summaryrefslogtreecommitdiffstats
path: root/llvm/lib
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib')
-rw-r--r--llvm/lib/Analysis/IVDescriptors.cpp10
-rw-r--r--llvm/lib/CodeGen/ExpandReductions.cpp4
-rw-r--r--llvm/lib/Transforms/Utils/LoopUtils.cpp46
-rw-r--r--llvm/lib/Transforms/Vectorize/LoopVectorize.cpp16
-rw-r--r--llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp3
5 files changed, 49 insertions, 30 deletions
diff --git a/llvm/lib/Analysis/IVDescriptors.cpp b/llvm/lib/Analysis/IVDescriptors.cpp
index 555e3c9ed45..19f1a771b85 100644
--- a/llvm/lib/Analysis/IVDescriptors.cpp
+++ b/llvm/lib/Analysis/IVDescriptors.cpp
@@ -251,6 +251,10 @@ bool RecurrenceDescriptor::AddReductionVar(PHINode *Phi, RecurrenceKind Kind,
Worklist.push_back(Start);
VisitedInsts.insert(Start);
+ // Start with all flags set because we will intersect this with the reduction
+ // flags from all the reduction operations.
+ FastMathFlags FMF = FastMathFlags::getFast();
+
// A value in the reduction can be used:
// - By the reduction:
// - Reduction operation:
@@ -296,6 +300,8 @@ bool RecurrenceDescriptor::AddReductionVar(PHINode *Phi, RecurrenceKind Kind,
ReduxDesc = isRecurrenceInstr(Cur, Kind, ReduxDesc, HasFunNoNaNAttr);
if (!ReduxDesc.isRecurrence())
return false;
+ if (isa<FPMathOperator>(ReduxDesc.getPatternInst()))
+ FMF &= ReduxDesc.getPatternInst()->getFastMathFlags();
}
bool IsASelect = isa<SelectInst>(Cur);
@@ -441,7 +447,7 @@ bool RecurrenceDescriptor::AddReductionVar(PHINode *Phi, RecurrenceKind Kind,
// Save the description of this reduction variable.
RecurrenceDescriptor RD(
- RdxStart, ExitInstruction, Kind, ReduxDesc.getMinMaxKind(),
+ RdxStart, ExitInstruction, Kind, FMF, ReduxDesc.getMinMaxKind(),
ReduxDesc.getUnsafeAlgebraInst(), RecurrenceType, IsSigned, CastInsts);
RedDes = RD;
@@ -550,7 +556,7 @@ RecurrenceDescriptor::InstDesc
RecurrenceDescriptor::isRecurrenceInstr(Instruction *I, RecurrenceKind Kind,
InstDesc &Prev, bool HasFunNoNaNAttr) {
Instruction *UAI = Prev.getUnsafeAlgebraInst();
- if (!UAI && isa<FPMathOperator>(I) && !I->isFast())
+ if (!UAI && isa<FPMathOperator>(I) && !I->hasAllowReassoc())
UAI = I; // Found an unsafe (unvectorizable) algebra instruction.
switch (I->getOpcode()) {
diff --git a/llvm/lib/CodeGen/ExpandReductions.cpp b/llvm/lib/CodeGen/ExpandReductions.cpp
index f44d89156b6..34858883298 100644
--- a/llvm/lib/CodeGen/ExpandReductions.cpp
+++ b/llvm/lib/CodeGen/ExpandReductions.cpp
@@ -118,9 +118,11 @@ bool expandReductions(Function &F, const TargetTransformInfo *TTI) {
}
if (!TTI->shouldExpandReduction(II))
continue;
+ FastMathFlags FMF =
+ isa<FPMathOperator>(II) ? II->getFastMathFlags() : FastMathFlags{};
Value *Rdx =
IsOrdered ? getOrderedReduction(Builder, Acc, Vec, getOpcode(ID), MRK)
- : getShuffleReduction(Builder, Vec, getOpcode(ID), MRK);
+ : getShuffleReduction(Builder, Vec, getOpcode(ID), MRK, FMF);
II->replaceAllUsesWith(Rdx);
II->eraseFromParent();
Changed = true;
diff --git a/llvm/lib/Transforms/Utils/LoopUtils.cpp b/llvm/lib/Transforms/Utils/LoopUtils.cpp
index c3a02685244..045cb6284c4 100644
--- a/llvm/lib/Transforms/Utils/LoopUtils.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUtils.cpp
@@ -671,13 +671,9 @@ bool llvm::hasIterationCountInvariantInParent(Loop *InnerLoop,
return true;
}
-/// Adds a 'fast' flag to floating point operations.
-static Value *addFastMathFlag(Value *V) {
- if (isa<FPMathOperator>(V)) {
- FastMathFlags Flags;
- Flags.setFast();
- cast<Instruction>(V)->setFastMathFlags(Flags);
- }
+static Value *addFastMathFlag(Value *V, FastMathFlags FMF) {
+ if (isa<FPMathOperator>(V))
+ cast<Instruction>(V)->setFastMathFlags(FMF);
return V;
}
@@ -761,7 +757,7 @@ llvm::getOrderedReduction(IRBuilder<> &Builder, Value *Acc, Value *Src,
Value *
llvm::getShuffleReduction(IRBuilder<> &Builder, Value *Src, unsigned Op,
RecurrenceDescriptor::MinMaxRecurrenceKind MinMaxKind,
- ArrayRef<Value *> RedOps) {
+ FastMathFlags FMF, ArrayRef<Value *> RedOps) {
unsigned VF = Src->getType()->getVectorNumElements();
// VF is a power of 2 so we can emit the reduction using log2(VF) shuffles
// and vector ops, reducing the set of values being computed by half each
@@ -786,7 +782,8 @@ llvm::getShuffleReduction(IRBuilder<> &Builder, Value *Src, unsigned Op,
if (Op != Instruction::ICmp && Op != Instruction::FCmp) {
// Floating point operations had to be 'fast' to enable the reduction.
