int ARMTTIImpl::getIntImmCost(const APInt &Imm, Type *Ty) {
assert(Ty->isIntegerTy());
unsigned Bits = Ty->getPrimitiveSizeInBits();
if (Bits == 0 || Imm.getActiveBits() >= 64)
return 4;
int64_t SImmVal = Imm.getSExtValue();
uint64_t ZImmVal = Imm.getZExtValue();
if (!ST->isThumb()) {
if ((SImmVal >= 0 && SImmVal < 65536) ||
(ARM_AM::getSOImmVal(ZImmVal) != -1) ||
(ARM_AM::getSOImmVal(~ZImmVal) != -1))
return 1;
return ST->hasV6T2Ops() ? 2 : 3;
}
if (ST->isThumb2()) {
if ((SImmVal >= 0 && SImmVal < 65536) ||
(ARM_AM::getT2SOImmVal(ZImmVal) != -1) ||
(ARM_AM::getT2SOImmVal(~ZImmVal) != -1))
return 1;
return ST->hasV6T2Ops() ? 2 : 3;
}
// Thumb1, any i8 imm cost 1.
if (Bits == 8 || (SImmVal >= 0 && SImmVal < 256))
return 1;
if ((~SImmVal < 256) || ARM_AM::isThumbImmShiftedVal(ZImmVal))
return 2;
// Load from constantpool.
return 3;
}
/// When we're compiling N-bit code, and the user uses parameters that are
/// greater than N bits (e.g. uint64_t on a 32-bit build), we can run into
/// trouble with APInt size issues. This function handles resizing + overflow
/// checks for us. Check and zext or trunc \p I depending on IntTyBits and
/// I's value.
bool ObjectSizeOffsetVisitor::CheckedZextOrTrunc(APInt &I) {
// More bits than we can handle. Checking the bit width isn't necessary, but
// it's faster than checking active bits, and should give `false` in the
// vast majority of cases.
if (I.getBitWidth() > IntTyBits && I.getActiveBits() > IntTyBits)
return false;
if (I.getBitWidth() != IntTyBits)
I = I.zextOrTrunc(IntTyBits);
return true;
}
void BDCE::determineLiveOperandBits(const Instruction *UserI,
const Instruction *I, unsigned OperandNo,
const APInt &AOut, APInt &AB,
APInt &KnownZero, APInt &KnownOne,
APInt &KnownZero2, APInt &KnownOne2) {
unsigned BitWidth = AB.getBitWidth();
// We're called once per operand, but for some instructions, we need to
// compute known bits of both operands in order to determine the live bits of
// either (when both operands are instructions themselves). We don't,
// however, want to do this twice, so we cache the result in APInts that live
// in the caller. For the two-relevant-operands case, both operand values are
// provided here.
auto ComputeKnownBits =
[&](unsigned BitWidth, const Value *V1, const Value *V2) {
const DataLayout &DL = I->getModule()->getDataLayout();
KnownZero = APInt(BitWidth, 0);
KnownOne = APInt(BitWidth, 0);
computeKnownBits(const_cast<Value *>(V1), KnownZero, KnownOne, DL, 0,
AC, UserI, DT);
if (V2) {
KnownZero2 = APInt(BitWidth, 0);
KnownOne2 = APInt(BitWidth, 0);
computeKnownBits(const_cast<Value *>(V2), KnownZero2, KnownOne2, DL,
0, AC, UserI, DT);
}
};
switch (UserI->getOpcode()) {
default: break;
case Instruction::Call:
case Instruction::Invoke:
if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(UserI))
switch (II->getIntrinsicID()) {
default: break;
case Intrinsic::bswap:
// The alive bits of the input are the swapped alive bits of
// the output.
AB = AOut.byteSwap();
break;
case Intrinsic::ctlz:
if (OperandNo == 0) {
// We need some output bits, so we need all bits of the
// input to the left of, and including, the leftmost bit
// known to be one.
ComputeKnownBits(BitWidth, I, nullptr);
AB = APInt::getHighBitsSet(BitWidth,
std::min(BitWidth, KnownOne.countLeadingZeros()+1));
}
break;
case Intrinsic::cttz:
if (OperandNo == 0) {
// We need some output bits, so we need all bits of the
// input to the right of, and including, the rightmost bit
// known to be one.
ComputeKnownBits(BitWidth, I, nullptr);
AB = APInt::getLowBitsSet(BitWidth,
std::min(BitWidth, KnownOne.countTrailingZeros()+1));
}
break;
}
break;
case Instruction::Add:
case Instruction::Sub:
// Find the highest live output bit. We don't need any more input
// bits than that (adds, and thus subtracts, ripple only to the
// left).
