bool MemsetRange::isProfitableToUseMemset(const TargetData &TD) const {
// If we found more than 8 stores to merge or 64 bytes, use memset.
if (TheStores.size() >= 8 || End-Start >= 64) return true;
// Assume that the code generator is capable of merging pairs of stores
// together if it wants to.
if (TheStores.size() <= 2) return false;
// If we have fewer than 8 stores, it can still be worthwhile to do this.
// For example, merging 4 i8 stores into an i32 store is useful almost always.
// However, merging 2 32-bit stores isn't useful on a 32-bit architecture (the
// memset will be split into 2 32-bit stores anyway) and doing so can
// pessimize the llvm optimizer.
//
// Since we don't have perfect knowledge here, make some assumptions: assume
// the maximum GPR width is the same size as the pointer size and assume that
// this width can be stored. If so, check to see whether we will end up
// actually reducing the number of stores used.
unsigned Bytes = unsigned(End-Start);
unsigned NumPointerStores = Bytes/TD.getPointerSize();
// Assume the remaining bytes if any are done a byte at a time.
unsigned NumByteStores = Bytes - NumPointerStores*TD.getPointerSize();
// If we will reduce the # stores (according to this heuristic), do the
// transformation. This encourages merging 4 x i8 -> i32 and 2 x i16 -> i32
// etc.
return TheStores.size() > NumPointerStores+NumByteStores;
}
static unsigned getTypeSize(TargetData &TD, Type *type) {
if (type->isFunctionTy()) /* it is not sized, weird */
return TD.getPointerSize();
if (!type->isSized())
return 100; /* FIXME */
if (StructType *ST = dyn_cast<StructType>(type))
return TD.getStructLayout(ST)->getSizeInBytes();
return TD.getTypeAllocSize(type);
}
/// getEntrySize - Return the size of each entry in the jump table.
unsigned MachineJumpTableInfo::getEntrySize(const TargetData &TD) const {
// The size of a jump table entry is 4 bytes unless the entry is just the
// address of a block, in which case it is the pointer size.
switch (getEntryKind()) {
case MachineJumpTableInfo::EK_BlockAddress:
return TD.getPointerSize();
case MachineJumpTableInfo::EK_GPRel32BlockAddress:
case MachineJumpTableInfo::EK_LabelDifference32:
case MachineJumpTableInfo::EK_Custom32:
return 4;
case MachineJumpTableInfo::EK_Inline:
return 0;
}
assert(0 && "Unknown jump table encoding!");
return ~0;
}
