From 9433a28845dd2fa6953dfd44172c3986f6d9c664 Mon Sep 17 00:00:00 2001 From: Sanjay Patel Date: Wed, 3 Sep 2014 17:40:30 +0000 Subject: Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802). 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 llvm-svn: 217051 --- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp | 35 +++++++++++++++++++++---- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp') diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index 65987626edd..76b46779535 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -166,6 +166,23 @@ static unsigned getSameOpcode(ArrayRef 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 VL) { + if (auto *VecOp = dyn_cast(I)) { + if (auto *Intersection = dyn_cast(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(VL[i])) + Intersection->andIRFlags(Scalar); + } + VecOp->copyIRFlags(Intersection); + } + } +} + /// \returns \p I after propagating metadata from \p VL. static Instruction *propagateMetadata(Instruction *I, ArrayRef VL) { Instruction *I0 = cast(VL[0]); @@ -2031,6 +2048,7 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) { BinaryOperator *BinOp = cast(VL0); Value *V = Builder.CreateBinOp(BinOp->getOpcode(), LHS, RHS); E->VectorizedValue = V; + propagateIRFlags(E->VectorizedValue, E->Scalars); ++NumVectorInstructions; if (Instruction *I = dyn_cast(V)) @@ -2194,18 +2212,25 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) { BinaryOperator *BinOp1 = cast(VL1); Value *V1 = Builder.CreateBinOp(BinOp1->getOpcode(), LHS, RHS); - // Create appropriate shuffle to take alternative operations from - // the vector. - std::vector 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 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; -- cgit v1.2.3