AB = APInt::getLowBitsSet(BitWidth, AOut.getActiveBits());
break;
case Instruction::Shl:
if (OperandNo == 0)
if (ConstantInt *CI =
dyn_cast<ConstantInt>(UserI->getOperand(1))) {
uint64_t ShiftAmt = CI->getLimitedValue(BitWidth-1);
AB = AOut.lshr(ShiftAmt);
// If the shift is nuw/nsw, then the high bits are not dead
// (because we've promised that they *must* be zero).
const ShlOperator *S = cast<ShlOperator>(UserI);
if (S->hasNoSignedWrap())
AB |= APInt::getHighBitsSet(BitWidth, ShiftAmt+1);
else if (S->hasNoUnsignedWrap())
AB |= APInt::getHighBitsSet(BitWidth, ShiftAmt);
}
break;
case Instruction::LShr:
if (OperandNo == 0)
if (ConstantInt *CI =
dyn_cast<ConstantInt>(UserI->getOperand(1))) {
uint64_t ShiftAmt = CI->getLimitedValue(BitWidth-1);
AB = AOut.shl(ShiftAmt);
// If the shift is exact, then the low bits are not dead
// (they must be zero).
if (cast<LShrOperator>(UserI)->isExact())
AB |= APInt::getLowBitsSet(BitWidth, ShiftAmt);
}
break;
case Instruction::AShr:
if (OperandNo == 0)
if (ConstantInt *CI =
dyn_cast<ConstantInt>(UserI->getOperand(1))) {
uint64_t ShiftAmt = CI->getLimitedValue(BitWidth-1);
AB = AOut.shl(ShiftAmt);
// Because the high input bit is replicated into the
// high-order bits of the result, if we need any of those
// bits, then we must keep the highest input bit.
if ((AOut & APInt::getHighBitsSet(BitWidth, ShiftAmt))
.getBoolValue())
AB.setBit(BitWidth-1);
// If the shift is exact, then the low bits are not dead
// (they must be zero).
if (cast<AShrOperator>(UserI)->isExact())
AB |= APInt::getLowBitsSet(BitWidth, ShiftAmt);
}
break;
case Instruction::And:
AB = AOut;
// For bits that are known zero, the corresponding bits in the
// other operand are dead (unless they're both zero, in which
// case they can't both be dead, so just mark the LHS bits as
// dead).
if (OperandNo == 0) {
ComputeKnownBits(BitWidth, I, UserI->getOperand(1));
AB &= ~KnownZero2;
} else {
if (!isa<Instruction>(UserI->getOperand(0)))
ComputeKnownBits(BitWidth, UserI->getOperand(0), I);
AB &= ~(KnownZero & ~KnownZero2);
}
break;
case Instruction::Or:
AB = AOut;
// For bits that are known one, the corresponding bits in the
// other operand are dead (unless they're both one, in which
// case they can't both be dead, so just mark the LHS bits as
// dead).
if (OperandNo == 0) {
ComputeKnownBits(BitWidth, I, UserI->getOperand(1));
AB &= ~KnownOne2;
} else {
if (!isa<Instruction>(UserI->getOperand(0)))
ComputeKnownBits(BitWidth, UserI->getOperand(0), I);
AB &= ~(KnownOne & ~KnownOne2);
}
break;
case Instruction::Xor:
case Instruction::PHI:
AB = AOut;
break;
case Instruction::Trunc:
AB = AOut.zext(BitWidth);
break;
case Instruction::ZExt:
AB = AOut.trunc(BitWidth);
break;
case Instruction::SExt:
AB = AOut.trunc(BitWidth);
// Because the high input bit is replicated into the
// high-order bits of the result, if we need any of those
// bits, then we must keep the highest input bit.
if ((AOut & APInt::getHighBitsSet(AOut.getBitWidth(),
AOut.getBitWidth() - BitWidth))
.getBoolValue())
AB.setBit(BitWidth-1);
break;
case Instruction::Select:
if (OperandNo != 0)
AB = AOut;
break;
}
}
APInt
swift::Compress::EncodeStringAsNumber(StringRef In, EncodingKind Kind) {
// Allocate enough space for the first character plus one bit which is the
// stop bit for variable length encoding.
unsigned BW = (1 + Huffman::LongestEncodingLength);
APInt num = APInt(BW, 0);
// We set the high bit to zero in order to support encoding
// of chars that start with zero (for variable length encoding).
if (Kind == EncodingKind::Variable) {
num = ++num;
}
// Encode variable-length strings.
if (Kind == EncodingKind::Variable) {
size_t num_bits = 0;
size_t bits = 0;
// Append the characters in the string in reverse. This will allow
// us to decode by appending to a string and not prepending.
for (int i = In.size() - 1; i >= 0; i--) {
char ch = In[i];
// The local variables 'bits' and 'num_bits' are used as a small
// bitstream. Keep accumulating bits into them until they overflow.
