void X86InterleavedAccessGroup::decompose(
Instruction *VecInst, unsigned NumSubVectors, VectorType *SubVecTy,
SmallVectorImpl<Instruction *> &DecomposedVectors) {
assert((isa<LoadInst>(VecInst) || isa<ShuffleVectorInst>(VecInst)) &&
"Expected Load or Shuffle");
Type *VecTy = VecInst->getType();
(void)VecTy;
assert(VecTy->isVectorTy() &&
DL.getTypeSizeInBits(VecTy) >=
DL.getTypeSizeInBits(SubVecTy) * NumSubVectors &&
"Invalid Inst-size!!!");
if (auto *SVI = dyn_cast<ShuffleVectorInst>(VecInst)) {
Value *Op0 = SVI->getOperand(0);
Value *Op1 = SVI->getOperand(1);
// Generate N(= NumSubVectors) shuffles of T(= SubVecTy) type.
for (unsigned i = 0; i < NumSubVectors; ++i)
DecomposedVectors.push_back(
cast<ShuffleVectorInst>(Builder.CreateShuffleVector(
Op0, Op1,
createSequentialMask(Builder, Indices[i],
SubVecTy->getVectorNumElements(), 0))));
return;
}
// Decompose the load instruction.
LoadInst *LI = cast<LoadInst>(VecInst);
Type *VecBasePtrTy = SubVecTy->getPointerTo(LI->getPointerAddressSpace());
Value *VecBasePtr;
unsigned int NumLoads = NumSubVectors;
// In the case of stride 3 with a vector of 32 elements load the information
// in the following way:
// [0,1...,VF/2-1,VF/2+VF,VF/2+VF+1,...,2VF-1]
if (DL.getTypeSizeInBits(VecTy) == 768) {
Type *VecTran =
VectorType::get(Type::getInt8Ty(LI->getContext()), 16)->getPointerTo();
VecBasePtr = Builder.CreateBitCast(LI->getPointerOperand(), VecTran);
NumLoads = NumSubVectors * 2;
} else
VecBasePtr = Builder.CreateBitCast(LI->getPointerOperand(), VecBasePtrTy);
// Generate N loads of T type.
for (unsigned i = 0; i < NumLoads; i++) {
// TODO: Support inbounds GEP.
Value *NewBasePtr = Builder.CreateGEP(VecBasePtr, Builder.getInt32(i));
Instruction *NewLoad =
Builder.CreateAlignedLoad(NewBasePtr, LI->getAlignment());
DecomposedVectors.push_back(NewLoad);
}
}
/// \brief Helper to combine a load to a new type.
///
/// This just does the work of combining a load to a new type. It handles
/// metadata, etc., and returns the new instruction. The \c NewTy should be the
/// loaded *value* type. This will convert it to a pointer, cast the operand to
/// that pointer type, load it, etc.
///
/// Note that this will create all of the instructions with whatever insert
/// point the \c InstCombiner currently is using.
static LoadInst *combineLoadToNewType(InstCombiner &IC, LoadInst &LI, Type *NewTy,
const Twine &Suffix = "") {
Value *Ptr = LI.getPointerOperand();
unsigned AS = LI.getPointerAddressSpace();
SmallVector<std::pair<unsigned, MDNode *>, 8> MD;
LI.getAllMetadata(MD);
LoadInst *NewLoad = IC.Builder->CreateAlignedLoad(
IC.Builder->CreateBitCast(Ptr, NewTy->getPointerTo(AS)),
LI.getAlignment(), LI.getName() + Suffix);
MDBuilder MDB(NewLoad->getContext());
for (const auto &MDPair : MD) {
unsigned ID = MDPair.first;
MDNode *N = MDPair.second;
// Note, essentially every kind of metadata should be preserved here! This
// routine is supposed to clone a load instruction changing *only its type*.
// The only metadata it makes sense to drop is metadata which is invalidated
// when the pointer type changes. This should essentially never be the case
// in LLVM, but we explicitly switch over only known metadata to be
// conservatively correct. If you are adding metadata to LLVM which pertains
// to loads, you almost certainly want to add it here.
switch (ID) {
case LLVMContext::MD_dbg:
case LLVMContext::MD_tbaa:
case LLVMContext::MD_prof:
case LLVMContext::MD_fpmath:
case LLVMContext::MD_tbaa_struct:
case LLVMContext::MD_invariant_load:
case LLVMContext::MD_alias_scope:
case LLVMContext::MD_noalias:
case LLVMContext::MD_nontemporal:
case LLVMContext::MD_mem_parallel_loop_access:
// All of these directly apply.
NewLoad->setMetadata(ID, N);
break;
case LLVMContext::MD_nonnull:
// This only directly applies if the new type is also a pointer.
if (NewTy->isPointerTy()) {
NewLoad->setMetadata(ID, N);
break;
}
// If it's integral now, translate it to !range metadata.
if (NewTy->isIntegerTy()) {
auto *ITy = cast<IntegerType>(NewTy);
auto *NullInt = ConstantExpr::getPtrToInt(
ConstantPointerNull::get(cast<PointerType>(Ptr->getType())), ITy);
auto *NonNullInt =
ConstantExpr::getAdd(NullInt, ConstantInt::get(ITy, 1));
NewLoad->setMetadata(LLVMContext::MD_range,
MDB.createRange(NonNullInt, NullInt));
}
break;
case LLVMContext::MD_align:
case LLVMContext::MD_dereferenceable:
case LLVMContext::MD_dereferenceable_or_null:
// These only directly apply if the new type is also a pointer.
if (NewTy->isPointerTy())
NewLoad->setMetadata(ID, N);
break;
case LLVMContext::MD_range:
// FIXME: It would be nice to propagate this in some way, but the type
// conversions make it hard. If the new type is a pointer, we could
// translate it to !nonnull metadata.
break;
}
}
return NewLoad;
}