TmpVec = addFastMathFlag(Builder.CreateBinOp((Instruction::BinaryOps)Op,
- TmpVec, Shuf, "bin.rdx"));
+ TmpVec, Shuf, "bin.rdx"),
+ FMF);
} else {
assert(MinMaxKind != RecurrenceDescriptor::MRK_Invalid &&
"Invalid min/max");
@@ -803,7 +800,7 @@ llvm::getShuffleReduction(IRBuilder<> &Builder, Value *Src, unsigned Op,
/// flags (if generating min/max reductions).
Value *llvm::createSimpleTargetReduction(
IRBuilder<> &Builder, const TargetTransformInfo *TTI, unsigned Opcode,
- Value *Src, TargetTransformInfo::ReductionFlags Flags,
+ Value *Src, TargetTransformInfo::ReductionFlags Flags, FastMathFlags FMF,
ArrayRef<Value *> RedOps) {
assert(isa<VectorType>(Src->getType()) && "Type must be a vector");
@@ -873,7 +870,7 @@ Value *llvm::createSimpleTargetReduction(
}
if (TTI->useReductionIntrinsic(Opcode, Src->getType(), Flags))
return BuildFunc();
- return getShuffleReduction(Builder, Src, Opcode, MinMaxKind, RedOps);
+ return getShuffleReduction(Builder, Src, Opcode, MinMaxKind, FMF, RedOps);
}
/// Create a vector reduction using a given recurrence descriptor.
@@ -888,28 +885,37 @@ Value *llvm::createTargetReduction(IRBuilder<> &B,
Flags.NoNaN = NoNaN;
switch (RecKind) {
case RD::RK_FloatAdd:
- return createSimpleTargetReduction(B, TTI, Instruction::FAdd, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::FAdd, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_FloatMult:
- return createSimpleTargetReduction(B, TTI, Instruction::FMul, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::FMul, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerAdd:
- return createSimpleTargetReduction(B, TTI, Instruction::Add, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::Add, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerMult:
- return createSimpleTargetReduction(B, TTI, Instruction::Mul, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::Mul, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerAnd:
- return createSimpleTargetReduction(B, TTI, Instruction::And, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::And, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerOr:
- return createSimpleTargetReduction(B, TTI, Instruction::Or, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::Or, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerXor:
- return createSimpleTargetReduction(B, TTI, Instruction::Xor, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::Xor, Src, Flags,
+ Desc.getFastMathFlags());
case RD::RK_IntegerMinMax: {
RD::MinMaxRecurrenceKind MMKind = Desc.getMinMaxRecurrenceKind();
Flags.IsMaxOp = (MMKind == RD::MRK_SIntMax || MMKind == RD::MRK_UIntMax);
Flags.IsSigned = (MMKind == RD::MRK_SIntMax || MMKind == RD::MRK_SIntMin);
- return createSimpleTargetReduction(B, TTI, Instruction::ICmp, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::ICmp, Src, Flags,
+ Desc.getFastMathFlags());
}
case RD::RK_FloatMinMax: {
Flags.IsMaxOp = Desc.getMinMaxRecurrenceKind() == RD::MRK_FloatMax;
- return createSimpleTargetReduction(B, TTI, Instruction::FCmp, Src, Flags);
+ return createSimpleTargetReduction(B, TTI, Instruction::FCmp, Src, Flags,
+ Desc.getFastMathFlags());
}
default:
llvm_unreachable("Unhandled RecKind");
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index b10ce86b682..b57012291df 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -319,11 +319,14 @@ static unsigned getReciprocalPredBlockProb() { return 2; }
/// A helper function that adds a 'fast' flag to floating-point operations.
static Value *addFastMathFlag(Value *V) {
- if (isa<FPMathOperator>(V)) {
- FastMathFlags Flags;
- Flags.setFast();
- cast<Instruction>(V)->setFastMathFlags(Flags);
- }
+ if (isa<FPMathOperator>(V))
+ cast<Instruction>(V)->setFastMathFlags(FastMathFlags::getFast());
+ return V;
+}
+
+static Value *addFastMathFlag(Value *V, FastMathFlags FMF) {
+ if (isa<FPMathOperator>(V))
+ cast<Instruction>(V)->setFastMathFlags(FMF);
return V;
}
@@ -3612,7 +3615,8 @@ void InnerLoopVectorizer::fixReduction(PHINode *Phi) {
// Floating point operations had to be 'fast' to enable the reduction.
ReducedPartRdx = addFastMathFlag(
Builder.CreateBinOp((Instruction::BinaryOps)Op, RdxPart,
- ReducedPartRdx, "bin.rdx"));
+ ReducedPartRdx, "bin.rdx"),
+ RdxDesc.getFastMathFlags());
else
ReducedPartRdx = createMinMaxOp(Builder, MinMaxKind, ReducedPartRdx,
RdxPart);
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 0016e10567e..28ed4e6ff1a 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5929,7 +5929,8 @@ private:
if (!IsPairwiseReduction)
return createSimpleTargetReduction(
Builder, TTI, ReductionData.getOpcode(), VectorizedValue,
- ReductionData.getFlags(), ReductionOps.back());
+ ReductionData.getFlags(), FastMathFlags::getFast(),
+ ReductionOps.back());
Value *TmpVec = VectorizedValue;
for (unsigned i = ReduxWidth / 2; i != 0; i >>= 1) {
OpenPOWER on IntegriCloud