#include "llvm/IR/ValueHandle.h"
#include "llvm/Pass.h"
#include "llvm/Support/raw_ostream.h"
-#include "llvm/Transforms/Utils/LoopUtils.h"
namespace llvm {
const SmallVectorImpl<Instruction *> &Instrs) const;
};
- MemoryDepChecker(PredicatedScalarEvolution &PSE, const Loop *L)
- : PSE(PSE), InnermostLoop(L), AccessIdx(0),
+ MemoryDepChecker(ScalarEvolution *Se, const Loop *L,
+ SCEVUnionPredicate &Preds)
+ : SE(Se), InnermostLoop(L), AccessIdx(0),
ShouldRetryWithRuntimeCheck(false), SafeForVectorization(true),
- RecordDependences(true) {}
+ RecordDependences(true), Preds(Preds) {}
/// \brief Register the location (instructions are given increasing numbers)
/// of a write access.
bool isWrite) const;
private:
- /// A wrapper around ScalarEvolution, used to add runtime SCEV checks, and
- /// applies dynamic knowledge to simplify SCEV expressions and convert them
- /// to a more usable form. We need this in case assumptions about SCEV
- /// expressions need to be made in order to avoid unknown dependences. For
- /// example we might assume a unit stride for a pointer in order to prove
- /// that a memory access is strided and doesn't wrap.
- PredicatedScalarEvolution &PSE;
+ ScalarEvolution *SE;
const Loop *InnermostLoop;
/// \brief Maps access locations (ptr, read/write) to program order.
/// \brief Check whether the data dependence could prevent store-load
/// forwarding.
bool couldPreventStoreLoadForward(unsigned Distance, unsigned TypeByteSize);
+
+ /// The SCEV predicate containing all the SCEV-related assumptions.
+ /// The dependence checker needs this in order to convert SCEVs of pointers
+ /// to more accurate expressions in the context of existing assumptions.
+ /// We also need this in case assumptions about SCEV expressions need to
+ /// be made in order to avoid unknown dependences. For example we might
+ /// assume a unit stride for a pointer in order to prove that a memory access
+ /// is strided and doesn't wrap.
+ SCEVUnionPredicate &Preds;
};
/// \brief Holds information about the memory runtime legality checks to verify
/// and change \p Preds.
void insert(Loop *Lp, Value *Ptr, bool WritePtr, unsigned DepSetId,
unsigned ASId, const ValueToValueMap &Strides,
- PredicatedScalarEvolution &PSE);
+ SCEVUnionPredicate &Preds);
/// \brief No run-time memory checking is necessary.
bool empty() const { return Pointers.empty(); }
/// ScalarEvolution, we will generate run-time checks by emitting a
/// SCEVUnionPredicate.
///
-/// Checks for both memory dependences and the SCEV predicates contained in the
-/// PSE must be emitted in order for the results of this analysis to be valid.
+/// Checks for both memory dependences and SCEV predicates must be emitted in
+/// order for the results of this analysis to be valid.
class LoopAccessInfo {
public:
LoopAccessInfo(Loop *L, ScalarEvolution *SE, const DataLayout &DL,
return StoreToLoopInvariantAddress;
}
- /// Used to add runtime SCEV checks. Simplifies SCEV expressions and converts
- /// them to a more usable form. All SCEV expressions during the analysis
- /// should be re-written (and therefore simplified) according to PSE.
+ /// The SCEV predicate contains all the SCEV-related assumptions.
+ /// The is used to keep track of the minimal set of assumptions on SCEV
+ /// expressions that the analysis needs to make in order to return a
+ /// meaningful result. All SCEV expressions during the analysis should be
+ /// re-written (and therefore simplified) according to Preds.
/// A user of LoopAccessAnalysis will need to emit the runtime checks
/// associated with this predicate.
- PredicatedScalarEvolution PSE;
+ SCEVUnionPredicate Preds;
private:
/// \brief Analyze the loop. Substitute symbolic strides using Strides.
MemoryDepChecker DepChecker;
Loop *TheLoop;
+ ScalarEvolution *SE;
const DataLayout &DL;
const TargetLibraryInfo *TLI;
AliasAnalysis *AA;
/// If \p OrigPtr is not null, use it to look up the stride value instead of \p
/// Ptr. \p PtrToStride provides the mapping between the pointer value and its
/// stride as collected by LoopVectorizationLegality::collectStridedAccess.
-const SCEV *replaceSymbolicStrideSCEV(PredicatedScalarEvolution &PSE,
+const SCEV *replaceSymbolicStrideSCEV(ScalarEvolution *SE,
const ValueToValueMap &PtrToStride,
- Value *Ptr, Value *OrigPtr = nullptr);
+ SCEVUnionPredicate &Preds, Value *Ptr,
+ Value *OrigPtr = nullptr);
/// \brief Check the stride of the pointer and ensure that it does not wrap in
/// the address space, assuming \p Preds is true.
///
/// If necessary this method will version the stride of the pointer according
/// to \p PtrToStride and therefore add a new predicate to \p Preds.
-int isStridedPtr(PredicatedScalarEvolution &PSE, Value *Ptr, const Loop *Lp,
- const ValueToValueMap &StridesMap);
+int isStridedPtr(ScalarEvolution *SE, Value *Ptr, const Loop *Lp,
+ const ValueToValueMap &StridesMap, SCEVUnionPredicate &Preds);
/// \brief This analysis provides dependence information for the memory accesses
/// of a loop.
