// Variable uniformity checks are inspired by:
// Karrenberg, R. and Hack, S. Whole Function Vectorization.
//
+// The interleaved access vectorization is based on the paper:
+// Dorit Nuzman, Ira Rosen and Ayal Zaks. Auto-Vectorization of Interleaved
+// Data for SIMD
+//
// Other ideas/concepts are from:
// A. Zaks and D. Nuzman. Autovectorization in GCC-two years later.
//
#include "llvm/Transforms/Vectorize.h"
#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/EquivalenceClasses.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/AliasSetTracker.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/CodeMetrics.h"
+#include "llvm/Analysis/DemandedBits.h"
+#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/LoopAccessAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
-#include "llvm/Transforms/Utils/VectorUtils.h"
+#include "llvm/Analysis/VectorUtils.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include <algorithm>
+#include <functional>
#include <map>
#include <tuple>
"enable-mem-access-versioning", cl::init(true), cl::Hidden,
cl::desc("Enable symblic stride memory access versioning"));
-/// We don't unroll loops with a known constant trip count below this number.
-static const unsigned TinyTripCountUnrollThreshold = 128;
+static cl::opt<bool> EnableInterleavedMemAccesses(
+ "enable-interleaved-mem-accesses", cl::init(false), cl::Hidden,
+ cl::desc("Enable vectorization on interleaved memory accesses in a loop"));
+
+/// Maximum factor for an interleaved memory access.
+static cl::opt<unsigned> MaxInterleaveGroupFactor(
+ "max-interleave-group-factor", cl::Hidden,
+ cl::desc("Maximum factor for an interleaved access group (default = 8)"),
+ cl::init(8));
+
+/// We don't interleave loops with a known constant trip count below this
+/// number.
+static const unsigned TinyTripCountInterleaveThreshold = 128;
static cl::opt<unsigned> ForceTargetNumScalarRegs(
"force-target-num-scalar-regs", cl::init(0), cl::Hidden,
static cl::opt<unsigned> SmallLoopCost(
"small-loop-cost", cl::init(20), cl::Hidden,
- cl::desc("The cost of a loop that is considered 'small' by the unroller."));
+ cl::desc(
+ "The cost of a loop that is considered 'small' by the interleaver."));
static cl::opt<bool> LoopVectorizeWithBlockFrequency(
"loop-vectorize-with-block-frequency", cl::init(false), cl::Hidden,
"heuristics minimizing code growth in cold regions and being more "
"aggressive in hot regions."));
-// Runtime unroll loops for load/store throughput.
-static cl::opt<bool> EnableLoadStoreRuntimeUnroll(
- "enable-loadstore-runtime-unroll", cl::init(true), cl::Hidden,
- cl::desc("Enable runtime unrolling until load/store ports are saturated"));
+// Runtime interleave loops for load/store throughput.
+static cl::opt<bool> EnableLoadStoreRuntimeInterleave(
+ "enable-loadstore-runtime-interleave", cl::init(true), cl::Hidden,
+ cl::desc(
+ "Enable runtime interleaving until load/store ports are saturated"));
/// The number of stores in a loop that are allowed to need predication.
static cl::opt<unsigned> NumberOfStoresToPredicate(
static cl::opt<bool> EnableIndVarRegisterHeur(
"enable-ind-var-reg-heur", cl::init(true), cl::Hidden,
- cl::desc("Count the induction variable only once when unrolling"));
+ cl::desc("Count the induction variable only once when interleaving"));
static cl::opt<bool> EnableCondStoresVectorization(
"enable-cond-stores-vec", cl::init(false), cl::Hidden,
cl::desc("Enable if predication of stores during vectorization."));
-static cl::opt<unsigned> MaxNestedScalarReductionUF(
- "max-nested-scalar-reduction-unroll", cl::init(2), cl::Hidden,
- cl::desc("The maximum unroll factor to use when unrolling a scalar "
+static cl::opt<unsigned> MaxNestedScalarReductionIC(
+ "max-nested-scalar-reduction-interleave", cl::init(2), cl::Hidden,
+ cl::desc("The maximum interleave count to use when interleaving a scalar "
"reduction in a nested loop."));
+static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(
+ "pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
+ cl::desc("The maximum allowed number of runtime memory checks with a "
+ "vectorize(enable) pragma."));
+
namespace {
// Forward declarations.
+class LoopVectorizeHints;
class LoopVectorizationLegality;
class LoopVectorizationCostModel;
-class LoopVectorizeHints;
+class LoopVectorizationRequirements;
/// \brief This modifies LoopAccessReport to initialize message with
/// loop-vectorizer-specific part.
: 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),
- Legal(nullptr), AddedSafetyChecks(false) {}
+ TripCount(nullptr), VectorTripCount(nullptr), Legal(nullptr),
+ AddedSafetyChecks(false) {}
// Perform the actual loop widening (vectorization).
- void vectorize(LoopVectorizationLegality *L) {
+ // MinimumBitWidths maps scalar integer values to the smallest bitwidth they
+ // can be validly truncated to. The cost model has assumed this truncation
+ // will happen when vectorizing.
+ void vectorize(LoopVectorizationLegality *L,
+ DenseMap<Instruction*,uint64_t> MinimumBitWidths) {
+ MinBWs = MinimumBitWidths;
Legal = L;
// Create a new empty loop. Unlink the old loop and connect the new one.
createEmptyLoop();
// Widen each instruction in the old loop to a new one in the new loop.
// Use the Legality module to find the induction and reduction variables.
vectorizeLoop();
- // Register the new loop and update the analysis passes.
- updateAnalysis();
}
// Return true if any runtime check is added.
/// originated from one scalar instruction.
typedef SmallVector<Value*, 2> VectorParts;
- // When we if-convert we need create edge masks. We have to cache values so
- // that we don't end up with exponential recursion/IR.
+ // When we if-convert we need to create edge masks. We have to cache values
+ // so that we don't end up with exponential recursion/IR.
typedef DenseMap<std::pair<BasicBlock*, BasicBlock*>,
VectorParts> EdgeMaskCache;
- /// \brief Add checks for strides that where assumed to be 1.
+ /// \brief Add checks for strides that were assumed to be 1.
///
/// Returns the last check instruction and the first check instruction in the
/// pair as (first, last).
/// Create an empty loop, based on the loop ranges of the old loop.
void createEmptyLoop();
+ /// Create a new induction variable inside L.
+ PHINode *createInductionVariable(Loop *L, Value *Start, Value *End,
+ Value *Step, Instruction *DL);
/// Copy and widen the instructions from the old loop.
virtual void vectorizeLoop();
/// See PR14725.
void fixLCSSAPHIs();
+ /// Shrinks vector element sizes based on information in "MinBWs".
+ void truncateToMinimalBitwidths();
+
/// A helper function that computes the predicate of the block BB, assuming
/// that the header block of the loop is set to True. It returns the *entry*
/// mask for the block BB.
/// A helper function to vectorize a single BB within the innermost loop.
void vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV);
-
+
/// Vectorize a single PHINode in a block. This method handles the induction
/// variable canonicalization. It supports both VF = 1 for unrolled loops and
/// arbitrary length vectors.
/// broadcast them into a vector.
VectorParts &getVectorValue(Value *V);
+ /// Try to vectorize the interleaved access group that \p Instr belongs to.
+ void vectorizeInterleaveGroup(Instruction *Instr);
+
/// Generate a shuffle sequence that will reverse the vector Vec.
virtual Value *reverseVector(Value *Vec);
+ /// Returns (and creates if needed) the original loop trip count.
+ Value *getOrCreateTripCount(Loop *NewLoop);
+
+ /// Returns (and creates if needed) the trip count of the widened loop.
+ Value *getOrCreateVectorTripCount(Loop *NewLoop);
+
+ /// Emit a bypass check to see if the trip count would overflow, or we
+ /// wouldn't have enough iterations to execute one vector loop.
+ void emitMinimumIterationCountCheck(Loop *L, BasicBlock *Bypass);
+ /// Emit a bypass check to see if the vector trip count is nonzero.
+ void emitVectorLoopEnteredCheck(Loop *L, BasicBlock *Bypass);
+ /// Emit bypass checks to check if strides we've assumed to be one really are.
+ void emitStrideChecks(Loop *L, BasicBlock *Bypass);
+ /// Emit bypass checks to check any memory assumptions we may have made.
+ void emitMemRuntimeChecks(Loop *L, BasicBlock *Bypass);
+
/// This is a helper class that holds the vectorizer state. It maps scalar
/// instructions to vector instructions. When the code is 'unrolled' then
/// then a single scalar value is mapped to multiple vector parts. The parts
PHINode *Induction;
/// The induction variable of the old basic block.
PHINode *OldInduction;
- /// Holds the extended (to the widest induction type) start index.
- Value *ExtendedIdx;
/// Maps scalars to widened vectors.
ValueMap WidenMap;
+ /// Store instructions that should be predicated, as a pair
+ /// <StoreInst, Predicate>
+ SmallVector<std::pair<StoreInst*,Value*>, 4> PredicatedStores;
EdgeMaskCache MaskCache;
-
+ /// Trip count of the original loop.
+ Value *TripCount;
+ /// Trip count of the widened loop (TripCount - TripCount % (VF*UF))
+ Value *VectorTripCount;
+
+ /// Map of scalar integer values to the smallest bitwidth they can be legally
+ /// represented as. The vector equivalents of these values should be truncated
+ /// to this type.
+ DenseMap<Instruction*,uint64_t> MinBWs;
LoopVectorizationLegality *Legal;
// Record whether runtime check is added.
if (Kind != LLVMContext::MD_tbaa &&
Kind != LLVMContext::MD_alias_scope &&
Kind != LLVMContext::MD_noalias &&
- Kind != LLVMContext::MD_fpmath)
+ Kind != LLVMContext::MD_fpmath &&
+ Kind != LLVMContext::MD_nontemporal)
continue;
To->setMetadata(Kind, M.second);
propagateMetadata(I, From);
}
-/// LoopVectorizationLegality checks if it is legal to vectorize a loop, and
-/// to what vectorization factor.
-/// This class does not look at the profitability of vectorization, only the
-/// legality. This class has two main kinds of checks:
-/// * Memory checks - The code in canVectorizeMemory checks if vectorization
-/// will change the order of memory accesses in a way that will change the
-/// correctness of the program.
-/// * Scalars checks - The code in canVectorizeInstrs and canVectorizeMemory
-/// checks for a number of different conditions, such as the availability of a
-/// single induction variable, that all types are supported and vectorize-able,
-/// etc. This code reflects the capabilities of InnerLoopVectorizer.
-/// This class is also used by InnerLoopVectorizer for identifying
-/// induction variable and the different reduction variables.
-class LoopVectorizationLegality {
+/// \brief The group of interleaved loads/stores sharing the same stride and
+/// close to each other.
+///
+/// Each member in this group has an index starting from 0, and the largest
+/// index should be less than interleaved factor, which is equal to the absolute
+/// value of the access's stride.
+///
+/// E.g. An interleaved load group of factor 4:
+/// for (unsigned i = 0; i < 1024; i+=4) {
+/// a = A[i]; // Member of index 0
+/// b = A[i+1]; // Member of index 1
+/// d = A[i+3]; // Member of index 3
+/// ...
+/// }
+///
+/// An interleaved store group of factor 4:
+/// for (unsigned i = 0; i < 1024; i+=4) {
+/// ...
+/// A[i] = a; // Member of index 0
+/// A[i+1] = b; // Member of index 1
+/// A[i+2] = c; // Member of index 2
+/// A[i+3] = d; // Member of index 3
+/// }
+///
+/// Note: the interleaved load group could have gaps (missing members), but
+/// the interleaved store group doesn't allow gaps.
+class InterleaveGroup {
public:
- LoopVectorizationLegality(Loop *L, ScalarEvolution *SE, DominatorTree *DT,
- TargetLibraryInfo *TLI, AliasAnalysis *AA,
- Function *F, const TargetTransformInfo *TTI,
- LoopAccessAnalysis *LAA)
- : NumPredStores(0), TheLoop(L), SE(SE), TLI(TLI), TheFunction(F),
- TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr), Induction(nullptr),
- WidestIndTy(nullptr), HasFunNoNaNAttr(false) {}
-
- /// This enum represents the kinds of inductions that we support.
- enum InductionKind {
- IK_NoInduction, ///< Not an induction variable.
- IK_IntInduction, ///< Integer induction variable. Step = C.
- IK_PtrInduction ///< Pointer induction var. Step = C / sizeof(elem).
- };
+ InterleaveGroup(Instruction *Instr, int Stride, unsigned Align)
+ : Align(Align), SmallestKey(0), LargestKey(0), InsertPos(Instr) {
+ assert(Align && "The alignment should be non-zero");
- /// A struct for saving information about induction variables.
