't do
+ // this, we could otherwise run into situations where removing a factor
+ // from an expression will drop a use of maxocc, and this can cause
+ // RemoveFactorFromExpression on successive values to behave differently.
+ Instruction *DummyInst = BinaryOperator::CreateAdd(MaxOccVal, MaxOccVal);
+ SmallVector<Value*, 4> NewMulOps;
+ for (unsigned i = 0; i != Ops.size(); ++i) {
+ // Only try to remove factors from expressions we're allowed to.
+ BinaryOperator *BOp = dyn_cast<BinaryOperator>(Ops[i].Op);
+ if (BOp == 0 || BOp->getOpcode() != Instruction::Mul || !BOp->use_empty())
+ continue;
+
+ if (Value *V = RemoveFactorFromExpression(Ops[i].Op, MaxOccVal)) {
+ // The factorized operand may occur several times. Convert them all in
+ // one fell swoop.
+ for (unsigned j = Ops.size(); j != i;) {
+ --j;
+ if (Ops[j].Op == Ops[i].Op) {
+ NewMulOps.push_back(V);
+ Ops.erase(Ops.begin()+j);
+ }
+ }
+ --i;
+ }
+ }
+
+ // No need for extra uses anymore.
+ delete DummyInst;
+
+ unsigned NumAddedValues = NewMulOps.size();
+ Value *V = EmitAddTreeOfValues(I, NewMulOps);
+
+ // Now that we have inserted the add tree, optimize it. This allows us to
+ // handle cases that require multiple factoring steps, such as this:
+ // A*A*B + A*A*C --> A*(A*B+A*C) --> A*(A*(B+C))
+ assert(NumAddedValues > 1 && "Each occurrence should contribute a value");
+ (void)NumAddedValues;
+ V = ReassociateExpression(cast<BinaryOperator>(V));
+
+ // Create the multiply.
+ Value *V2 = BinaryOperator::CreateMul(V, MaxOccVal, "tmp", I);