/// \brief Returns the instructions that use values defined in the loop.
SmallVector<Instruction *, 8> findDefsUsedOutsideOfLoop(Loop *L);
-
-/// An interface layer with SCEV used to manage how we see SCEV expressions for
-/// values in the context of existing predicates. We can add new predicates,
-/// but we cannot remove them.
-///
-/// This layer has multiple purposes:
-/// - provides a simple interface for SCEV versioning.
-/// - guarantees that the order of transformations applied on a SCEV
-/// expression for a single Value is consistent across two different
-/// getSCEV calls. This means that, for example, once we've obtained
-/// an AddRec expression for a certain value through expression rewriting,
-/// we will continue to get an AddRec expression for that Value.
-/// - lowers the number of expression rewrites.
-class PredicatedScalarEvolution {
-public:
- PredicatedScalarEvolution(ScalarEvolution &SE);
- const SCEVUnionPredicate &getUnionPredicate() const;
- /// \brief Returns the SCEV expression of V, in the context of the current
- /// SCEV predicate.
- /// The order of transformations applied on the expression of V returned
- /// by ScalarEvolution is guaranteed to be preserved, even when adding new
- /// predicates.
- const SCEV *getSCEV(Value *V);
- /// \brief Adds a new predicate.
- void addPredicate(const SCEVPredicate &Pred);
- /// \brief Returns the ScalarEvolution analysis used.
- ScalarEvolution *getSE() const { return &SE; }
-
-private:
- /// \brief Increments the version number of the predicate.
- /// This needs to be called every time the SCEV predicate changes.
- void updateGeneration();
- /// Holds a SCEV and the version number of the SCEV predicate used to
- /// perform the rewrite of the expression.
- typedef std::pair<unsigned, const SCEV *> RewriteEntry;
- /// Maps a SCEV to the rewrite result of that SCEV at a certain version
- /// number. If this number doesn't match the current Generation, we will
- /// need to do a rewrite. To preserve the transformation order of previous
- /// rewrites, we will rewrite the previous result instead of the original
- /// SCEV.
- DenseMap<const SCEV *, RewriteEntry> RewriteMap;
- /// The ScalarEvolution analysis.
- ScalarEvolution &SE;
- /// The SCEVPredicate that forms our context. We will rewrite all expressions
- /// assuming that this predicate true.
- SCEVUnionPredicate Preds;
- /// Marks the version of the SCEV predicate used. When rewriting a SCEV
- /// expression we mark it with the version of the predicate. We use this to
- /// figure out if the predicate has changed from the last rewrite of the
- /// SCEV. If so, we need to perform a new rewrite.
- unsigned Generation;
-};
}
#endif
return V;
}
-const SCEV *llvm::replaceSymbolicStrideSCEV(PredicatedScalarEvolution &PSE,
+const SCEV *llvm::replaceSymbolicStrideSCEV(ScalarEvolution *SE,
const ValueToValueMap &PtrToStride,
+ SCEVUnionPredicate &Preds,
Value *Ptr, Value *OrigPtr) {
- const SCEV *OrigSCEV = PSE.getSCEV(Ptr);
+ const SCEV *OrigSCEV = SE->getSCEV(Ptr);
// If there is an entry in the map return the SCEV of the pointer with the
// symbolic stride replaced by one.
ValueToValueMap RewriteMap;
RewriteMap[StrideVal] = One;
- ScalarEvolution *SE = PSE.getSE();
const auto *U = cast<SCEVUnknown>(SE->getSCEV(StrideVal));
const auto *CT =
static_cast<const SCEVConstant *>(SE->getOne(StrideVal->getType()));
- PSE.addPredicate(*SE->getEqualPredicate(U, CT));
- auto *Expr = PSE.getSCEV(Ptr);
+ Preds.add(SE->getEqualPredicate(U, CT));
- DEBUG(dbgs() << "LAA: Replacing SCEV: " << *OrigSCEV << " by: " << *Expr
+ const SCEV *ByOne = SE->rewriteUsingPredicate(OrigSCEV, Preds);
+ DEBUG(dbgs() << "LAA: Replacing SCEV: " << *OrigSCEV << " by: " << *ByOne
<< "\n");
- return Expr;
+ return ByOne;
}
// Otherwise, just return the SCEV of the original pointer.
void RuntimePointerChecking::insert(Loop *Lp, Value *Ptr, bool WritePtr,
unsigned DepSetId, unsigned ASId,
const ValueToValueMap &Strides,
- PredicatedScalarEvolution &PSE) {
+ SCEVUnionPredicate &Preds) {
// Get the stride replaced scev.
- const SCEV *Sc = replaceSymbolicStrideSCEV(PSE, Strides, Ptr);
+ const SCEV *Sc = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Sc);
assert(AR && "Invalid addrec expression");
- ScalarEvolution *SE = PSE.getSE();
const SCEV *Ex = SE->getBackedgeTakenCount(Lp);
const SCEV *ScStart = AR->getStart();
typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;
AccessAnalysis(const DataLayout &Dl, AliasAnalysis *AA, LoopInfo *LI,
- MemoryDepChecker::DepCandidates &DA,
- PredicatedScalarEvolution &PSE)
+ MemoryDepChecker::DepCandidates &DA, SCEVUnionPredicate &Preds)
: DL(Dl), AST(*AA), LI(LI), DepCands(DA), IsRTCheckAnalysisNeeded(false),
- PSE(PSE) {}
+ Preds(Preds) {}
/// \brief Register a load and whether it is only read from.
void addLoad(MemoryLocation &Loc, bool IsReadOnly) {
bool IsRTCheckAnalysisNeeded;
/// The SCEV predicate containing all the SCEV-related assumptions.
- PredicatedScalarEvolution &PSE;
+ SCEVUnionPredicate &Preds;
};
} // end anonymous namespace
/// \brief Check whether a pointer can participate in a runtime bounds check.
-static bool hasComputableBounds(PredicatedScalarEvolution &PSE,
+static bool hasComputableBounds(ScalarEvolution *SE,
const ValueToValueMap &Strides, Value *Ptr,
- Loop *L) {
- const SCEV *PtrScev = replaceSymbolicStrideSCEV(PSE, Strides, Ptr);
+ Loop *L, SCEVUnionPredicate &Preds) {
+ const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
if (!AR)
return false;
else
++NumReadPtrChecks;
- if (hasComputableBounds(PSE, StridesMap, Ptr, TheLoop) &&
+ if (hasComputableBounds(SE, StridesMap, Ptr, TheLoop, Preds) &&
// When we run after a failing dependency check we have to make sure
// we don't have wrapping pointers.
(!ShouldCheckStride ||
- isStridedPtr(PSE, Ptr, TheLoop, StridesMap) == 1)) {
+ isStridedPtr(SE, Ptr, TheLoop, StridesMap, Preds) == 1)) {
// The id of the dependence set.
unsigned DepId;
// Each access has its own dependence set.
DepId = RunningDepId++;
- RtCheck.insert(TheLoop, Ptr, IsWrite, DepId, ASId, StridesMap, PSE);
+ RtCheck.insert(TheLoop, Ptr, IsWrite, DepId, ASId, StridesMap, Preds);
DEBUG(dbgs() << "LAA: Found a runtime check ptr:" << *Ptr << '\n');
} else {
}
/// \brief Check whether the access through \p Ptr has a constant stride.
-int llvm::isStridedPtr(PredicatedScalarEvolution &PSE, Value *Ptr,
- const Loop *Lp, const ValueToValueMap &StridesMap) {
+int llvm::isStridedPtr(ScalarEvolution *SE, Value *Ptr, const Loop *Lp,
+ const ValueToValueMap &StridesMap,
+ SCEVUnionPredicate &Preds) {
Type *Ty = Ptr->getType();
assert(Ty->isPointerTy() && "Unexpected non-ptr");
return 0;
}
- const SCEV *PtrScev = replaceSymbolicStrideSCEV(PSE, StridesMap, Ptr);
+ const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, StridesMap, Preds, Ptr);
const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
if (!AR) {
// to access the pointer value "0" which is undefined behavior in address
// space 0, therefore we can also vectorize this case.
bool IsInBoundsGEP = isInBoundsGep(Ptr);
- bool IsNoWrapAddRec = isNoWrapAddRec(Ptr, AR, PSE.getSE(), Lp);
+ bool IsNoWrapAddRec = isNoWrapAddRec(Ptr, AR, SE, Lp);
bool IsInAddressSpaceZero = PtrTy->getAddressSpace() == 0;
if (!IsNoWrapAddRec && !IsInBoundsGEP && !IsInAddressSpaceZero) {
DEBUG(dbgs() << "LAA: Bad stride - Pointer may wrap in the address space "
- << *Ptr << " SCEV: " << *PtrScev << "\n");
+ << *Ptr << " SCEV: " << *PtrScev << "\n");
return 0;
}
// Check the step is constant.
- const SCEV *Step = AR->getStepRecurrence(*PSE.getSE());
+ const SCEV *Step = AR->getStepRecurrence(*SE);
// Calculate the pointer stride and check if it is constant.
const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
BPtr->getType()->getPointerAddressSpace())
return Dependence::Unknown;
- const SCEV *AScev = replaceSymbolicStrideSCEV(PSE, Strides, APtr);
- const SCEV *BScev = replaceSymbolicStrideSCEV(PSE, Strides, BPtr);
+ const SCEV *AScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, APtr);
+ const SCEV *BScev = replaceSymbolicStrideSCEV(SE, Strides, Preds, BPtr);
- int StrideAPtr = isStridedPtr(PSE, APtr, InnermostLoop, Strides);
- int StrideBPtr = isStridedPtr(PSE, BPtr, InnermostLoop, Strides);
+ int StrideAPtr = isStridedPtr(SE, APtr, InnermostLoop, Strides, Preds);
+ int StrideBPtr = isStridedPtr(SE, BPtr, InnermostLoop, Strides, Preds);
const SCEV *Src = AScev;
const SCEV *Sink = BScev;
std::swap(StrideAPtr, StrideBPtr);
}
- const SCEV *Dist = PSE.getSE()->getMinusSCEV(Sink, Src);
+ const SCEV *Dist = SE->getMinusSCEV(Sink, Src);
DEBUG(dbgs() << "LAA: Src Scev: " << *Src << "Sink Scev: " << *Sink
- << "(Induction step: " << StrideAPtr << ")\n");
+ << "(Induction step: " << StrideAPtr << ")\n");
DEBUG(dbgs() << "LAA: Distance for " << *InstMap[AIdx] << " to "
<< *InstMap[BIdx] << ": " << *Dist << "\n");
}
// ScalarEvolution needs to be able to find the exit count.
- const SCEV *ExitCount = PSE.getSE()->getBackedgeTakenCount(TheLoop);
- if (ExitCount == PSE.getSE()->getCouldNotCompute()) {
- emitAnalysis(LoopAccessReport()
- << "could not determine number of loop iterations");
+ const SCEV *ExitCount = SE->getBackedgeTakenCount(TheLoop);
+ if (ExitCount == SE->getCouldNotCompute()) {
+ emitAnalysis(LoopAccessReport() <<
+ "could not determine number of loop iterations");
DEBUG(dbgs() << "LAA: SCEV could not compute the loop exit count.\n");
return false;
}
MemoryDepChecker::DepCandidates DependentAccesses;
AccessAnalysis Accesses(TheLoop->getHeader()->getModule()->getDataLayout(),
- AA, LI, DependentAccesses, PSE);
+ AA, LI, DependentAccesses, Preds);
// Holds the analyzed pointers. We don't want to call GetUnderlyingObjects
// multiple times on the same object. If the ptr is accessed twice, once
// read a few words, modify, and write a few words, and some of the
// words may be written to the same address.
bool IsReadOnlyPtr = false;
- if (Seen.insert(Ptr).second || !isStridedPtr(PSE, Ptr, TheLoop, Strides)) {
+ if (Seen.insert(Ptr).second ||
+ !isStridedPtr(SE, Ptr, TheLoop, Strides, Preds)) {
++NumReads;
IsReadOnlyPtr = true;
}
// Find pointers with computable bounds. We are going to use this information
// to place a runtime bound check.
bool CanDoRTIfNeeded =
- Accesses.canCheckPtrAtRT(PtrRtChecking, PSE.getSE(), TheLoop, Strides);
+ Accesses.canCheckPtrAtRT(PtrRtChecking, SE, TheLoop, Strides);
if (!CanDoRTIfNeeded) {
emitAnalysis(LoopAccessReport() << "cannot identify array bounds");
DEBUG(dbgs() << "LAA: We can't vectorize because we can't find "
PtrRtChecking.reset();
PtrRtChecking.Need = true;
- auto *SE = PSE.getSE();
CanDoRTIfNeeded =
Accesses.canCheckPtrAtRT(PtrRtChecking, SE, TheLoop, Strides, true);
}
bool LoopAccessInfo::isUniform(Value *V) const {
- return (PSE.getSE()->isLoopInvariant(PSE.getSE()->getSCEV(V), TheLoop));
+ return (SE->isLoopInvariant(SE->getSCEV(V), TheLoop));
}
// FIXME: this function is currently a duplicate of the one in
Instruction *Loc,
const SmallVectorImpl<RuntimePointerChecking::PointerCheck> &PointerChecks)
const {
- auto *SE = PSE.getSE();
+
SCEVExpander Exp(*SE, DL, "induction");
auto ExpandedChecks =
expandBounds(PointerChecks, TheLoop, Loc, SE, Exp, PtrRtChecking);
const TargetLibraryInfo *TLI, AliasAnalysis *AA,
DominatorTree *DT, LoopInfo *LI,
const ValueToValueMap &Strides)
- : PSE(*SE), PtrRtChecking(SE), DepChecker(PSE, L), TheLoop(L), DL(DL),
+ : PtrRtChecking(SE), DepChecker(SE, L, Preds), TheLoop(L), SE(SE), DL(DL),
TLI(TLI), AA(AA), DT(DT), LI(LI), NumLoads(0), NumStores(0),
MaxSafeDepDistBytes(-1U), CanVecMem(false),
StoreToLoopInvariantAddress(false) {
<< "found in loop.\n";
OS.indent(Depth) << "SCEV assumptions:\n";
- PSE.getUnionPredicate().print(OS, Depth);
+ Preds.print(OS, Depth);
}
const LoopAccessInfo &
}
// Don't distribute the loop if we need too many SCEV run-time checks.
- const SCEVUnionPredicate &Pred = LAI.PSE.getUnionPredicate();
+ const SCEVUnionPredicate &Pred = LAI.Preds;
if (Pred.getComplexity() > DistributeSCEVCheckThreshold) {
DEBUG(dbgs() << "Too many SCEV run-time checks needed.\n");
return false;
DEBUG(LAI.getRuntimePointerChecking()->printChecks(dbgs(), Checks));
LoopVersioning LVer(LAI, L, LI, DT, SE, false);
LVer.setAliasChecks(std::move(Checks));
- LVer.setSCEVChecks(LAI.PSE.getUnionPredicate());
+ LVer.setSCEVChecks(LAI.Preds);
LVer.versionLoop(DefsUsedOutside);
}
return false;
}
- if (LAI.PSE.getUnionPredicate().getComplexity() >
- LoadElimSCEVCheckThreshold) {
+ if (LAI.Preds.getComplexity() > LoadElimSCEVCheckThreshold) {
DEBUG(dbgs() << "Too many SCEV run-time checks needed.\n");
return false;
}
// Point of no-return, start the transformation. First, version the loop if
// necessary.
- if (!Checks.empty() || !LAI.PSE.getUnionPredicate().isAlwaysTrue()) {
+ if (!Checks.empty() || !LAI.Preds.isAlwaysTrue()) {
LoopVersioning LV(LAI, L, LI, DT, SE, false);
LV.setAliasChecks(std::move(Checks));
- LV.setSCEVChecks(LAI.PSE.getUnionPredicate());
+ LV.setSCEVChecks(LAI.Preds);
LV.versionLoop();
}
return UsedOutside;
}
-
-PredicatedScalarEvolution::PredicatedScalarEvolution(ScalarEvolution &SE)
- : SE(SE), Generation(0) {}
-
-const SCEV *PredicatedScalarEvolution::getSCEV(Value *V) {
- const SCEV *Expr = SE.getSCEV(V);
- RewriteEntry &Entry = RewriteMap[Expr];
-
- // If we already have an entry and the version matches, return it.
- if (Entry.second && Generation == Entry.first)
- return Entry.second;
-
- // We found an entry but it's stale. Rewrite the stale entry
- // acording to the current predicate.
- if (Entry.second)
- Expr = Entry.second;
-
- const SCEV *NewSCEV = SE.rewriteUsingPredicate(Expr, Preds);
- Entry = {Generation, NewSCEV};
-
- return NewSCEV;
-}
-
-void PredicatedScalarEvolution::addPredicate(const SCEVPredicate &Pred) {
- if (Preds.implies(&Pred))
- return;
- Preds.add(&Pred);
- updateGeneration();
-}
-
-const SCEVUnionPredicate &PredicatedScalarEvolution::getUnionPredicate() const {
- return Preds;
-}
-
-void PredicatedScalarEvolution::updateGeneration() {
- // If the generation number wrapped recompute everything.
- if (++Generation == 0) {
- for (auto &II : RewriteMap) {
- const SCEV *Rewritten = II.second.second;
- II.second = {Generation, SE.rewriteUsingPredicate(Rewritten, Preds)};
- }
- }
-}
assert(L->getLoopPreheader() && "No preheader");
if (UseLAIChecks) {
setAliasChecks(LAI.getRuntimePointerChecking()->getChecks());
- setSCEVChecks(LAI.PSE.getUnionPredicate());
+ setSCEVChecks(LAI.Preds);
}
}
LAI.addRuntimeChecks(RuntimeCheckBB->getTerminator(), AliasChecks);
assert(MemRuntimeCheck && "called even though needsAnyChecking = false");
- const SCEVUnionPredicate &Pred = LAI.PSE.getUnionPredicate();
+ const SCEVUnionPredicate &Pred = LAI.Preds;
SCEVExpander Exp(*SE, RuntimeCheckBB->getModule()->getDataLayout(),
"scev.check");
SCEVRuntimeCheck =
/// and reduction variables that were found to a given vectorization factor.
class InnerLoopVectorizer {
public:
- InnerLoopVectorizer(Loop *OrigLoop, PredicatedScalarEvolution &PSE,
- LoopInfo *LI, DominatorTree *DT,
- const TargetLibraryInfo *TLI,
+ InnerLoopVectorizer(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
+ DominatorTree *DT, const TargetLibraryInfo *TLI,
const TargetTransformInfo *TTI, unsigned VecWidth,
- unsigned UnrollFactor)
- : OrigLoop(OrigLoop), PSE(PSE), LI(LI), DT(DT), TLI(TLI), TTI(TTI),
- VF(VecWidth), UF(UnrollFactor), Builder(PSE.getSE()->getContext()),
+ unsigned UnrollFactor, SCEVUnionPredicate &Preds)
+ : OrigLoop(OrigLoop), SE(SE), LI(LI), DT(DT), TLI(TLI), TTI(TTI),
+ VF(VecWidth), UF(UnrollFactor), Builder(SE->getContext()),
Induction(nullptr), OldInduction(nullptr), WidenMap(UnrollFactor),
TripCount(nullptr), VectorTripCount(nullptr), Legal(nullptr),
- AddedSafetyChecks(false) {}
+ AddedSafetyChecks(false), Preds(Preds) {}
// Perform the actual loop widening (vectorization).
// MinimumBitWidths maps scalar integer values to the smallest bitwidth they
/// The original loop.
Loop *OrigLoop;
- /// A wrapper around ScalarEvolution used to add runtime SCEV checks. Applies
- /// dynamic knowledge to simplify SCEV expressions and converts them to a
- /// more usable form.
- PredicatedScalarEvolution &PSE;
+ /// Scev analysis to use.
+ ScalarEvolution *SE;
/// Loop Info.
LoopInfo *LI;
/// Dominator Tree.
// Record whether runtime check is added.
bool AddedSafetyChecks;
+
+ /// The SCEV predicate containing all the SCEV-related assumptions.
+ /// The predicate is used to simplify existing expressions in the
+ /// context of existing SCEV assumptions. Since legality checking is
+ /// not done here, we don't need to use this predicate to record
+ /// further assumptions.
+ SCEVUnionPredicate &Preds;
};
class InnerLoopUnroller : public InnerLoopVectorizer {
public:
- InnerLoopUnroller(Loop *OrigLoop, PredicatedScalarEvolution &PSE,
- LoopInfo *LI, DominatorTree *DT,
- const TargetLibraryInfo *TLI,
- const TargetTransformInfo *TTI, unsigned UnrollFactor)
- : InnerLoopVectorizer(OrigLoop, PSE, LI, DT, TLI, TTI, 1, UnrollFactor) {}
+ InnerLoopUnroller(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
+ DominatorTree *DT, const TargetLibraryInfo *TLI,
+ const TargetTransformInfo *TTI, unsigned UnrollFactor,
+ SCEVUnionPredicate &Preds)
+ : InnerLoopVectorizer(OrigLoop, SE, LI, DT, TLI, TTI, 1, UnrollFactor,
+ Preds) {}
private:
void scalarizeInstruction(Instruction *Instr,
/// between the member and the group in a map.
class InterleavedAccessInfo {
public:
- InterleavedAccessInfo(PredicatedScalarEvolution &PSE, Loop *L,
- DominatorTree *DT)
- : PSE(PSE), TheLoop(L), DT(DT) {}
+ InterleavedAccessInfo(ScalarEvolution *SE, Loop *L, DominatorTree *DT,
+ SCEVUnionPredicate &Preds)
+ : SE(SE), TheLoop(L), DT(DT), Preds(Preds) {}
~InterleavedAccessInfo() {
SmallSet<InterleaveGroup *, 4> DelSet;
}
private:
- /// A wrapper around ScalarEvolution, used to add runtime SCEV checks.
- /// Simplifies SCEV expressions in the context of existing SCEV assumptions.
- /// The interleaved access analysis can also add new predicates (for example
- /// by versioning strides of pointers).
- PredicatedScalarEvolution &PSE;
+ ScalarEvolution *SE;
Loop *TheLoop;
DominatorTree *DT;
+ /// The SCEV predicate containing all the SCEV-related assumptions.
+ /// The predicate is used to simplify SCEV expressions in the
+ /// context of existing SCEV assumptions. The interleaved access
+ /// analysis can also add new predicates (for example by versioning
+ /// strides of pointers).
+ SCEVUnionPredicate &Preds;
+
/// Holds the relationships between the members and the interleave group.
DenseMap<Instruction *, InterleaveGroup *> InterleaveGroupMap;
/// induction variable and the different reduction variables.
class LoopVectorizationLegality {
public:
- LoopVectorizationLegality(Loop *L, PredicatedScalarEvolution &PSE,
- DominatorTree *DT, TargetLibraryInfo *TLI,
- AliasAnalysis *AA, Function *F,
- const TargetTransformInfo *TTI,
+ LoopVectorizationLegality(Loop *L, ScalarEvolution *SE, DominatorTree *DT,
+ TargetLibraryInfo *TLI, AliasAnalysis *AA,
+ Function *F, const TargetTransformInfo *TTI,
LoopAccessAnalysis *LAA,
LoopVectorizationRequirements *R,
- const LoopVectorizeHints *H)
- : NumPredStores(0), TheLoop(L), PSE(PSE), TLI(TLI), TheFunction(F),
- TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr), InterleaveInfo(PSE, L, DT),
- Induction(nullptr), WidestIndTy(nullptr), HasFunNoNaNAttr(false),
- Requirements(R), Hints(H) {}
+ const LoopVectorizeHints *H,
+ SCEVUnionPredicate &Preds)
+ : NumPredStores(0), TheLoop(L), SE(SE), TLI(TLI), TheFunction(F),
+ TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr),
+ InterleaveInfo(SE, L, DT, Preds), Induction(nullptr),
+ WidestIndTy(nullptr), HasFunNoNaNAttr(false), Requirements(R), Hints(H),
+ Preds(Preds) {}
/// ReductionList contains the reduction descriptors for all
/// of the reductions that were found in the loop.
/// The loop that we evaluate.
Loop *TheLoop;
- /// A wrapper around ScalarEvolution used to add runtime SCEV checks.
- /// Applies dynamic knowledge to simplify SCEV expressions in the context
- /// of existing SCEV assumptions. The analysis will also add a minimal set
- /// of new predicates if this is required to enable vectorization and
- /// unrolling.
- PredicatedScalarEvolution &PSE;
+ /// Scev analysis.
+ ScalarEvolution *SE;
/// Target Library Info.
TargetLibraryInfo *TLI;
/// Parent function
/// While vectorizing these instructions we have to generate a
/// call to the appropriate masked intrinsic
SmallPtrSet<const Instruction *, 8> MaskedOp;
+
+ /// The SCEV predicate containing all the SCEV-related assumptions.
+ /// The predicate is used to simplify SCEV expressions in the
+ /// context of existing SCEV assumptions. The analysis will also
+ /// add a minimal set of new predicates if this is required to
+ /// enable vectorization/unrolling.
+ SCEVUnionPredicate &Preds;
};
/// LoopVectorizationCostModel - estimates the expected speedups due to
const TargetLibraryInfo *TLI, DemandedBits *DB,
AssumptionCache *AC, const Function *F,
const LoopVectorizeHints *Hints,
- SmallPtrSetImpl<const Value *> &ValuesToIgnore)
+ SmallPtrSetImpl<const Value *> &ValuesToIgnore,
+ SCEVUnionPredicate &Preds)
: TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
TheFunction(F), Hints(Hints), ValuesToIgnore(ValuesToIgnore) {}
}
}
- PredicatedScalarEvolution PSE(*SE);
+ SCEVUnionPredicate Preds;
// Check if it is legal to vectorize the loop.
LoopVectorizationRequirements Requirements;
- LoopVectorizationLegality LVL(L, PSE, DT, TLI, AA, F, TTI, LAA,
- &Requirements, &Hints);
+ LoopVectorizationLegality LVL(L, SE, DT, TLI, AA, F, TTI, LAA,
+ &Requirements, &Hints, Preds);
if (!LVL.canVectorize()) {
DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
emitMissedWarning(F, L, Hints);
}
// Use the cost model.
- LoopVectorizationCostModel CM(L, PSE.getSE(), LI, &LVL, *TTI, TLI, DB, AC,
- F, &Hints, ValuesToIgnore);
+ LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, TLI, DB, AC, F, &Hints,
+ ValuesToIgnore, Preds);
// Check the function attributes to find out if this function should be
// optimized for size.
assert(IC > 1 && "interleave count should not be 1 or 0");
// If we decided that it is not legal to vectorize the loop then
// interleave it.
- InnerLoopUnroller Unroller(L, PSE, LI, DT, TLI, TTI, IC);
+ InnerLoopUnroller Unroller(L, SE, LI, DT, TLI, TTI, IC, Preds);
Unroller.vectorize(&LVL, CM.MinBWs);
emitOptimizationRemark(F->getContext(), LV_NAME, *F, L->getStartLoc(),
Twine(IC) + ")");
} else {
// If we decided that it is *legal* to vectorize the loop then do it.
- InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, VF.Width, IC);
+ InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, IC, Preds);
LB.vectorize(&LVL, CM.MinBWs);
++LoopsVectorized;
int LoopVectorizationLegality::isConsecutivePtr(Value *Ptr) {
assert(Ptr->getType()->isPointerTy() && "Unexpected non-ptr");
- auto *SE = PSE.getSE();
// Make sure that the pointer does not point to structs.
if (Ptr->getType()->getPointerElementType()->isAggregateType())
return 0;
// Make sure that all of the index operands are loop invariant.
for (unsigned i = 1; i < NumOperands; ++i)
- if (!SE->isLoopInvariant(PSE.getSCEV(Gep->getOperand(i)), TheLoop))
+ if (!SE->isLoopInvariant(SE->getSCEV(Gep->getOperand(i)), TheLoop))
return 0;
InductionDescriptor II = Inductions[Phi];
// operand.
for (unsigned i = 0; i != NumOperands; ++i)
if (i != InductionOperand &&
- !SE->isLoopInvariant(PSE.getSCEV(Gep->getOperand(i)), TheLoop))
+ !SE->isLoopInvariant(SE->getSCEV(Gep->getOperand(i)), TheLoop))
return 0;
// We can emit wide load/stores only if the last non-zero index is the
// induction variable.
const SCEV *Last = nullptr;
if (!Strides.count(Gep))
- Last = PSE.getSCEV(Gep->getOperand(InductionOperand));
+ Last = SE->getSCEV(Gep->getOperand(InductionOperand));
else {
// Because of the multiplication by a stride we can have a s/zext cast.
// We are going to replace this stride by 1 so the cast is safe to ignore.
// %idxprom = zext i32 %mul to i64 << Safe cast.
// %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
//
- Last = replaceSymbolicStrideSCEV(PSE, Strides,
+ Last = replaceSymbolicStrideSCEV(SE, Strides, Preds,
Gep->getOperand(InductionOperand), Gep);
if (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(Last))
Last =
Ptr = Builder.Insert(Gep2);
} else if (Gep) {
setDebugLocFromInst(Builder, Gep);
- assert(PSE.getSE()->isLoopInvariant(PSE.getSCEV(Gep->getPointerOperand()),
- OrigLoop) &&
- "Base ptr must be invariant");
+ assert(SE->isLoopInvariant(SE->getSCEV(Gep->getPointerOperand()),
+ OrigLoop) && "Base ptr must be invariant");
// The last index does not have to be the induction. It can be
// consecutive and be a function of the index. For example A[I+1];
if (i == InductionOperand ||
(GepOperandInst && OrigLoop->contains(GepOperandInst))) {
assert((i == InductionOperand ||
- PSE.getSE()->isLoopInvariant(PSE.getSCEV(GepOperandInst),
- OrigLoop)) &&
+ SE->isLoopInvariant(SE->getSCEV(GepOperandInst), OrigLoop)) &&
"Must be last index or loop invariant");
VectorParts &GEPParts = getVectorValue(GepOperand);
IRBuilder<> Builder(L->getLoopPreheader()->getTerminator());
// Find the loop boundaries.
- ScalarEvolution *SE = PSE.getSE();
const SCEV *BackedgeTakenCount = SE->getBackedgeTakenCount(OrigLoop);
assert(BackedgeTakenCount != SE->getCouldNotCompute() &&
"Invalid loop count");
// Generate the code to check that the SCEV assumptions that we made.
// We want the new basic block to start at the first instruction in a
// sequence of instructions that form a check.
- SCEVExpander Exp(*PSE.getSE(), Bypass->getModule()->getDataLayout(),
- "scev.check");
- Value *SCEVCheck =
- Exp.expandCodeForPredicate(&PSE.getUnionPredicate(), BB->getTerminator());
+ SCEVExpander Exp(*SE, Bypass->getModule()->getDataLayout(), "scev.check");
+ Value *SCEVCheck = Exp.expandCodeForPredicate(&Preds, BB->getTerminator());
if (auto *C = dyn_cast<ConstantInt>(SCEVCheck))
if (C->isZero())
// Widen selects.
// If the selector is loop invariant we can create a select
// instruction with a scalar condition. Otherwise, use vector-select.
- auto *SE = PSE.getSE();
- bool InvariantCond =
- SE->isLoopInvariant(PSE.getSCEV(it->getOperand(0)), OrigLoop);
+ bool InvariantCond = SE->isLoopInvariant(SE->getSCEV(it->getOperand(0)),
+ OrigLoop);
setDebugLocFromInst(Builder, &*it);
// The condition can be loop invariant but still defined inside the
void InnerLoopVectorizer::updateAnalysis() {
// Forget the original basic block.
- PSE.getSE()->forgetLoop(OrigLoop);
+ SE->forgetLoop(OrigLoop);
// Update the dominator tree information.
assert(DT->properlyDominates(LoopBypassBlocks.front(), LoopExitBlock) &&
}
// ScalarEvolution needs to be able to find the exit count.
- const SCEV *ExitCount = PSE.getSE()->getBackedgeTakenCount(TheLoop);
- if (ExitCount == PSE.getSE()->getCouldNotCompute()) {
- emitAnalysis(VectorizationReport()
- << "could not determine number of loop iterations");
+ const SCEV *ExitCount = SE->getBackedgeTakenCount(TheLoop);
+ if (ExitCount == SE->getCouldNotCompute()) {
+ emitAnalysis(VectorizationReport() <<
+ "could not determine number of loop iterations");
DEBUG(dbgs() << "LV: SCEV could not compute the loop exit count.\n");
return false;
}
if (Hints->getForce() == LoopVectorizeHints::FK_Enabled)
SCEVThreshold = PragmaVectorizeSCEVCheckThreshold;
- if (PSE.getUnionPredicate().getComplexity() > SCEVThreshold) {
+ if (Preds.getComplexity() > SCEVThreshold) {
emitAnalysis(VectorizationReport()
<< "Too many SCEV assumptions need to be made and checked "
<< "at runtime");
}
InductionDescriptor ID;
- if (InductionDescriptor::isInductionPHI(Phi, PSE.getSE(), ID)) {
+ if (InductionDescriptor::isInductionPHI(Phi, SE, ID)) {
Inductions[Phi] = ID;
// Get the widest type.
if (!WidestIndTy)
// second argument is the same (i.e. loop invariant)
if (CI &&
hasVectorInstrinsicScalarOpd(getIntrinsicIDForCall(CI, TLI), 1)) {
- auto *SE = PSE.getSE();
- if (!SE->isLoopInvariant(PSE.getSCEV(CI->getOperand(1)), TheLoop)) {
+ if (!SE->isLoopInvariant(SE->getSCEV(CI->getOperand(1)), TheLoop)) {
emitAnalysis(VectorizationReport(&*it)
<< "intrinsic instruction cannot be vectorized");
DEBUG(dbgs() << "LV: Found unvectorizable intrinsic " << *CI << "\n");
else
return;
- Value *Stride = getStrideFromPointer(Ptr, PSE.getSE(), TheLoop);
+ Value *Stride = getStrideFromPointer(Ptr, SE, TheLoop);
if (!Stride)
return;
}
Requirements->addRuntimePointerChecks(LAI->getNumRuntimePointerChecks());
- PSE.addPredicate(LAI->PSE.getUnionPredicate());
+ Preds.add(&LAI->Preds);
return true;
}
StoreInst *SI = dyn_cast<StoreInst>(I);
Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
- int Stride = isStridedPtr(PSE, Ptr, TheLoop, Strides);
+ int Stride = isStridedPtr(SE, Ptr, TheLoop, Strides, Preds);
// The factor of the corresponding interleave group.
unsigned Factor = std::abs(Stride);
if (Factor < 2 || Factor > MaxInterleaveGroupFactor)
continue;
- const SCEV *Scev = replaceSymbolicStrideSCEV(PSE, Strides, Ptr);
+ const SCEV *Scev = replaceSymbolicStrideSCEV(SE, Strides, Preds, Ptr);
PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
unsigned Size = DL.getTypeAllocSize(PtrTy->getElementType());
continue;
// Calculate the distance and prepare for the rule 3.
- const SCEVConstant *DistToA = dyn_cast<SCEVConstant>(
- PSE.getSE()->getMinusSCEV(DesB.Scev, DesA.Scev));
+ const SCEVConstant *DistToA =
+ dyn_cast<SCEVConstant>(SE->getMinusSCEV(DesB.Scev, DesA.Scev));
if (!DistToA)
continue;
projects / oota-llvm.git / commitdiff