// At that point move them into the APInt.
uint64_t local_bits;
uint64_t local_num_bits;
// Find the huffman encoding of the character.
Huffman::variable_encode(local_bits, local_num_bits, ch);
// Add the encoded character into our bitstream.
num_bits += local_num_bits;
bits = (bits << local_num_bits) + local_bits;
// Check if there is enough room for another word. If not, flush
// the local bitstream into the APInt.
if (num_bits >= (64 - Huffman::LongestEncodingLength)) {
// Make room for the new bits and add the bits.
num = num.zext(num.getBitWidth() + num_bits);
num = num.shl(num_bits); num = num + bits;
num_bits = 0; bits = 0;
}
}
// Flush the local bitstream into the APInt number.
if (num_bits) {
num = num.zext(num.getBitWidth() + num_bits);
num = num.shl(num_bits); num = num + bits;
num_bits = 0; bits = 0;
}
// Make sure that we have a minimal word size to be able to perform
// calculations on our alphabet.
return num.zextOrSelf(std::max(64u, num.getBitWidth()));
}
// Encode fixed width strings.
for (int i = In.size() - 1; i >= 0; i--) {
char ch = In[i];
// Extend the number and create room for encoding another character.
unsigned MinBits = num.getActiveBits() + Huffman::LongestEncodingLength;
num = num.zextOrTrunc(std::max(64u, MinBits));
EncodeFixedWidth(num, ch);
}
return num;
}
/*
* method computeStats
*
* computes the statistics that require the processing to be complete.
*/
void llvm::RangeAnalysis::computeStats(){
for(DepGraph::iterator It = depGraph->begin(), Iend = depGraph->end(); It != Iend; It++){
GraphNode* Node = *It;
bool isIntegerVariable = false;
unsigned int currentBitWidth;
//We only count precision statistics of VarNodes and MemNodes
if (isa<OpNode>(Node)) {
numOps++;
continue;
}
if (isa<MemNode>(Node)) {
numMems++;
} else if (VarNode* VN = dyn_cast<VarNode>(Node)){
Value* V = VN->getValue();
if (isa<ConstantInt>(V)){
numConstants++;
} else {
//Only Variables are considered for bitwidth reduction
isIntegerVariable = V->getType()->isIntegerTy();
numVars++;
if(isIntegerVariable){
currentBitWidth = V->getType()->getPrimitiveSizeInBits();
usedBits += currentBitWidth;
}
}
} else assert(false && "Unknown Node Type");
assert(out_state.count(Node) && "Node not found in the list of computed ranges.");
Range CR = out_state[Node];
// If range is unknown, we have total needed bits
if (CR.isUnknown()) {
++numUnknown;
if (isIntegerVariable) needBits += currentBitWidth;
continue;
}
// If range is empty, we have 0 needed bits
if (CR.isEmpty()) {
++numEmpty;
continue;
}
if (CR.getLower().eq(Min)) {
if (CR.getUpper().eq(Max)) {
++numMaxRange;
}
else {
++numMinInfC;
}
}
else if (CR.getUpper().eq(Max)) {
++numCPlusInf;
}
else {
++numCC;
}
//Compute needed bits >> only for variables
if (isIntegerVariable) {
unsigned ub, lb;
if (CR.getLower().isNegative()) {
APInt abs = CR.getLower().abs();
lb = abs.getActiveBits() + 1;
} else {
lb = CR.getLower().getActiveBits() + 1;
}
if (CR.getUpper().isNegative()) {
APInt abs = CR.getUpper().abs();
ub = abs.getActiveBits() + 1;
} else {
ub = CR.getUpper().getActiveBits() + 1;
}
unsigned nBits = lb > ub ? lb : ub;
// If both bounds are positive, decrement needed bits by 1
if (!CR.getLower().isNegative() && !CR.getUpper().isNegative()) {
--nBits;
}
if (nBits < currentBitWidth) {
needBits += nBits;
} else {
needBits += currentBitWidth;
}
}
}
double totalB = usedBits;
double needB = needBits;
double reduction = (double) (totalB - needB) * 100 / totalB;
percentReduction = (unsigned int) reduction;
}