- struct InductionInfo {
- InductionInfo(Value *Start, InductionKind K, ConstantInt *Step)
- : StartValue(Start), IK(K), StepValue(Step) {
- assert(IK != IK_NoInduction && "Not an induction");
- assert(StartValue && "StartValue is null");
- assert(StepValue && !StepValue->isZero() && "StepValue is zero");
- assert((IK != IK_PtrInduction || StartValue->getType()->isPointerTy()) &&
- "StartValue is not a pointer for pointer induction");
- assert((IK != IK_IntInduction || StartValue->getType()->isIntegerTy()) &&
- "StartValue is not an integer for integer induction");
- assert(StepValue->getType()->isIntegerTy() &&
- "StepValue is not an integer");
- }
- InductionInfo()
- : StartValue(nullptr), IK(IK_NoInduction), StepValue(nullptr) {}
-
- /// Get the consecutive direction. Returns:
- /// 0 - unknown or non-consecutive.
- /// 1 - consecutive and increasing.
- /// -1 - consecutive and decreasing.
- int getConsecutiveDirection() const {
- if (StepValue && (StepValue->isOne() || StepValue->isMinusOne()))
- return StepValue->getSExtValue();
- return 0;
- }
+ Factor = std::abs(Stride);
+ assert(Factor > 1 && "Invalid interleave factor");
- /// Compute the transformed value of Index at offset StartValue using step
- /// StepValue.
- /// For integer induction, returns StartValue + Index * StepValue.
- /// For pointer induction, returns StartValue[Index * StepValue].
- /// FIXME: The newly created binary instructions should contain nsw/nuw
- /// flags, which can be found from the original scalar operations.
- Value *transform(IRBuilder<> &B, Value *Index) const {
- switch (IK) {
- case IK_IntInduction:
- assert(Index->getType() == StartValue->getType() &&
- "Index type does not match StartValue type");
- if (StepValue->isMinusOne())
- return B.CreateSub(StartValue, Index);
- if (!StepValue->isOne())
- Index = B.CreateMul(Index, StepValue);
- return B.CreateAdd(StartValue, Index);
-
- case IK_PtrInduction:
- if (StepValue->isMinusOne())
- Index = B.CreateNeg(Index);
- else if (!StepValue->isOne())
- Index = B.CreateMul(Index, StepValue);
- return B.CreateGEP(nullptr, StartValue, Index);
-
- case IK_NoInduction:
- return nullptr;
- }
- llvm_unreachable("invalid enum");
- }
+ Reverse = Stride < 0;
+ Members[0] = Instr;
+ }
- /// Start value.
- TrackingVH<Value> StartValue;
- /// Induction kind.
- InductionKind IK;
- /// Step value.
- ConstantInt *StepValue;
- };
+ bool isReverse() const { return Reverse; }
+ unsigned getFactor() const { return Factor; }
+ unsigned getAlignment() const { return Align; }
+ unsigned getNumMembers() const { return Members.size(); }
- /// ReductionList contains the reduction descriptors for all
- /// of the reductions that were found in the loop.
- typedef DenseMap<PHINode*, ReductionDescriptor> ReductionList;
+ /// \brief Try to insert a new member \p Instr with index \p Index and
+ /// alignment \p NewAlign. The index is related to the leader and it could be
+ /// negative if it is the new leader.
+ ///
+ /// \returns false if the instruction doesn't belong to the group.
+ bool insertMember(Instruction *Instr, int Index, unsigned NewAlign) {
+ assert(NewAlign && "The new member's alignment should be non-zero");
- /// InductionList saves induction variables and maps them to the
- /// induction descriptor.
- typedef MapVector<PHINode*, InductionInfo> InductionList;
+ int Key = Index + SmallestKey;
- /// Returns true if it is legal to vectorize this loop.
- /// This does not mean that it is profitable to vectorize this
- /// loop, only that it is legal to do so.
- bool canVectorize();
+ // Skip if there is already a member with the same index.
+ if (Members.count(Key))
+ return false;
- /// Returns the Induction variable.
- PHINode *getInduction() { return Induction; }
+ if (Key > LargestKey) {
+ // The largest index is always less than the interleave factor.
+ if (Index >= static_cast<int>(Factor))
+ return false;
- /// Returns the reduction variables found in the loop.
- ReductionList *getReductionVars() { return &Reductions; }
+ LargestKey = Key;
+ } else if (Key < SmallestKey) {
+ // The largest index is always less than the interleave factor.
+ if (LargestKey - Key >= static_cast<int>(Factor))
+ return false;
- /// Returns the induction variables found in the loop.
- InductionList *getInductionVars() { return &Inductions; }
+ SmallestKey = Key;
+ }
- /// Returns the widest induction type.
- Type *getWidestInductionType() { return WidestIndTy; }
+ // It's always safe to select the minimum alignment.
+ Align = std::min(Align, NewAlign);
+ Members[Key] = Instr;
+ return true;
+ }
- /// Returns True if V is an induction variable in this loop.
- bool isInductionVariable(const Value *V);
+ /// \brief Get the member with the given index \p Index
+ ///
+ /// \returns nullptr if contains no such member.
+ Instruction *getMember(unsigned Index) const {
+ int Key = SmallestKey + Index;
+ if (!Members.count(Key))
+ return nullptr;
- /// Return true if the block BB needs to be predicated in order for the loop
- /// to be vectorized.
- bool blockNeedsPredication(BasicBlock *BB);
+ return Members.find(Key)->second;
+ }
- /// Check if this pointer is consecutive when vectorizing. This happens
- /// when the last index of the GEP is the induction variable, or that the
- /// pointer itself is an induction variable.
- /// This check allows us to vectorize A[idx] into a wide load/store.
- /// Returns:
- /// 0 - Stride is unknown or non-consecutive.
- /// 1 - Address is consecutive.
- /// -1 - Address is consecutive, and decreasing.
- int isConsecutivePtr(Value *Ptr);
+ /// \brief Get the index for the given member. Unlike the key in the member
+ /// map, the index starts from 0.
+ unsigned getIndex(Instruction *Instr) const {
+ for (auto I : Members)
+ if (I.second == Instr)
+ return I.first - SmallestKey;
- /// Returns true if the value V is uniform within the loop.
- bool isUniform(Value *V);
+ llvm_unreachable("InterleaveGroup contains no such member");
+ }
- /// Returns true if this instruction will remain scalar after vectorization.
- bool isUniformAfterVectorization(Instruction* I) { return Uniforms.count(I); }
+ Instruction *getInsertPos() const { return InsertPos; }
+ void setInsertPos(Instruction *Inst) { InsertPos = Inst; }
- /// Returns the information that we collected about runtime memory check.
- const LoopAccessInfo::RuntimePointerCheck *getRuntimePointerCheck() const {
- return LAI->getRuntimePointerCheck();
- }
+private:
+ unsigned Factor; // Interleave Factor.
+ bool Reverse;
+ unsigned Align;
+ DenseMap<int, Instruction *> Members;
+ int SmallestKey;
+ int LargestKey;
+
+ // To avoid breaking dependences, vectorized instructions of an interleave
+ // group should be inserted at either the first load or the last store in
+ // program order.
+ //
+ // E.g. %even = load i32 // Insert Position
+ // %add = add i32 %even // Use of %even
+ // %odd = load i32
+ //
+ // store i32 %even
+ // %odd = add i32 // Def of %odd
+ // store i32 %odd // Insert Position
+ Instruction *InsertPos;
+};
- const LoopAccessInfo *getLAI() const {
- return LAI;
+/// \brief Drive the analysis of interleaved memory accesses in the loop.
+///
+/// Use this class to analyze interleaved accesses only when we can vectorize
+/// a loop. Otherwise it's meaningless to do analysis as the vectorization
+/// on interleaved accesses is unsafe.
+///
+/// The analysis collects interleave groups and records the relationships
+/// between the member and the group in a map.
+class InterleavedAccessInfo {
+public:
+ InterleavedAccessInfo(ScalarEvolution *SE, Loop *L, DominatorTree *DT)
+ : SE(SE), TheLoop(L), DT(DT) {}
+
+ ~InterleavedAccessInfo() {
+ SmallSet<InterleaveGroup *, 4> DelSet;
+ // Avoid releasing a pointer twice.
+ for (auto &I : InterleaveGroupMap)
+ DelSet.insert(I.second);
+ for (auto *Ptr : DelSet)
+ delete Ptr;
}
- unsigned getMaxSafeDepDistBytes() { return LAI->getMaxSafeDepDistBytes(); }
+ /// \brief Analyze the interleaved accesses and collect them in interleave
+ /// groups. Substitute symbolic strides using \p Strides.
+ void analyzeInterleaving(const ValueToValueMap &Strides);
- bool hasStride(Value *V) { return StrideSet.count(V); }
- bool mustCheckStrides() { return !StrideSet.empty(); }
- SmallPtrSet<Value *, 8>::iterator strides_begin() {
- return StrideSet.begin();
+ /// \brief Check if \p Instr belongs to any interleave group.
+ bool isInterleaved(Instruction *Instr) const {
+ return InterleaveGroupMap.count(Instr);
}
- SmallPtrSet<Value *, 8>::iterator strides_end() { return StrideSet.end(); }
- /// Returns true if the target machine supports masked store operation
- /// for the given \p DataType and kind of access to \p Ptr.
- bool isLegalMaskedStore(Type *DataType, Value *Ptr) {
- return TTI->isLegalMaskedStore(DataType, isConsecutivePtr(Ptr));
- }
- /// Returns true if the target machine supports masked load operation
- /// for the given \p DataType and kind of access to \p Ptr.
- bool isLegalMaskedLoad(Type *DataType, Value *Ptr) {
- return TTI->isLegalMaskedLoad(DataType, isConsecutivePtr(Ptr));
- }
- /// Returns true if vector representation of the instruction \p I
- /// requires mask.
- bool isMaskRequired(const Instruction* I) {
- return (MaskedOp.count(I) != 0);
- }
- unsigned getNumStores() const {
- return LAI->getNumStores();
- }
- unsigned getNumLoads() const {
- return LAI->getNumLoads();
- }
- unsigned getNumPredStores() const {
- return NumPredStores;
+ /// \brief Get the interleave group that \p Instr belongs to.
+ ///
+ /// \returns nullptr if doesn't have such group.
+ InterleaveGroup *getInterleaveGroup(Instruction *Instr) const {
+ if (InterleaveGroupMap.count(Instr))
+ return InterleaveGroupMap.find(Instr)->second;
+ return nullptr;
}
-private:
- /// Check if a single basic block loop is vectorizable.
- /// At this point we know that this is a loop with a constant trip count
- /// and we only need to check individual instructions.
- bool canVectorizeInstrs();
- /// When we vectorize loops we may change the order in which
- /// we read and write from memory. This method checks if it is
- /// legal to vectorize the code, considering only memory constrains.
- /// Returns true if the loop is vectorizable
- bool canVectorizeMemory();
+private:
+ ScalarEvolution *SE;
+ Loop *TheLoop;
+ DominatorTree *DT;
- /// Return true if we can vectorize this loop using the IF-conversion
- /// transformation.
- bool canVectorizeWithIfConvert();
+ /// Holds the relationships between the members and the interleave group.
+ DenseMap<Instruction *, InterleaveGroup *> InterleaveGroupMap;
- /// Collect the variables that need to stay uniform after vectorization.
- void collectLoopUniforms();
+ /// \brief The descriptor for a strided memory access.
+ struct StrideDescriptor {
+ StrideDescriptor(int Stride, const SCEV *Scev, unsigned Size,
+ unsigned Align)
+ : Stride(Stride), Scev(Scev), Size(Size), Align(Align) {}
- /// Return true if all of the instructions in the block can be speculatively
- /// executed. \p SafePtrs is a list of addresses that are known to be legal
- /// and we know that we can read from them without segfault.
- bool blockCanBePredicated(BasicBlock *BB, SmallPtrSetImpl<Value *> &SafePtrs);
+ StrideDescriptor() : Stride(0), Scev(nullptr), Size(0), Align(0) {}
- /// Returns the induction kind of Phi and record the step. This function may
- /// return NoInduction if the PHI is not an induction variable.
- InductionKind isInductionVariable(PHINode *Phi, ConstantInt *&StepValue);
+ int Stride; // The access's stride. It is negative for a reverse access.
+ const SCEV *Scev; // The scalar expression of this access
+ unsigned Size; // The size of the memory object.
+ unsigned Align; // The alignment of this access.
+ };
- /// \brief Collect memory access with loop invariant strides.
+ /// \brief Create a new interleave group with the given instruction \p Instr,
+ /// stride \p Stride and alignment \p Align.
///
- /// Looks for accesses like "a[i * StrideA]" where "StrideA" is loop
- /// invariant.
- void collectStridedAccess(Value *LoadOrStoreInst);
-
- /// Report an analysis message to assist the user in diagnosing loops that are
- /// not vectorized. These are handled as LoopAccessReport rather than
- /// VectorizationReport because the << operator of VectorizationReport returns
- /// LoopAccessReport.
- void emitAnalysis(const LoopAccessReport &Message) {
- LoopAccessReport::emitAnalysis(Message, TheFunction, TheLoop, LV_NAME);
+ /// \returns the newly created interleave group.
+ InterleaveGroup *createInterleaveGroup(Instruction *Instr, int Stride,
+ unsigned Align) {
+ assert(!InterleaveGroupMap.count(Instr) &&
+ "Already in an interleaved access group");
+ InterleaveGroupMap[Instr] = new InterleaveGroup(Instr, Stride, Align);
+ return InterleaveGroupMap[Instr];
}
- unsigned NumPredStores;
+ /// \brief Release the group and remove all the relationships.
+ void releaseGroup(InterleaveGroup *Group) {
+ for (unsigned i = 0; i < Group->getFactor(); i++)
+ if (Instruction *Member = Group->getMember(i))
+ InterleaveGroupMap.erase(Member);
- /// The loop that we evaluate.
- Loop *TheLoop;
- /// Scev analysis.
- ScalarEvolution *SE;
- /// Target Library Info.
- TargetLibraryInfo *TLI;
- /// Parent function
- Function *TheFunction;
- /// Target Transform Info
- const TargetTransformInfo *TTI;
- /// Dominator Tree.
- DominatorTree *DT;
- // LoopAccess analysis.
- LoopAccessAnalysis *LAA;
- // And the loop-accesses info corresponding to this loop. This pointer is
- // null until canVectorizeMemory sets it up.
- const LoopAccessInfo *LAI;
+ delete Group;
+ }
- // --- vectorization state --- //
+ /// \brief Collect all the accesses with a constant stride in program order.
+ void collectConstStridedAccesses(
+ MapVector<Instruction *, StrideDescriptor> &StrideAccesses,
+ const ValueToValueMap &Strides);
+};
- /// Holds the integer induction variable. This is the counter of the
- /// loop.
- PHINode *Induction;
- /// Holds the reduction variables.
- ReductionList Reductions;
- /// Holds all of the induction variables that we found in the loop.
- /// Notice that inductions don't need to start at zero and that induction
- /// variables can be pointers.
- InductionList Inductions;
- /// Holds the widest induction type encountered.
- Type *WidestIndTy;
+/// Utility class for getting and setting loop vectorizer hints in the form
+/// of loop metadata.
+/// This class keeps a number of loop annotations locally (as member variables)
+/// and can, upon request, write them back as metadata on the loop. It will
+/// initially scan the loop for existing metadata, and will update the local
+/// values based on information in the loop.
+/// We cannot write all values to metadata, as the mere presence of some info,
+/// for example 'force', means a decision has been made. So, we need to be
+/// careful NOT to add them if the user hasn't specifically asked so.
+class LoopVectorizeHints {
+ enum HintKind {
+ HK_WIDTH,
+ HK_UNROLL,
+ HK_FORCE
+ };
- /// Allowed outside users. This holds the reduction
- /// vars which can be accessed from outside the loop.
- SmallPtrSet<Value*, 4> AllowedExit;
- /// This set holds the variables which are known to be uniform after
- /// vectorization.
- SmallPtrSet<Instruction*, 4> Uniforms;
+ /// Hint - associates name and validation with the hint value.
+ struct Hint {
+ const char * Name;
+ unsigned Value; // This may have to change for non-numeric values.
+ HintKind Kind;
- /// Can we assume the absence of NaNs.
- bool HasFunNoNaNAttr;
+ Hint(const char * Name, unsigned Value, HintKind Kind)
+ : Name(Name), Value(Value), Kind(Kind) { }
- ValueToValueMap Strides;
- SmallPtrSet<Value *, 8> StrideSet;
+ bool validate(unsigned Val) {
+ switch (Kind) {
+ case HK_WIDTH:
+ return isPowerOf2_32(Val) && Val <= VectorizerParams::MaxVectorWidth;
+ case HK_UNROLL:
+ return isPowerOf2_32(Val) && Val <= MaxInterleaveFactor;
+ case HK_FORCE:
+ return (Val <= 1);
+ }
+ return false;
+ }
+ };
- /// While vectorizing these instructions we have to generate a
- /// call to the appropriate masked intrinsic
- SmallPtrSet<const Instruction*, 8> MaskedOp;
-};
-
-/// LoopVectorizationCostModel - estimates the expected speedups due to
-/// vectorization.
-/// In many cases vectorization is not profitable. This can happen because of
-/// a number of reasons. In this class we mainly attempt to predict the
-/// expected speedup/slowdowns due to the supported instruction set. We use the
-/// TargetTransformInfo to query the different backends for the cost of
-/// different operations.
-class LoopVectorizationCostModel {
-public:
- LoopVectorizationCostModel(Loop *L, ScalarEvolution *SE, LoopInfo *LI,
- LoopVectorizationLegality *Legal,
- const TargetTransformInfo &TTI,
- const TargetLibraryInfo *TLI, AssumptionCache *AC,
- const Function *F, const LoopVectorizeHints *Hints)
- : TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI),
- TheFunction(F), Hints(Hints) {
- CodeMetrics::collectEphemeralValues(L, AC, EphValues);
- }
-
- /// Information about vectorization costs
- struct VectorizationFactor {
- unsigned Width; // Vector width with best cost
- unsigned Cost; // Cost of the loop with that width
- };
- /// \return The most profitable vectorization factor and the cost of that VF.
- /// This method checks every power of two up to VF. If UserVF is not ZERO
- /// then this vectorization factor will be selected if vectorization is
- /// possible.
- VectorizationFactor selectVectorizationFactor(bool OptForSize);
-
- /// \return The size (in bits) of the widest type in the code that
- /// needs to be vectorized. We ignore values that remain scalar such as
- /// 64 bit loop indices.
- unsigned getWidestType();
-
- /// \return The most profitable unroll factor.
- /// If UserUF is non-zero then this method finds the best unroll-factor
- /// based on register pressure and other parameters.
- /// VF and LoopCost are the selected vectorization factor and the cost of the
- /// selected VF.
- unsigned selectUnrollFactor(bool OptForSize, unsigned VF, unsigned LoopCost);
-
- /// \brief A struct that represents some properties of the register usage
- /// of a loop.
- struct RegisterUsage {
- /// Holds the number of loop invariant values that are used in the loop.
- unsigned LoopInvariantRegs;
- /// Holds the maximum number of concurrent live intervals in the loop.
- unsigned MaxLocalUsers;
- /// Holds the number of instructions in the loop.
- unsigned NumInstructions;
- };
-
- /// \return information about the register usage of the loop.
- RegisterUsage calculateRegisterUsage();
-
-private:
- /// Returns the expected execution cost. The unit of the cost does
- /// not matter because we use the 'cost' units to compare different
- /// vector widths. The cost that is returned is *not* normalized by
- /// the factor width.
- unsigned expectedCost(unsigned VF);
-
- /// Returns the execution time cost of an instruction for a given vector
- /// width. Vector width of one means scalar.
- unsigned getInstructionCost(Instruction *I, unsigned VF);
-
- /// Returns whether the instruction is a load or store and will be a emitted
- /// as a vector operation.
- bool isConsecutiveLoadOrStore(Instruction *I);
-
- /// Report an analysis message to assist the user in diagnosing loops that are
- /// not vectorized. These are handled as LoopAccessReport rather than
- /// VectorizationReport because the << operator of VectorizationReport returns
- /// LoopAccessReport.
- void emitAnalysis(const LoopAccessReport &Message) {
- LoopAccessReport::emitAnalysis(Message, TheFunction, TheLoop, LV_NAME);
- }
-
- /// Values used only by @llvm.assume calls.
- SmallPtrSet<const Value *, 32> EphValues;
-
- /// The loop that we evaluate.
- Loop *TheLoop;
- /// Scev analysis.
- ScalarEvolution *SE;
- /// Loop Info analysis.
- LoopInfo *LI;
- /// Vectorization legality.
- LoopVectorizationLegality *Legal;
- /// Vector target information.
- const TargetTransformInfo &TTI;
- /// Target Library Info.
- const TargetLibraryInfo *TLI;
- const Function *TheFunction;
- // Loop Vectorize Hint.
- const LoopVectorizeHints *Hints;
-};
-
-/// Utility class for getting and setting loop vectorizer hints in the form
-/// of loop metadata.
-/// This class keeps a number of loop annotations locally (as member variables)
-/// and can, upon request, write them back as metadata on the loop. It will
-/// initially scan the loop for existing metadata, and will update the local
-/// values based on information in the loop.
-/// We cannot write all values to metadata, as the mere presence of some info,
-/// for example 'force', means a decision has been made. So, we need to be
-/// careful NOT to add them if the user hasn't specifically asked so.
-class LoopVectorizeHints {
- enum HintKind {
- HK_WIDTH,
- HK_UNROLL,
- HK_FORCE
- };
-
- /// Hint - associates name and validation with the hint value.
- struct Hint {
- const char * Name;
- unsigned Value; // This may have to change for non-numeric values.
- HintKind Kind;
-
- Hint(const char * Name, unsigned Value, HintKind Kind)
- : Name(Name), Value(Value), Kind(Kind) { }
-
- bool validate(unsigned Val) {
- switch (Kind) {
- case HK_WIDTH:
- return isPowerOf2_32(Val) && Val <= VectorizerParams::MaxVectorWidth;
- case HK_UNROLL:
- return isPowerOf2_32(Val) && Val <= MaxInterleaveFactor;
- case HK_FORCE:
- return (Val <= 1);
- }
- return false;
- }
- };
-
- /// Vectorization width.
- Hint Width;
- /// Vectorization interleave factor.
- Hint Interleave;
- /// Vectorization forced
- Hint Force;
-
- /// Return the loop metadata prefix.
- static StringRef Prefix() { return "llvm.loop."; }
+ /// Vectorization width.
+ Hint Width;
+ /// Vectorization interleave factor.
+ Hint Interleave;
+ /// Vectorization forced
+ Hint Force;
+
+ /// Return the loop metadata prefix.
+ static StringRef Prefix() { return "llvm.loop."; }
public:
enum ForceKind {
writeHintsToMetadata(Hints);
}
+ bool allowVectorization(Function *F, Loop *L, bool AlwaysVectorize) const {
+ if (getForce() == LoopVectorizeHints::FK_Disabled) {
+ DEBUG(dbgs() << "LV: Not vectorizing: #pragma vectorize disable.\n");
+ emitOptimizationRemarkAnalysis(F->getContext(),
+ vectorizeAnalysisPassName(), *F,
+ L->getStartLoc(), emitRemark());
+ return false;
+ }
+
+ if (!AlwaysVectorize && getForce() != LoopVectorizeHints::FK_Enabled) {
+ DEBUG(dbgs() << "LV: Not vectorizing: No #pragma vectorize enable.\n");
+ emitOptimizationRemarkAnalysis(F->getContext(),
+ vectorizeAnalysisPassName(), *F,
+ L->getStartLoc(), emitRemark());
+ return false;
+ }
+
+ if (getWidth() == 1 && getInterleave() == 1) {
+ // FIXME: Add a separate metadata to indicate when the loop has already
+ // been vectorized instead of setting width and count to 1.
+ DEBUG(dbgs() << "LV: Not vectorizing: Disabled/already vectorized.\n");
+ // FIXME: Add interleave.disable metadata. This will allow
+ // vectorize.disable to be used without disabling the pass and errors
+ // to differentiate between disabled vectorization and a width of 1.
+ emitOptimizationRemarkAnalysis(
+ F->getContext(), vectorizeAnalysisPassName(), *F, L->getStartLoc(),
+ "loop not vectorized: vectorization and interleaving are explicitly "
+ "disabled, or vectorize width and interleave count are both set to "
+ "1");
+ return false;
+ }
+
+ return true;
+ }
+
/// Dumps all the hint information.
std::string emitRemark() const {
VectorizationReport R;
unsigned getWidth() const { return Width.Value; }
unsigned getInterleave() const { return Interleave.Value; }
enum ForceKind getForce() const { return (ForceKind)Force.Value; }
+ const char *vectorizeAnalysisPassName() const {
+ // If hints are provided that don't disable vectorization use the
+ // AlwaysPrint pass name to force the frontend to print the diagnostic.
+ if (getWidth() == 1)
+ return LV_NAME;
+ if (getForce() == LoopVectorizeHints::FK_Disabled)
+ return LV_NAME;
+ if (getForce() == LoopVectorizeHints::FK_Undefined && getWidth() == 0)
+ return LV_NAME;
+ return DiagnosticInfo::AlwaysPrint;
+ }
+
+ bool allowReordering() const {
+ // When enabling loop hints are provided we allow the vectorizer to change
+ // the order of operations that is given by the scalar loop. This is not
+ // enabled by default because can be unsafe or inefficient. For example,
+ // reordering floating-point operations will change the way round-off
+ // error accumulates in the loop.
+ return getForce() == LoopVectorizeHints::FK_Enabled || getWidth() > 1;
+ }
private:
/// Find hints specified in the loop metadata and update local values.
return MDNode::get(Context, MDs);
}
- /// Matches metadata with hint name.
- bool matchesHintMetadataName(MDNode *Node, ArrayRef<Hint> HintTypes) {
- MDString* Name = dyn_cast<MDString>(Node->getOperand(0));
- if (!Name)
- return false;
+ /// Matches metadata with hint name.
+ bool matchesHintMetadataName(MDNode *Node, ArrayRef<Hint> HintTypes) {
+ MDString* Name = dyn_cast<MDString>(Node->getOperand(0));
+ if (!Name)
+ return false;
+
+ for (auto H : HintTypes)
+ if (Name->getString().endswith(H.Name))
+ return true;
+ return false;
+ }
+
+ /// Sets current hints into loop metadata, keeping other values intact.
+ void writeHintsToMetadata(ArrayRef<Hint> HintTypes) {
+ if (HintTypes.size() == 0)
+ return;
+
+ // Reserve the first element to LoopID (see below).
+ SmallVector<Metadata *, 4> MDs(1);
+ // If the loop already has metadata, then ignore the existing operands.
+ MDNode *LoopID = TheLoop->getLoopID();
+ if (LoopID) {
+ for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i) {
+ MDNode *Node = cast<MDNode>(LoopID->getOperand(i));
+ // If node in update list, ignore old value.
+ if (!matchesHintMetadataName(Node, HintTypes))
+ MDs.push_back(Node);
+ }
+ }
+
+ // Now, add the missing hints.
+ for (auto H : HintTypes)
+ MDs.push_back(createHintMetadata(Twine(Prefix(), H.Name).str(), H.Value));
+
+ // Replace current metadata node with new one.
+ LLVMContext &Context = TheLoop->getHeader()->getContext();
+ MDNode *NewLoopID = MDNode::get(Context, MDs);
+ // Set operand 0 to refer to the loop id itself.
+ NewLoopID->replaceOperandWith(0, NewLoopID);
+
+ TheLoop->setLoopID(NewLoopID);
+ }
+
+ /// The loop these hints belong to.
+ const Loop *TheLoop;
+};
+
+static void emitAnalysisDiag(const Function *TheFunction, const Loop *TheLoop,
+ const LoopVectorizeHints &Hints,
+ const LoopAccessReport &Message) {
+ const char *Name = Hints.vectorizeAnalysisPassName();
+ LoopAccessReport::emitAnalysis(Message, TheFunction, TheLoop, Name);
+}
+
+static void emitMissedWarning(Function *F, Loop *L,
+ const LoopVectorizeHints &LH) {
+ emitOptimizationRemarkMissed(F->getContext(), LV_NAME, *F, L->getStartLoc(),
+ LH.emitRemark());
+
+ if (LH.getForce() == LoopVectorizeHints::FK_Enabled) {
+ if (LH.getWidth() != 1)
+ emitLoopVectorizeWarning(
+ F->getContext(), *F, L->getStartLoc(),
+ "failed explicitly specified loop vectorization");
+ else if (LH.getInterleave() != 1)
+ emitLoopInterleaveWarning(
+ F->getContext(), *F, L->getStartLoc(),
+ "failed explicitly specified loop interleaving");
+ }
+}
+
+/// LoopVectorizationLegality checks if it is legal to vectorize a loop, and
+/// to what vectorization factor.
+/// This class does not look at the profitability of vectorization, only the
+/// legality. This class has two main kinds of checks:
+/// * Memory checks - The code in canVectorizeMemory checks if vectorization
+/// will change the order of memory accesses in a way that will change the
+/// correctness of the program.
+/// * Scalars checks - The code in canVectorizeInstrs and canVectorizeMemory
+/// checks for a number of different conditions, such as the availability of a
+/// single induction variable, that all types are supported and vectorize-able,
+/// etc. This code reflects the capabilities of InnerLoopVectorizer.
+/// This class is also used by InnerLoopVectorizer for identifying
+/// induction variable and the different reduction variables.
+class LoopVectorizationLegality {
+public:
+ 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), SE(SE), TLI(TLI), TheFunction(F),
+ TTI(TTI), DT(DT), LAA(LAA), LAI(nullptr), InterleaveInfo(SE, L, DT),
+ Induction(nullptr), WidestIndTy(nullptr), HasFunNoNaNAttr(false),
+ Requirements(R), Hints(H) {}
+
+ /// ReductionList contains the reduction descriptors for all
+ /// of the reductions that were found in the loop.
+ typedef DenseMap<PHINode *, RecurrenceDescriptor> ReductionList;
+
+ /// InductionList saves induction variables and maps them to the
+ /// induction descriptor.
+ typedef MapVector<PHINode*, InductionDescriptor> InductionList;
+
+ /// Returns true if it is legal to vectorize this loop.
+ /// This does not mean that it is profitable to vectorize this
+ /// loop, only that it is legal to do so.
+ bool canVectorize();
+
+ /// Returns the Induction variable.
+ PHINode *getInduction() { return Induction; }
+
+ /// Returns the reduction variables found in the loop.
+ ReductionList *getReductionVars() { return &Reductions; }
+
+ /// Returns the induction variables found in the loop.
+ InductionList *getInductionVars() { return &Inductions; }
+
+ /// Returns the widest induction type.
+ Type *getWidestInductionType() { return WidestIndTy; }
+
+ /// Returns True if V is an induction variable in this loop.
+ bool isInductionVariable(const Value *V);
+
+ /// Return true if the block BB needs to be predicated in order for the loop
+ /// to be vectorized.
+ bool blockNeedsPredication(BasicBlock *BB);
+
+ /// Check if this pointer is consecutive when vectorizing. This happens
+ /// when the last index of the GEP is the induction variable, or that the
+ /// pointer itself is an induction variable.
+ /// This check allows us to vectorize A[idx] into a wide load/store.
+ /// Returns:
+ /// 0 - Stride is unknown or non-consecutive.
+ /// 1 - Address is consecutive.
+ /// -1 - Address is consecutive, and decreasing.
+ int isConsecutivePtr(Value *Ptr);
+
+ /// Returns true if the value V is uniform within the loop.
+ bool isUniform(Value *V);
+
+ /// Returns true if this instruction will remain scalar after vectorization.
+ bool isUniformAfterVectorization(Instruction* I) { return Uniforms.count(I); }
+
+ /// Returns the information that we collected about runtime memory check.
+ const RuntimePointerChecking *getRuntimePointerChecking() const {
+ return LAI->getRuntimePointerChecking();
+ }
+
+ const LoopAccessInfo *getLAI() const {
+ return LAI;
+ }
+
+ /// \brief Check if \p Instr belongs to any interleaved access group.
+ bool isAccessInterleaved(Instruction *Instr) {
+ return InterleaveInfo.isInterleaved(Instr);
+ }
+
+ /// \brief Get the interleaved access group that \p Instr belongs to.
+ const InterleaveGroup *getInterleavedAccessGroup(Instruction *Instr) {
+ return InterleaveInfo.getInterleaveGroup(Instr);
+ }
+
+ unsigned getMaxSafeDepDistBytes() { return LAI->getMaxSafeDepDistBytes(); }
+
+ bool hasStride(Value *V) { return StrideSet.count(V); }
+ bool mustCheckStrides() { return !StrideSet.empty(); }
+ SmallPtrSet<Value *, 8>::iterator strides_begin() {
+ return StrideSet.begin();
+ }
+ SmallPtrSet<Value *, 8>::iterator strides_end() { return StrideSet.end(); }
+
+ /// Returns true if the target machine supports masked store operation
+ /// for the given \p DataType and kind of access to \p Ptr.
+ bool isLegalMaskedStore(Type *DataType, Value *Ptr) {
+ return isConsecutivePtr(Ptr) && TTI->isLegalMaskedStore(DataType);
+ }
+ /// Returns true if the target machine supports masked load operation
+ /// for the given \p DataType and kind of access to \p Ptr.
+ bool isLegalMaskedLoad(Type *DataType, Value *Ptr) {
+ return isConsecutivePtr(Ptr) && TTI->isLegalMaskedLoad(DataType);
+ }
+ /// Returns true if vector representation of the instruction \p I
+ /// requires mask.
+ bool isMaskRequired(const Instruction* I) {
+ return (MaskedOp.count(I) != 0);
+ }
+ unsigned getNumStores() const {
+ return LAI->getNumStores();
+ }
+ unsigned getNumLoads() const {
+ return LAI->getNumLoads();
+ }
+ unsigned getNumPredStores() const {
+ return NumPredStores;
+ }
+private:
+ /// Check if a single basic block loop is vectorizable.
+ /// At this point we know that this is a loop with a constant trip count
+ /// and we only need to check individual instructions.
+ bool canVectorizeInstrs();
+
+ /// When we vectorize loops we may change the order in which
+ /// we read and write from memory. This method checks if it is
+ /// legal to vectorize the code, considering only memory constrains.
+ /// Returns true if the loop is vectorizable
+ bool canVectorizeMemory();
+
+ /// Return true if we can vectorize this loop using the IF-conversion
+ /// transformation.
+ bool canVectorizeWithIfConvert();
+
+ /// Collect the variables that need to stay uniform after vectorization.
+ void collectLoopUniforms();
+
+ /// Return true if all of the instructions in the block can be speculatively
+ /// executed. \p SafePtrs is a list of addresses that are known to be legal
+ /// and we know that we can read from them without segfault.
+ bool blockCanBePredicated(BasicBlock *BB, SmallPtrSetImpl<Value *> &SafePtrs);
+
+ /// \brief Collect memory access with loop invariant strides.
+ ///
+ /// Looks for accesses like "a[i * StrideA]" where "StrideA" is loop
+ /// invariant.
+ void collectStridedAccess(Value *LoadOrStoreInst);
+
+ /// Report an analysis message to assist the user in diagnosing loops that are
+ /// not vectorized. These are handled as LoopAccessReport rather than
+ /// VectorizationReport because the << operator of VectorizationReport returns
+ /// LoopAccessReport.
+ void emitAnalysis(const LoopAccessReport &Message) const {
+ emitAnalysisDiag(TheFunction, TheLoop, *Hints, Message);
+ }
+
+ unsigned NumPredStores;
+
+ /// The loop that we evaluate.
+ Loop *TheLoop;
+ /// Scev analysis.
+ ScalarEvolution *SE;
+ /// Target Library Info.
+ TargetLibraryInfo *TLI;
+ /// Parent function
+ Function *TheFunction;
+ /// Target Transform Info
+ const TargetTransformInfo *TTI;
+ /// Dominator Tree.
+ DominatorTree *DT;
+ // LoopAccess analysis.
+ LoopAccessAnalysis *LAA;
+ // And the loop-accesses info corresponding to this loop. This pointer is
+ // null until canVectorizeMemory sets it up.
+ const LoopAccessInfo *LAI;
+
+ /// The interleave access information contains groups of interleaved accesses
+ /// with the same stride and close to each other.
+ InterleavedAccessInfo InterleaveInfo;
+
+ // --- vectorization state --- //
+
+ /// Holds the integer induction variable. This is the counter of the
+ /// loop.
+ PHINode *Induction;
+ /// Holds the reduction variables.
+ ReductionList Reductions;
+ /// Holds all of the induction variables that we found in the loop.
+ /// Notice that inductions don't need to start at zero and that induction
+ /// variables can be pointers.
+ InductionList Inductions;
+ /// Holds the widest induction type encountered.
+ Type *WidestIndTy;
+
+ /// Allowed outside users. This holds the reduction
+ /// vars which can be accessed from outside the loop.
+ SmallPtrSet<Value*, 4> AllowedExit;
+ /// This set holds the variables which are known to be uniform after
+ /// vectorization.
+ SmallPtrSet<Instruction*, 4> Uniforms;
+
+ /// Can we assume the absence of NaNs.
+ bool HasFunNoNaNAttr;
+
+ /// Vectorization requirements that will go through late-evaluation.
+ LoopVectorizationRequirements *Requirements;
+
+ /// Used to emit an analysis of any legality issues.
+ const LoopVectorizeHints *Hints;
+
+ ValueToValueMap Strides;
+ SmallPtrSet<Value *, 8> StrideSet;
+
+ /// While vectorizing these instructions we have to generate a
+ /// call to the appropriate masked intrinsic
+ SmallPtrSet<const Instruction*, 8> MaskedOp;
+};
+
+/// LoopVectorizationCostModel - estimates the expected speedups due to
+/// vectorization.
+/// In many cases vectorization is not profitable. This can happen because of
+/// a number of reasons. In this class we mainly attempt to predict the
+/// expected speedup/slowdowns due to the supported instruction set. We use the
+/// TargetTransformInfo to query the different backends for the cost of
+/// different operations.
+class LoopVectorizationCostModel {
+public:
+ LoopVectorizationCostModel(Loop *L, ScalarEvolution *SE, LoopInfo *LI,
+ LoopVectorizationLegality *Legal,
+ const TargetTransformInfo &TTI,
+ const TargetLibraryInfo *TLI, DemandedBits *DB,
+ AssumptionCache *AC,
+ const Function *F, const LoopVectorizeHints *Hints,
+ SmallPtrSetImpl<const Value *> &ValuesToIgnore)
+ : TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
+ TheFunction(F), Hints(Hints), ValuesToIgnore(ValuesToIgnore) {}
+
+ /// Information about vectorization costs
+ struct VectorizationFactor {
+ unsigned Width; // Vector width with best cost
+ unsigned Cost; // Cost of the loop with that width
+ };
+ /// \return The most profitable vectorization factor and the cost of that VF.
+ /// This method checks every power of two up to VF. If UserVF is not ZERO
+ /// then this vectorization factor will be selected if vectorization is
+ /// possible.
+ VectorizationFactor selectVectorizationFactor(bool OptForSize);
+
+ /// \return The size (in bits) of the widest type in the code that
+ /// needs to be vectorized. We ignore values that remain scalar such as
+ /// 64 bit loop indices.
+ unsigned getWidestType();
+
+ /// \return The desired interleave count.
+ /// If interleave count has been specified by metadata it will be returned.
+ /// Otherwise, the interleave count is computed and returned. VF and LoopCost
+ /// are the selected vectorization factor and the cost of the selected VF.
+ unsigned selectInterleaveCount(bool OptForSize, unsigned VF,
+ unsigned LoopCost);
+
+ /// \return The most profitable unroll factor.
+ /// This method finds the best unroll-factor based on register pressure and
+ /// other parameters. VF and LoopCost are the selected vectorization factor
+ /// and the cost of the selected VF.
+ unsigned computeInterleaveCount(bool OptForSize, unsigned VF,
+ unsigned LoopCost);
+
+ /// \brief A struct that represents some properties of the register usage
+ /// of a loop.
+ struct RegisterUsage {
+ /// Holds the number of loop invariant values that are used in the loop.
+ unsigned LoopInvariantRegs;
+ /// Holds the maximum number of concurrent live intervals in the loop.
+ unsigned MaxLocalUsers;
+ /// Holds the number of instructions in the loop.
+ unsigned NumInstructions;
+ };
+
+ /// \return information about the register usage of the loop.
+ RegisterUsage calculateRegisterUsage();
+
+private:
+ /// Returns the expected execution cost. The unit of the cost does
+ /// not matter because we use the 'cost' units to compare different
+ /// vector widths. The cost that is returned is *not* normalized by
+ /// the factor width.
+ unsigned expectedCost(unsigned VF);
+
+ /// Returns the execution time cost of an instruction for a given vector
+ /// width. Vector width of one means scalar.
+ unsigned getInstructionCost(Instruction *I, unsigned VF);
+
+ /// Returns whether the instruction is a load or store and will be a emitted
+ /// as a vector operation.
+ bool isConsecutiveLoadOrStore(Instruction *I);
+
+ /// Report an analysis message to assist the user in diagnosing loops that are
+ /// not vectorized. These are handled as LoopAccessReport rather than
+ /// VectorizationReport because the << operator of VectorizationReport returns
+ /// LoopAccessReport.
+ void emitAnalysis(const LoopAccessReport &Message) const {
+ emitAnalysisDiag(TheFunction, TheLoop, *Hints, Message);
+ }
+
+public:
+ /// Map of scalar integer values to the smallest bitwidth they can be legally
+ /// represented as. The vector equivalents of these values should be truncated
+ /// to this type.
+ DenseMap<Instruction*,uint64_t> MinBWs;
+
+ /// The loop that we evaluate.
+ Loop *TheLoop;
+ /// Scev analysis.
+ ScalarEvolution *SE;
+ /// Loop Info analysis.
+ LoopInfo *LI;
+ /// Vectorization legality.
+ LoopVectorizationLegality *Legal;
+ /// Vector target information.
+ const TargetTransformInfo &TTI;
+ /// Target Library Info.
+ const TargetLibraryInfo *TLI;
+ /// Demanded bits analysis
+ DemandedBits *DB;
+ const Function *TheFunction;
+ // Loop Vectorize Hint.
+ const LoopVectorizeHints *Hints;
+ // Values to ignore in the cost model.
+ const SmallPtrSetImpl<const Value *> &ValuesToIgnore;
+};
+
+/// \brief This holds vectorization requirements that must be verified late in
+/// the process. The requirements are set by legalize and costmodel. Once
+/// vectorization has been determined to be possible and profitable the
+/// requirements can be verified by looking for metadata or compiler options.
+/// For example, some loops require FP commutativity which is only allowed if
+/// vectorization is explicitly specified or if the fast-math compiler option
+/// has been provided.
+/// Late evaluation of these requirements allows helpful diagnostics to be
+/// composed that tells the user what need to be done to vectorize the loop. For
+/// example, by specifying #pragma clang loop vectorize or -ffast-math. Late
+/// evaluation should be used only when diagnostics can generated that can be
+/// followed by a non-expert user.
+class LoopVectorizationRequirements {
+public:
+ LoopVectorizationRequirements()
+ : NumRuntimePointerChecks(0), UnsafeAlgebraInst(nullptr) {}
- for (auto H : HintTypes)
- if (Name->getString().endswith(H.Name))
- return true;
- return false;
+ void addUnsafeAlgebraInst(Instruction *I) {
+ // First unsafe algebra instruction.
+ if (!UnsafeAlgebraInst)
+ UnsafeAlgebraInst = I;
}
- /// Sets current hints into loop metadata, keeping other values intact.
- void writeHintsToMetadata(ArrayRef<Hint> HintTypes) {
- if (HintTypes.size() == 0)
- return;
-
- // Reserve the first element to LoopID (see below).
- SmallVector<Metadata *, 4> MDs(1);
- // If the loop already has metadata, then ignore the existing operands.
- MDNode *LoopID = TheLoop->getLoopID();
- if (LoopID) {
- for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i) {
- MDNode *Node = cast<MDNode>(LoopID->getOperand(i));
- // If node in update list, ignore old value.
- if (!matchesHintMetadataName(Node, HintTypes))
- MDs.push_back(Node);
- }
+ void addRuntimePointerChecks(unsigned Num) { NumRuntimePointerChecks = Num; }
+
+ bool doesNotMeet(Function *F, Loop *L, const LoopVectorizeHints &Hints) {
+ const char *Name = Hints.vectorizeAnalysisPassName();
+ bool Failed = false;
+ if (UnsafeAlgebraInst && !Hints.allowReordering()) {
+ emitOptimizationRemarkAnalysisFPCommute(
+ F->getContext(), Name, *F, UnsafeAlgebraInst->getDebugLoc(),
+ VectorizationReport() << "cannot prove it is safe to reorder "
+ "floating-point operations");
+ Failed = true;
}
- // Now, add the missing hints.
- for (auto H : HintTypes)
- MDs.push_back(createHintMetadata(Twine(Prefix(), H.Name).str(), H.Value));
-
- // Replace current metadata node with new one.
- LLVMContext &Context = TheLoop->getHeader()->getContext();
- MDNode *NewLoopID = MDNode::get(Context, MDs);
- // Set operand 0 to refer to the loop id itself.
- NewLoopID->replaceOperandWith(0, NewLoopID);
+ // Test if runtime memcheck thresholds are exceeded.
+ bool PragmaThresholdReached =
+ NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold;
+ bool ThresholdReached =
+ NumRuntimePointerChecks > VectorizerParams::RuntimeMemoryCheckThreshold;
+ if ((ThresholdReached && !Hints.allowReordering()) ||
+ PragmaThresholdReached) {
+ emitOptimizationRemarkAnalysisAliasing(
+ F->getContext(), Name, *F, L->getStartLoc(),
+ VectorizationReport()
+ << "cannot prove it is safe to reorder memory operations");
+ DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
+ Failed = true;
+ }
- TheLoop->setLoopID(NewLoopID);
+ return Failed;
}
- /// The loop these hints belong to.
- const Loop *TheLoop;
+private:
+ unsigned NumRuntimePointerChecks;
+ Instruction *UnsafeAlgebraInst;
};
-static void emitMissedWarning(Function *F, Loop *L,
- const LoopVectorizeHints &LH) {
- emitOptimizationRemarkMissed(F->getContext(), DEBUG_TYPE, *F,
- L->getStartLoc(), LH.emitRemark());
-
- if (LH.getForce() == LoopVectorizeHints::FK_Enabled) {
- if (LH.getWidth() != 1)
- emitLoopVectorizeWarning(
- F->getContext(), *F, L->getStartLoc(),
- "failed explicitly specified loop vectorization");
- else if (LH.getInterleave() != 1)
- emitLoopInterleaveWarning(
- F->getContext(), *F, L->getStartLoc(),
- "failed explicitly specified loop interleaving");
- }
-}
-
static void addInnerLoop(Loop &L, SmallVectorImpl<Loop *> &V) {
if (L.empty())
return V.push_back(&L);
DominatorTree *DT;
BlockFrequencyInfo *BFI;
TargetLibraryInfo *TLI;
+ DemandedBits *DB;
AliasAnalysis *AA;
AssumptionCache *AC;
LoopAccessAnalysis *LAA;
BlockFrequency ColdEntryFreq;
bool runOnFunction(Function &F) override {
- SE = &getAnalysis<ScalarEvolution>();
+ SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
- BFI = &getAnalysis<BlockFrequencyInfo>();
+ BFI = &getAnalysis<BlockFrequencyInfoWrapperPass>().getBFI();
auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
TLI = TLIP ? &TLIP->getTLI() : nullptr;
- AA = &getAnalysis<AliasAnalysis>();
+ AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
LAA = &getAnalysis<LoopAccessAnalysis>();
+ DB = &getAnalysis<DemandedBits>();
// Compute some weights outside of the loop over the loops. Compute this
// using a BranchProbability to re-use its scaling math.
const BranchProbability ColdProb(1, 5); // 20%
ColdEntryFreq = BlockFrequency(BFI->getEntryFreq()) * ColdProb;
- // If the target claims to have no vector registers don't attempt
- // vectorization.
- if (!TTI->getNumberOfRegisters(true))
+ // Don't attempt if
+ // 1. the target claims to have no vector registers, and
+ // 2. interleaving won't help ILP.
+ //
+ // The second condition is necessary because, even if the target has no
+ // vector registers, loop vectorization may still enable scalar
+ // interleaving.
+ if (!TTI->getNumberOfRegisters(true) && TTI->getMaxInterleaveFactor(1) < 2)
return false;
// Build up a worklist of inner-loops to vectorize. This is necessary as
// less verbose reporting vectorized loops and unvectorized loops that may
// benefit from vectorization, respectively.
- if (Hints.getForce() == LoopVectorizeHints::FK_Disabled) {
- DEBUG(dbgs() << "LV: Not vectorizing: #pragma vectorize disable.\n");
- emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F,
- L->getStartLoc(), Hints.emitRemark());
- return false;
- }
-
- if (!AlwaysVectorize && Hints.getForce() != LoopVectorizeHints::FK_Enabled) {
- DEBUG(dbgs() << "LV: Not vectorizing: No #pragma vectorize enable.\n");
- emitOptimizationRemarkAnalysis(F->getContext(), DEBUG_TYPE, *F,
- L->getStartLoc(), Hints.emitRemark());
- return false;
- }
-
- if (Hints.getWidth() == 1 && Hints.getInterleave() == 1) {
- DEBUG(dbgs() << "LV: Not vectorizing: Disabled/already vectorized.\n");
- emitOptimizationRemarkAnalysis(
- F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- "loop not vectorized: vector width and interleave count are "
- "explicitly set to 1");
+ if (!Hints.allowVectorization(F, L, AlwaysVectorize)) {
+ DEBUG(dbgs() << "LV: Loop hints prevent vectorization.\n");
return false;
}
DEBUG(dbgs() << " But vectorizing was explicitly forced.\n");
else {
DEBUG(dbgs() << "\n");
- emitOptimizationRemarkAnalysis(
- F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- "vectorization is not beneficial and is not explicitly forced");
+ emitAnalysisDiag(F, L, Hints, VectorizationReport()
+ << "vectorization is not beneficial "
+ "and is not explicitly forced");
return false;
}
}
// Check if it is legal to vectorize the loop.
- LoopVectorizationLegality LVL(L, SE, DT, TLI, AA, F, TTI, LAA);
+ LoopVectorizationRequirements Requirements;
+ LoopVectorizationLegality LVL(L, SE, DT, TLI, AA, F, TTI, LAA,
+ &Requirements, &Hints);
if (!LVL.canVectorize()) {
DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
emitMissedWarning(F, L, Hints);
return false;
}
+ // Collect values we want to ignore in the cost model. This includes
+ // type-promoting instructions we identified during reduction detection.
+ SmallPtrSet<const Value *, 32> ValuesToIgnore;
+ CodeMetrics::collectEphemeralValues(L, AC, ValuesToIgnore);
+ for (auto &Reduction : *LVL.getReductionVars()) {
+ RecurrenceDescriptor &RedDes = Reduction.second;
+ SmallPtrSetImpl<Instruction *> &Casts = RedDes.getCastInsts();
+ ValuesToIgnore.insert(Casts.begin(), Casts.end());
+ }
+
// Use the cost model.
- LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, TLI, AC, F, &Hints);
+ LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, TLI, DB, AC, F, &Hints,
+ ValuesToIgnore);
// Check the function attributes to find out if this function should be
// optimized for size.
bool OptForSize = Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
- F->hasFnAttribute(Attribute::OptimizeForSize);
+ F->optForSize();
// Compute the weighted frequency of this loop being executed and see if it
// is less than 20% of the function entry baseline frequency. Note that we
- // always have a canonical loop here because we think we *can* vectoriez.
+ // always have a canonical loop here because we think we *can* vectorize.
// FIXME: This is hidden behind a flag due to pervasive problems with
// exactly what block frequency models.
if (LoopVectorizeWithBlockFrequency) {
OptForSize = true;
}
- // Check the function attributes to see if implicit floats are allowed.a
+ // Check the function attributes to see if implicit floats are allowed.
// FIXME: This check doesn't seem possibly correct -- what if the loop is
// an integer loop and the vector instructions selected are purely integer
// vector instructions?
if (F->hasFnAttribute(Attribute::NoImplicitFloat)) {
DEBUG(dbgs() << "LV: Can't vectorize when the NoImplicitFloat"
"attribute is used.\n");
- emitOptimizationRemarkAnalysis(
- F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- "loop not vectorized due to NoImplicitFloat attribute");
+ emitAnalysisDiag(
+ F, L, Hints,
+ VectorizationReport()
+ << "loop not vectorized due to NoImplicitFloat attribute");
emitMissedWarning(F, L, Hints);
return false;
}
const LoopVectorizationCostModel::VectorizationFactor VF =
CM.selectVectorizationFactor(OptForSize);
- // Select the unroll factor.
- const unsigned UF =
- CM.selectUnrollFactor(OptForSize, VF.Width, VF.Cost);
+ // Select the interleave count.
+ unsigned IC = CM.selectInterleaveCount(OptForSize, VF.Width, VF.Cost);
+
+ // Get user interleave count.
+ unsigned UserIC = Hints.getInterleave();
+
+ // Identify the diagnostic messages that should be produced.
+ std::string VecDiagMsg, IntDiagMsg;
+ bool VectorizeLoop = true, InterleaveLoop = true;
- DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in "
- << DebugLocStr << '\n');
- DEBUG(dbgs() << "LV: Unroll Factor is " << UF << '\n');
+ if (Requirements.doesNotMeet(F, L, Hints)) {
+ DEBUG(dbgs() << "LV: Not vectorizing: loop did not meet vectorization "
+ "requirements.\n");
+ emitMissedWarning(F, L, Hints);
+ return false;
+ }
if (VF.Width == 1) {
- DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial\n");
+ DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial.\n");
+ VecDiagMsg =
+ "the cost-model indicates that vectorization is not beneficial";
+ VectorizeLoop = false;
+ }
- if (UF == 1) {
- emitOptimizationRemarkAnalysis(
- F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- "not beneficial to vectorize and user disabled interleaving");
- return false;
- }
- DEBUG(dbgs() << "LV: Trying to at least unroll the loops.\n");
+ if (IC == 1 && UserIC <= 1) {
+ // Tell the user interleaving is not beneficial.
+ DEBUG(dbgs() << "LV: Interleaving is not beneficial.\n");
+ IntDiagMsg =
+ "the cost-model indicates that interleaving is not beneficial";
+ InterleaveLoop = false;
+ if (UserIC == 1)
+ IntDiagMsg +=
+ " and is explicitly disabled or interleave count is set to 1";
+ } else if (IC > 1 && UserIC == 1) {
+ // Tell the user interleaving is beneficial, but it explicitly disabled.
+ DEBUG(dbgs()
+ << "LV: Interleaving is beneficial but is explicitly disabled.");
+ IntDiagMsg = "the cost-model indicates that interleaving is beneficial "
+ "but is explicitly disabled or interleave count is set to 1";
+ InterleaveLoop = false;
+ }
- // Report the unrolling decision.
- emitOptimizationRemark(F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- Twine("unrolled with interleaving factor " +
- Twine(UF) +
- " (vectorization not beneficial)"));
+ // Override IC if user provided an interleave count.
+ IC = UserIC > 0 ? UserIC : IC;
+
+ // Emit diagnostic messages, if any.
+ const char *VAPassName = Hints.vectorizeAnalysisPassName();
+ if (!VectorizeLoop && !InterleaveLoop) {
+ // Do not vectorize or interleaving the loop.
+ emitOptimizationRemarkAnalysis(F->getContext(), VAPassName, *F,
+ L->getStartLoc(), VecDiagMsg);
+ emitOptimizationRemarkAnalysis(F->getContext(), LV_NAME, *F,
+ L->getStartLoc(), IntDiagMsg);
+ return false;
+ } else if (!VectorizeLoop && InterleaveLoop) {
+ DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n');
+ emitOptimizationRemarkAnalysis(F->getContext(), VAPassName, *F,
+ L->getStartLoc(), VecDiagMsg);
+ } else if (VectorizeLoop && !InterleaveLoop) {
+ DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in "
+ << DebugLocStr << '\n');
+ emitOptimizationRemarkAnalysis(F->getContext(), LV_NAME, *F,
+ L->getStartLoc(), IntDiagMsg);
+ } else if (VectorizeLoop && InterleaveLoop) {
+ DEBUG(dbgs() << "LV: Found a vectorizable loop (" << VF.Width << ") in "
+ << DebugLocStr << '\n');
+ DEBUG(dbgs() << "LV: Interleave Count is " << IC << '\n');
+ }
- // We decided not to vectorize, but we may want to unroll.
+ if (!VectorizeLoop) {
+ 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, SE, LI, DT, TLI, TTI, IC);
+ Unroller.vectorize(&LVL, CM.MinBWs);
- InnerLoopUnroller Unroller(L, SE, LI, DT, TLI, TTI, UF);
- Unroller.vectorize(&LVL);
+ emitOptimizationRemark(F->getContext(), LV_NAME, *F, L->getStartLoc(),
+ Twine("interleaved loop (interleaved count: ") +
+ Twine(IC) + ")");
} else {
// If we decided that it is *legal* to vectorize the loop then do it.
- InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, UF);
- LB.vectorize(&LVL);
+ InnerLoopVectorizer LB(L, SE, LI, DT, TLI, TTI, VF.Width, IC);
+ LB.vectorize(&LVL, CM.MinBWs);
++LoopsVectorized;
// Add metadata to disable runtime unrolling scalar loop when there's no
AddRuntimeUnrollDisableMetaData(L);
// Report the vectorization decision.
- emitOptimizationRemark(
- F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
- Twine("vectorized loop (vectorization factor: ") + Twine(VF.Width) +
- ", unrolling interleave factor: " + Twine(UF) + ")");
+ emitOptimizationRemark(F->getContext(), LV_NAME, *F, L->getStartLoc(),
+ Twine("vectorized loop (vectorization width: ") +
+ Twine(VF.Width) + ", interleaved count: " +
+ Twine(IC) + ")");
}
// Mark the loop as already vectorized to avoid vectorizing again.
AU.addRequired<AssumptionCacheTracker>();
AU.addRequiredID(LoopSimplifyID);
AU.addRequiredID(LCSSAID);
- AU.addRequired<BlockFrequencyInfo>();
+ AU.addRequired<BlockFrequencyInfoWrapperPass>();
AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<LoopInfoWrapperPass>();
- AU.addRequired<ScalarEvolution>();
+ AU.addRequired<ScalarEvolutionWrapperPass>();
AU.addRequired<TargetTransformInfoWrapperPass>();
- AU.addRequired<AliasAnalysis>();
+ AU.addRequired<AAResultsWrapperPass>();
AU.addRequired<LoopAccessAnalysis>();
+ AU.addRequired<DemandedBits>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
- AU.addPreserved<AliasAnalysis>();
+ AU.addPreserved<BasicAAWrapperPass>();
+ AU.addPreserved<AAResultsWrapperPass>();
+ AU.addPreserved<GlobalsAAWrapperPass>();
}
};
return Builder.CreateAdd(Val, Step, "induction");
}
-/// \brief Find the operand of the GEP that should be checked for consecutive
-/// stores. This ignores trailing indices that have no effect on the final
-/// pointer.
-static unsigned getGEPInductionOperand(const GetElementPtrInst *Gep) {
- const DataLayout &DL = Gep->getModule()->getDataLayout();
- unsigned LastOperand = Gep->getNumOperands() - 1;
- unsigned GEPAllocSize = DL.getTypeAllocSize(
- cast<PointerType>(Gep->getType()->getScalarType())->getElementType());
-
- // Walk backwards and try to peel off zeros.
- while (LastOperand > 1 && match(Gep->getOperand(LastOperand), m_Zero())) {
- // Find the type we're currently indexing into.
- gep_type_iterator GEPTI = gep_type_begin(Gep);
- std::advance(GEPTI, LastOperand - 1);
-
- // If it's a type with the same allocation size as the result of the GEP we
- // can peel off the zero index.
- if (DL.getTypeAllocSize(*GEPTI) != GEPAllocSize)
- break;
- --LastOperand;
- }
-
- return LastOperand;
-}
-
int LoopVectorizationLegality::isConsecutivePtr(Value *Ptr) {
assert(Ptr->getType()->isPointerTy() && "Unexpected non-ptr");
// Make sure that the pointer does not point to structs.
// If this value is a pointer induction variable we know it is consecutive.
PHINode *Phi = dyn_cast_or_null<PHINode>(Ptr);
if (Phi && Inductions.count(Phi)) {
- InductionInfo II = Inductions[Phi];
+ InductionDescriptor II = Inductions[Phi];
return II.getConsecutiveDirection();
}
if (!SE->isLoopInvariant(SE->getSCEV(Gep->getOperand(i)), TheLoop))
return 0;
- InductionInfo II = Inductions[Phi];
+ InductionDescriptor II = Inductions[Phi];
return II.getConsecutiveDirection();
}
// If this scalar is unknown, assume that it is a constant or that it is
// loop invariant. Broadcast V and save the value for future uses.
Value *B = getBroadcastInstrs(V);
+
return WidenMap.splat(V, B);
}
"reverse");
}
+// Get a mask to interleave \p NumVec vectors into a wide vector.
+// I.e. <0, VF, VF*2, ..., VF*(NumVec-1), 1, VF+1, VF*2+1, ...>
+// E.g. For 2 interleaved vectors, if VF is 4, the mask is:
+// <0, 4, 1, 5, 2, 6, 3, 7>
+static Constant *getInterleavedMask(IRBuilder<> &Builder, unsigned VF,
+ unsigned NumVec) {
+ SmallVector<Constant *, 16> Mask;
+ for (unsigned i = 0; i < VF; i++)
+ for (unsigned j = 0; j < NumVec; j++)
+ Mask.push_back(Builder.getInt32(j * VF + i));
+
+ return ConstantVector::get(Mask);
+}
+
+// Get the strided mask starting from index \p Start.
+// I.e. <Start, Start + Stride, ..., Start + Stride*(VF-1)>
+static Constant *getStridedMask(IRBuilder<> &Builder, unsigned Start,
+ unsigned Stride, unsigned VF) {
+ SmallVector<Constant *, 16> Mask;
+ for (unsigned i = 0; i < VF; i++)
+ Mask.push_back(Builder.getInt32(Start + i * Stride));
+
+ return ConstantVector::get(Mask);
+}
+
+// Get a mask of two parts: The first part consists of sequential integers
+// starting from 0, The second part consists of UNDEFs.
+// I.e. <0, 1, 2, ..., NumInt - 1, undef, ..., undef>
+static Constant *getSequentialMask(IRBuilder<> &Builder, unsigned NumInt,
+ unsigned NumUndef) {
+ SmallVector<Constant *, 16> Mask;
+ for (unsigned i = 0; i < NumInt; i++)
+ Mask.push_back(Builder.getInt32(i));
+
+ Constant *Undef = UndefValue::get(Builder.getInt32Ty());
+ for (unsigned i = 0; i < NumUndef; i++)
+ Mask.push_back(Undef);
+
+ return ConstantVector::get(Mask);
+}
+
+// Concatenate two vectors with the same element type. The 2nd vector should
+// not have more elements than the 1st vector. If the 2nd vector has less
+// elements, extend it with UNDEFs.
+static Value *ConcatenateTwoVectors(IRBuilder<> &Builder, Value *V1,
+ Value *V2) {
+ VectorType *VecTy1 = dyn_cast<VectorType>(V1->getType());
+ VectorType *VecTy2 = dyn_cast<VectorType>(V2->getType());
+ assert(VecTy1 && VecTy2 &&
+ VecTy1->getScalarType() == VecTy2->getScalarType() &&
+ "Expect two vectors with the same element type");
+
+ unsigned NumElts1 = VecTy1->getNumElements();
+ unsigned NumElts2 = VecTy2->getNumElements();
+ assert(NumElts1 >= NumElts2 && "Unexpect the first vector has less elements");
+
+ if (NumElts1 > NumElts2) {
+ // Extend with UNDEFs.
+ Constant *ExtMask =
+ getSequentialMask(Builder, NumElts2, NumElts1 - NumElts2);
+ V2 = Builder.CreateShuffleVector(V2, UndefValue::get(VecTy2), ExtMask);
+ }
+
+ Constant *Mask = getSequentialMask(Builder, NumElts1 + NumElts2, 0);
+ return Builder.CreateShuffleVector(V1, V2, Mask);
+}
+
+// Concatenate vectors in the given list. All vectors have the same type.
+static Value *ConcatenateVectors(IRBuilder<> &Builder,
+ ArrayRef<Value *> InputList) {
+ unsigned NumVec = InputList.size();
+ assert(NumVec > 1 && "Should be at least two vectors");
+
+ SmallVector<Value *, 8> ResList;
+ ResList.append(InputList.begin(), InputList.end());
+ do {
+ SmallVector<Value *, 8> TmpList;
+ for (unsigned i = 0; i < NumVec - 1; i += 2) {
+ Value *V0 = ResList[i], *V1 = ResList[i + 1];
+ assert((V0->getType() == V1->getType() || i == NumVec - 2) &&
+ "Only the last vector may have a different type");
+
+ TmpList.push_back(ConcatenateTwoVectors(Builder, V0, V1));
+ }
+
+ // Push the last vector if the total number of vectors is odd.
+ if (NumVec % 2 != 0)
+ TmpList.push_back(ResList[NumVec - 1]);
+
+ ResList = TmpList;
+ NumVec = ResList.size();
+ } while (NumVec > 1);
+
+ return ResList[0];
+}
+
+// Try to vectorize the interleave group that \p Instr belongs to.
+//
+// E.g. Translate following interleaved load group (factor = 3):
+// for (i = 0; i < N; i+=3) {
+// R = Pic[i]; // Member of index 0
+// G = Pic[i+1]; // Member of index 1
+// B = Pic[i+2]; // Member of index 2
+// ... // do something to R, G, B
+// }
+// To:
+// %wide.vec = load <12 x i32> ; Read 4 tuples of R,G,B
+// %R.vec = shuffle %wide.vec, undef, <0, 3, 6, 9> ; R elements
+// %G.vec = shuffle %wide.vec, undef, <1, 4, 7, 10> ; G elements
+// %B.vec = shuffle %wide.vec, undef, <2, 5, 8, 11> ; B elements
+//
+// Or translate following interleaved store group (factor = 3):
+// for (i = 0; i < N; i+=3) {
+// ... do something to R, G, B
+// Pic[i] = R; // Member of index 0
+// Pic[i+1] = G; // Member of index 1
+// Pic[i+2] = B; // Member of index 2
+// }
+// To:
+// %R_G.vec = shuffle %R.vec, %G.vec, <0, 1, 2, ..., 7>
+// %B_U.vec = shuffle %B.vec, undef, <0, 1, 2, 3, u, u, u, u>
+// %interleaved.vec = shuffle %R_G.vec, %B_U.vec,
+// <0, 4, 8, 1, 5, 9, 2, 6, 10, 3, 7, 11> ; Interleave R,G,B elements
+// store <12 x i32> %interleaved.vec ; Write 4 tuples of R,G,B
+void InnerLoopVectorizer::vectorizeInterleaveGroup(Instruction *Instr) {
+ const InterleaveGroup *Group = Legal->getInterleavedAccessGroup(Instr);
+ assert(Group && "Fail to get an interleaved access group.");
+
+ // Skip if current instruction is not the insert position.
+ if (Instr != Group->getInsertPos())
+ return;
+
+ LoadInst *LI = dyn_cast<LoadInst>(Instr);
+ StoreInst *SI = dyn_cast<StoreInst>(Instr);
+ Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
+
+ // Prepare for the vector type of the interleaved load/store.
+ Type *ScalarTy = LI ? LI->getType() : SI->getValueOperand()->getType();
+ unsigned InterleaveFactor = Group->getFactor();
+ Type *VecTy = VectorType::get(ScalarTy, InterleaveFactor * VF);
+ Type *PtrTy = VecTy->getPointerTo(Ptr->getType()->getPointerAddressSpace());
+
+ // Prepare for the new pointers.
+ setDebugLocFromInst(Builder, Ptr);
+ VectorParts &PtrParts = getVectorValue(Ptr);
+ SmallVector<Value *, 2> NewPtrs;
+ unsigned Index = Group->getIndex(Instr);
+ for (unsigned Part = 0; Part < UF; Part++) {
+ // Extract the pointer for current instruction from the pointer vector. A
+ // reverse access uses the pointer in the last lane.
+ Value *NewPtr = Builder.CreateExtractElement(
+ PtrParts[Part],
+ Group->isReverse() ? Builder.getInt32(VF - 1) : Builder.getInt32(0));
+
+ // Notice current instruction could be any index. Need to adjust the address
+ // to the member of index 0.
+ //
+ // E.g. a = A[i+1]; // Member of index 1 (Current instruction)
+ // b = A[i]; // Member of index 0
+ // Current pointer is pointed to A[i+1], adjust it to A[i].
+ //
+ // E.g. A[i+1] = a; // Member of index 1
+ // A[i] = b; // Member of index 0
+ // A[i+2] = c; // Member of index 2 (Current instruction)
+ // Current pointer is pointed to A[i+2], adjust it to A[i].
+ NewPtr = Builder.CreateGEP(NewPtr, Builder.getInt32(-Index));
+
+ // Cast to the vector pointer type.
+ NewPtrs.push_back(Builder.CreateBitCast(NewPtr, PtrTy));
+ }
+
+ setDebugLocFromInst(Builder, Instr);
+ Value *UndefVec = UndefValue::get(VecTy);
+
+ // Vectorize the interleaved load group.
+ if (LI) {
+ for (unsigned Part = 0; Part < UF; Part++) {
+ Instruction *NewLoadInstr = Builder.CreateAlignedLoad(
+ NewPtrs[Part], Group->getAlignment(), "wide.vec");
+
+ for (unsigned i = 0; i < InterleaveFactor; i++) {
+ Instruction *Member = Group->getMember(i);
+
+ // Skip the gaps in the group.
+ if (!Member)
+ continue;
+
+ Constant *StrideMask = getStridedMask(Builder, i, InterleaveFactor, VF);
+ Value *StridedVec = Builder.CreateShuffleVector(
+ NewLoadInstr, UndefVec, StrideMask, "strided.vec");
+
+ // If this member has different type, cast the result type.
+ if (Member->getType() != ScalarTy) {
+ VectorType *OtherVTy = VectorType::get(Member->getType(), VF);
+ StridedVec = Builder.CreateBitOrPointerCast(StridedVec, OtherVTy);
+ }
+
+ VectorParts &Entry = WidenMap.get(Member);
+ Entry[Part] =
+ Group->isReverse() ? reverseVector(StridedVec) : StridedVec;
+ }
+
+ propagateMetadata(NewLoadInstr, Instr);
+ }
+ return;
+ }
+
+ // The sub vector type for current instruction.
+ VectorType *SubVT = VectorType::get(ScalarTy, VF);
+
+ // Vectorize the interleaved store group.
+ for (unsigned Part = 0; Part < UF; Part++) {
+ // Collect the stored vector from each member.
+ SmallVector<Value *, 4> StoredVecs;
+ for (unsigned i = 0; i < InterleaveFactor; i++) {
+ // Interleaved store group doesn't allow a gap, so each index has a member
+ Instruction *Member = Group->getMember(i);
+ assert(Member && "Fail to get a member from an interleaved store group");
+
+ Value *StoredVec =
+ getVectorValue(dyn_cast<StoreInst>(Member)->getValueOperand())[Part];
+ if (Group->isReverse())
+ StoredVec = reverseVector(StoredVec);
+
+ // If this member has different type, cast it to an unified type.
+ if (StoredVec->getType() != SubVT)
+ StoredVec = Builder.CreateBitOrPointerCast(StoredVec, SubVT);
+
+ StoredVecs.push_back(StoredVec);
+ }
+
+ // Concatenate all vectors into a wide vector.
+ Value *WideVec = ConcatenateVectors(Builder, StoredVecs);
+
+ // Interleave the elements in the wide vector.
+ Constant *IMask = getInterleavedMask(Builder, VF, InterleaveFactor);
+ Value *IVec = Builder.CreateShuffleVector(WideVec, UndefVec, IMask,
+ "interleaved.vec");
+
+ Instruction *NewStoreInstr =
+ Builder.CreateAlignedStore(IVec, NewPtrs[Part], Group->getAlignment());
+ propagateMetadata(NewStoreInstr, Instr);
+ }
+}
+
void InnerLoopVectorizer::vectorizeMemoryInstruction(Instruction *Instr) {
// Attempt to issue a wide load.
LoadInst *LI = dyn_cast<LoadInst>(Instr);
assert((LI || SI) && "Invalid Load/Store instruction");
+ // Try to vectorize the interleave group if this access is interleaved.
+ if (Legal->isAccessInterleaved(Instr))
+ return vectorizeInterleaveGroup(Instr);
+
Type *ScalarDataTy = LI ? LI->getType() : SI->getValueOperand()->getType();
Type *DataTy = VectorType::get(ScalarDataTy, VF);
Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
// We don't want to update the value in the map as it might be used in
// another expression. So don't use a reference type for "StoredVal".
VectorParts StoredVal = getVectorValue(SI->getValueOperand());
-
+
for (unsigned Part = 0; Part < UF; ++Part) {
// Calculate the pointer for the specific unroll-part.
Value *PartPtr =
Builder.CreateGEP(nullptr, Ptr, Builder.getInt32(Part * VF));
if (Reverse) {
- // If we store to reverse consecutive memory locations then we need
+ // If we store to reverse consecutive memory locations, then we need
// to reverse the order of elements in the stored value.
StoredVal[Part] = reverseVector(StoredVal[Part]);
// If the address is consecutive but reversed, then the
// Try using previously calculated values.
Instruction *SrcInst = dyn_cast<Instruction>(SrcOp);
- // If the src is an instruction that appeared earlier in the basic block
+ // If the src is an instruction that appeared earlier in the basic block,
// then it should already be vectorized.
if (SrcInst && OrigLoop->contains(SrcInst)) {
assert(WidenMap.has(SrcInst) && "Source operand is unavailable");
// Create a new entry in the WidenMap and initialize it to Undef or Null.
VectorParts &VecResults = WidenMap.splat(Instr, UndefVec);
- Instruction *InsertPt = Builder.GetInsertPoint();
- BasicBlock *IfBlock = Builder.GetInsertBlock();
- BasicBlock *CondBlock = nullptr;
-
VectorParts Cond;
- Loop *VectorLp = nullptr;
if (IfPredicateStore) {
assert(Instr->getParent()->getSinglePredecessor() &&
"Only support single predecessor blocks");
Cond = createEdgeMask(Instr->getParent()->getSinglePredecessor(),
Instr->getParent());
- VectorLp = LI->getLoopFor(IfBlock);
- assert(VectorLp && "Must have a loop for this block");
}
// For each vector unroll 'part':
if (IfPredicateStore) {
Cmp = Builder.CreateExtractElement(Cond[Part], Builder.getInt32(Width));
Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Cmp, ConstantInt::get(Cmp->getType(), 1));
- CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
- LoopVectorBody.push_back(CondBlock);
- VectorLp->addBasicBlockToLoop(CondBlock, *LI);
- // Update Builder with newly created basic block.
- Builder.SetInsertPoint(InsertPt);
}
Instruction *Cloned = Instr->clone();
VecResults[Part] = Builder.CreateInsertElement(VecResults[Part], Cloned,
Builder.getInt32(Width));
// End if-block.
- if (IfPredicateStore) {
- BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
- LoopVectorBody.push_back(NewIfBlock);
- VectorLp->addBasicBlockToLoop(NewIfBlock, *LI);
- Builder.SetInsertPoint(InsertPt);
- Instruction *OldBr = IfBlock->getTerminator();
- BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
- OldBr->eraseFromParent();
- IfBlock = NewIfBlock;
- }
+ if (IfPredicateStore)
+ PredicatedStores.push_back(std::make_pair(cast<StoreInst>(Cloned),
+ Cmp));
}
}
}
return std::make_pair(FirstInst, TheCheck);
}
-void InnerLoopVectorizer::createEmptyLoop() {
- /*
- In this function we generate a new loop. The new loop will contain
- the vectorized instructions while the old loop will continue to run the
- scalar remainder.
+PHINode *InnerLoopVectorizer::createInductionVariable(Loop *L,
+ Value *Start,
+ Value *End,
+ Value *Step,
+ Instruction *DL) {
+ BasicBlock *Header = L->getHeader();
+ BasicBlock *Latch = L->getLoopLatch();
+ // As we're just creating this loop, it's possible no latch exists
+ // yet. If so, use the header as this will be a single block loop.
+ if (!Latch)
+ Latch = Header;
+
+ IRBuilder<> Builder(&*Header->getFirstInsertionPt());
+ setDebugLocFromInst(Builder, getDebugLocFromInstOrOperands(OldInduction));
+ auto *Induction = Builder.CreatePHI(Start->getType(), 2, "index");
- [ ] <-- Back-edge taken count overflow check.
- / |
- / v
- | [ ] <-- vector loop bypass (may consist of multiple blocks).
- | / |
- | / v
- || [ ] <-- vector pre header.
- || |
- || v
- || [ ] \
- || [ ]_| <-- vector loop.
- || |
- | \ v
- | >[ ] <--- middle-block.
- | / |
- | / v
- -|- >[ ] <--- new preheader.
- | |
- | v
- | [ ] \
- | [ ]_| <-- old scalar loop to handle remainder.
- \ |
- \ v
- >[ ] <-- exit block.
- ...
- */
+ Builder.SetInsertPoint(Latch->getTerminator());
+
+ // Create i+1 and fill the PHINode.
+ Value *Next = Builder.CreateAdd(Induction, Step, "index.next");
+ Induction->addIncoming(Start, L->getLoopPreheader());
+ Induction->addIncoming(Next, Latch);
+ // Create the compare.
+ Value *ICmp = Builder.CreateICmpEQ(Next, End);
+ Builder.CreateCondBr(ICmp, L->getExitBlock(), Header);
+
+ // Now we have two terminators. Remove the old one from the block.
+ Latch->getTerminator()->eraseFromParent();
- BasicBlock *OldBasicBlock = OrigLoop->getHeader();
- BasicBlock *BypassBlock = OrigLoop->getLoopPreheader();
- BasicBlock *ExitBlock = OrigLoop->getExitBlock();
- assert(BypassBlock && "Invalid loop structure");
- assert(ExitBlock && "Must have an exit block");
+ return Induction;
+}
- // Some loops have a single integer induction variable, while other loops
- // don't. One example is c++ iterators that often have multiple pointer
- // induction variables. In the code below we also support a case where we
- // don't have a single induction variable.
- OldInduction = Legal->getInduction();
- Type *IdxTy = Legal->getWidestInductionType();
+Value *InnerLoopVectorizer::getOrCreateTripCount(Loop *L) {
+ if (TripCount)
+ return TripCount;
+ IRBuilder<> Builder(L->getLoopPreheader()->getTerminator());
// Find the loop boundaries.
- const SCEV *ExitCount = SE->getBackedgeTakenCount(OrigLoop);
- assert(ExitCount != SE->getCouldNotCompute() && "Invalid loop count");
+ const SCEV *BackedgeTakenCount = SE->getBackedgeTakenCount(OrigLoop);
+ assert(BackedgeTakenCount != SE->getCouldNotCompute() && "Invalid loop count");
+ Type *IdxTy = Legal->getWidestInductionType();
+
// The exit count might have the type of i64 while the phi is i32. This can
// happen if we have an induction variable that is sign extended before the
// compare. The only way that we get a backedge taken count is that the
// induction variable was signed and as such will not overflow. In such a case
// truncation is legal.
- if (ExitCount->getType()->getPrimitiveSizeInBits() >
+ if (BackedgeTakenCount->getType()->getPrimitiveSizeInBits() >
IdxTy->getPrimitiveSizeInBits())
- ExitCount = SE->getTruncateOrNoop(ExitCount, IdxTy);
-
- const SCEV *BackedgeTakeCount = SE->getNoopOrZeroExtend(ExitCount, IdxTy);
+ BackedgeTakenCount = SE->getTruncateOrNoop(BackedgeTakenCount, IdxTy);
+ BackedgeTakenCount = SE->getNoopOrZeroExtend(BackedgeTakenCount, IdxTy);
+
// Get the total trip count from the count by adding 1.
- ExitCount = SE->getAddExpr(BackedgeTakeCount,
- SE->getConstant(BackedgeTakeCount->getType(), 1));
+ const SCEV *ExitCount = SE->getAddExpr(
+ BackedgeTakenCount, SE->getOne(BackedgeTakenCount->getType()));
- const DataLayout &DL = OldBasicBlock->getModule()->getDataLayout();
+ const DataLayout &DL = L->getHeader()->getModule()->getDataLayout();
// Expand the trip count and place the new instructions in the preheader.
// Notice that the pre-header does not change, only the loop body.
SCEVExpander Exp(*SE, DL, "induction");
- // We need to test whether the backedge-taken count is uint##_max. Adding one
- // to it will cause overflow and an incorrect loop trip count in the vector
- // body. In case of overflow we want to directly jump to the scalar remainder
- // loop.
- Value *BackedgeCount =
- Exp.expandCodeFor(BackedgeTakeCount, BackedgeTakeCount->getType(),
- BypassBlock->getTerminator());
- if (BackedgeCount->getType()->isPointerTy())
- BackedgeCount = CastInst::CreatePointerCast(BackedgeCount, IdxTy,
- "backedge.ptrcnt.to.int",
- BypassBlock->getTerminator());
- Instruction *CheckBCOverflow =
- CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, BackedgeCount,
- Constant::getAllOnesValue(BackedgeCount->getType()),
- "backedge.overflow", BypassBlock->getTerminator());
-
- // The loop index does not have to start at Zero. Find the original start
- // value from the induction PHI node. If we don't have an induction variable
- // then we know that it starts at zero.
- Builder.SetInsertPoint(BypassBlock->getTerminator());
- Value *StartIdx = ExtendedIdx = OldInduction ?
- Builder.CreateZExt(OldInduction->getIncomingValueForBlock(BypassBlock),
- IdxTy):
- ConstantInt::get(IdxTy, 0);
-
- // We need an instruction to anchor the overflow check on. StartIdx needs to
- // be defined before the overflow check branch. Because the scalar preheader
- // is going to merge the start index and so the overflow branch block needs to
- // contain a definition of the start index.
- Instruction *OverflowCheckAnchor = BinaryOperator::CreateAdd(
- StartIdx, ConstantInt::get(IdxTy, 0), "overflow.check.anchor",
- BypassBlock->getTerminator());
+ // Count holds the overall loop count (N).
+ TripCount = Exp.expandCodeFor(ExitCount, ExitCount->getType(),
+ L->getLoopPreheader()->getTerminator());
+
+ if (TripCount->getType()->isPointerTy())
+ TripCount =
+ CastInst::CreatePointerCast(TripCount, IdxTy,
+ "exitcount.ptrcnt.to.int",
+ L->getLoopPreheader()->getTerminator());
+
+ return TripCount;
+}
+
+Value *InnerLoopVectorizer::getOrCreateVectorTripCount(Loop *L) {
+ if (VectorTripCount)
+ return VectorTripCount;
+
+ Value *TC = getOrCreateTripCount(L);
+ IRBuilder<> Builder(L->getLoopPreheader()->getTerminator());
+
+ // Now we need to generate the expression for N - (N % VF), which is
+ // the part that the vectorized body will execute.
+ // The loop step is equal to the vectorization factor (num of SIMD elements)
+ // times the unroll factor (num of SIMD instructions).
+ Constant *Step = ConstantInt::get(TC->getType(), VF * UF);
+ Value *R = Builder.CreateURem(TC, Step, "n.mod.vf");
+ VectorTripCount = Builder.CreateSub(TC, R, "n.vec");
+
+ return VectorTripCount;
+}
+
+void InnerLoopVectorizer::emitMinimumIterationCountCheck(Loop *L,
+ BasicBlock *Bypass) {
+ Value *Count = getOrCreateTripCount(L);
+ BasicBlock *BB = L->getLoopPreheader();
+ IRBuilder<> Builder(BB->getTerminator());
+
+ // Generate code to check that the loop's trip count that we computed by
+ // adding one to the backedge-taken count will not overflow.
+ Value *CheckMinIters =
+ Builder.CreateICmpULT(Count,
+ ConstantInt::get(Count->getType(), VF * UF),
+ "min.iters.check");
+
+ BasicBlock *NewBB = BB->splitBasicBlock(BB->getTerminator(),
+ "min.iters.checked");
+ if (L->getParentLoop())
+ L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
+ ReplaceInstWithInst(BB->getTerminator(),
+ BranchInst::Create(Bypass, NewBB, CheckMinIters));
+ LoopBypassBlocks.push_back(BB);
+}
+
+void InnerLoopVectorizer::emitVectorLoopEnteredCheck(Loop *L,
+ BasicBlock *Bypass) {
+ Value *TC = getOrCreateVectorTripCount(L);
+ BasicBlock *BB = L->getLoopPreheader();
+ IRBuilder<> Builder(BB->getTerminator());
+
+ // Now, compare the new count to zero. If it is zero skip the vector loop and
+ // jump to the scalar loop.
+ Value *Cmp = Builder.CreateICmpEQ(TC, Constant::getNullValue(TC->getType()),
+ "cmp.zero");
+
+ // Generate code to check that the loop's trip count that we computed by
+ // adding one to the backedge-taken count will not overflow.
+ BasicBlock *NewBB = BB->splitBasicBlock(BB->getTerminator(),
+ "vector.ph");
+ if (L->getParentLoop())
+ L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
+ ReplaceInstWithInst(BB->getTerminator(),
+ BranchInst::Create(Bypass, NewBB, Cmp));
+ LoopBypassBlocks.push_back(BB);
+}
+
+void InnerLoopVectorizer::emitStrideChecks(Loop *L,
+ BasicBlock *Bypass) {
+ BasicBlock *BB = L->getLoopPreheader();
+
+ // Generate the code to check that the strides we assumed to be one are really
+ // one. We want the new basic block to start at the first instruction in a
+ // sequence of instructions that form a check.
+ Instruction *StrideCheck;
+ Instruction *FirstCheckInst;
+ std::tie(FirstCheckInst, StrideCheck) = addStrideCheck(BB->getTerminator());
+ if (!StrideCheck)
+ return;
+
+ // Create a new block containing the stride check.
+ BB->setName("vector.stridecheck");
+ auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
+ if (L->getParentLoop())
+ L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
+ ReplaceInstWithInst(BB->getTerminator(),
+ BranchInst::Create(Bypass, NewBB, StrideCheck));
+ LoopBypassBlocks.push_back(BB);
+ AddedSafetyChecks = true;
+}
+
+void InnerLoopVectorizer::emitMemRuntimeChecks(Loop *L,
+ BasicBlock *Bypass) {
+ BasicBlock *BB = L->getLoopPreheader();
+
+ // Generate the code that checks in runtime if arrays overlap. We put the
+ // checks into a separate block to make the more common case of few elements
+ // faster.
+ Instruction *FirstCheckInst;
+ Instruction *MemRuntimeCheck;
+ std::tie(FirstCheckInst, MemRuntimeCheck) =
+ Legal->getLAI()->addRuntimeChecks(BB->getTerminator());
+ if (!MemRuntimeCheck)
+ return;
+
+ // Create a new block containing the memory check.
+ BB->setName("vector.memcheck");
+ auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
+ if (L->getParentLoop())
+ L->getParentLoop()->addBasicBlockToLoop(NewBB, *LI);
+ ReplaceInstWithInst(BB->getTerminator(),
+ BranchInst::Create(Bypass, NewBB, MemRuntimeCheck));
+ LoopBypassBlocks.push_back(BB);
+ AddedSafetyChecks = true;
+}
+
+
+void InnerLoopVectorizer::createEmptyLoop() {
+ /*
+ In this function we generate a new loop. The new loop will contain
+ the vectorized instructions while the old loop will continue to run the
+ scalar remainder.
+
+ [ ] <-- loop iteration number check.
+ / |
+ / v
+ | [ ] <-- vector loop bypass (may consist of multiple blocks).
+ | / |
+ | / v
+ || [ ] <-- vector pre header.
+ |/ |
+ | v
+ | [ ] \
+ | [ ]_| <-- vector loop.
+ | |
+ | v
+ | -[ ] <--- middle-block.
+ | / |
+ | / v
+ -|- >[ ] <--- new preheader.
+ | |
+ | v
+ | [ ] \
+ | [ ]_| <-- old scalar loop to handle remainder.
+ \ |
+ \ v
+ >[ ] <-- exit block.
+ ...
+ */
- // Count holds the overall loop count (N).
- Value *Count = Exp.expandCodeFor(ExitCount, ExitCount->getType(),
- BypassBlock->getTerminator());
+ BasicBlock *OldBasicBlock = OrigLoop->getHeader();
+ BasicBlock *VectorPH = OrigLoop->getLoopPreheader();
+ BasicBlock *ExitBlock = OrigLoop->getExitBlock();
+ assert(VectorPH && "Invalid loop structure");
+ assert(ExitBlock && "Must have an exit block");
- LoopBypassBlocks.push_back(BypassBlock);
+ // Some loops have a single integer induction variable, while other loops
+ // don't. One example is c++ iterators that often have multiple pointer
+ // induction variables. In the code below we also support a case where we
+ // don't have a single induction variable.
+ //
+ // We try to obtain an induction variable from the original loop as hard
+ // as possible. However if we don't find one that:
+ // - is an integer
+ // - counts from zero, stepping by one
+ // - is the size of the widest induction variable type
+ // then we create a new one.
+ OldInduction = Legal->getInduction();
+ Type *IdxTy = Legal->getWidestInductionType();
// Split the single block loop into the two loop structure described above.
- BasicBlock *VectorPH =
- BypassBlock->splitBasicBlock(BypassBlock->getTerminator(), "vector.ph");
BasicBlock *VecBody =
- VectorPH->splitBasicBlock(VectorPH->getTerminator(), "vector.body");
+ VectorPH->splitBasicBlock(VectorPH->getTerminator(), "vector.body");
BasicBlock *MiddleBlock =
VecBody->splitBasicBlock(VecBody->getTerminator(), "middle.block");
BasicBlock *ScalarPH =
if (ParentLoop) {
ParentLoop->addChildLoop(Lp);
ParentLoop->addBasicBlockToLoop(ScalarPH, *LI);
- ParentLoop->addBasicBlockToLoop(VectorPH, *LI);
ParentLoop->addBasicBlockToLoop(MiddleBlock, *LI);
} else {
LI->addTopLevelLoop(Lp);
}
Lp->addBasicBlockToLoop(VecBody, *LI);
- // