6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-06-14 14:24:05 +00:00
Code Issues Projects Releases Wiki Activity

Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).

Browse Source 
The SLP vectorizer should propagate IR-level optimization hints/flags (nsw, nuw, exact, fast-math)
when converting scalar instructions into vectors. But this isn't a simple copy - we need to take
the intersection (the logical 'and') of the sets of flags on the scalars.

The solution is further complicated because we can have non-uniform (non-SIMD) vector ops after:
http://reviews.llvm.org/D4015
http://llvm.org/viewvc/llvm-project?view=revision&revision=211339

The vast majority of changed files are existing tests that were not propagating IR flags, but I've
also added a new test file for focused testing of IR flag possibilities.

Differential Revision: http://reviews.llvm.org/D5172



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217051 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel
2014-09-03 17:40:30 +00:00
parent 6d66a1cd2f
commit b89304eb7c
13 changed files with 404 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -166,6 +166,23 @@ static unsigned getSameOpcode(ArrayRef<Value *> VL) {
return Opcode;
}
/// Get the intersection (logical and) of all of the potential IR flags
/// of each scalar operation (VL) that will be converted into a vector (I).
/// Flag set: NSW, NUW, exact, and all of fast-math.
static void propagateIRFlags(Value *I, ArrayRef<Value *> VL) {
if (auto *VecOp = dyn_cast<BinaryOperator>(I)) {
if (auto *Intersection = dyn_cast<BinaryOperator>(VL[0])) {
// Intersection is initialized to the 0th scalar,
// so start counting from index '1'.
for (int i = 1, e = VL.size(); i < e; ++i) {
if (auto *Scalar = dyn_cast<BinaryOperator>(VL[i]))
Intersection->andIRFlags(Scalar);
}
VecOp->copyIRFlags(Intersection);
}
}
}
/// \returns \p I after propagating metadata from \p VL.
static Instruction *propagateMetadata(Instruction *I, ArrayRef<Value *> VL) {
Instruction *I0 = cast<Instruction>(VL[0]);
@ -2031,6 +2048,7 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
BinaryOperator *BinOp = cast<BinaryOperator>(VL0);
Value *V = Builder.CreateBinOp(BinOp->getOpcode(), LHS, RHS);
E->VectorizedValue = V;
propagateIRFlags(E->VectorizedValue, E->Scalars);
++NumVectorInstructions;
if (Instruction *I = dyn_cast<Instruction>(V))
@ -2194,18 +2212,25 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
BinaryOperator *BinOp1 = cast<BinaryOperator>(VL1);
Value *V1 = Builder.CreateBinOp(BinOp1->getOpcode(), LHS, RHS);
// Create appropriate shuffle to take alternative operations from
// the vector.
std::vector<Constant *> Mask(E->Scalars.size());
// Create shuffle to take alternate operations from the vector.
// Also, gather up odd and even scalar ops to propagate IR flags to
// each vector operation.
ValueList OddScalars, EvenScalars;
unsigned e = E->Scalars.size();
SmallVector<Constant *, 8> Mask(e);
for (unsigned i = 0; i < e; ++i) {
if (i & 1)
if (i & 1) {
Mask[i] = Builder.getInt32(e + i);
else
OddScalars.push_back(E->Scalars[i]);
} else {
Mask[i] = Builder.getInt32(i);
EvenScalars.push_back(E->Scalars[i]);
}
}
Value *ShuffleMask = ConstantVector::get(Mask);
propagateIRFlags(V0, EvenScalars);
propagateIRFlags(V1, OddScalars);
Value *V = Builder.CreateShuffleVector(V0, V1, ShuffleMask);
E->VectorizedValue = V;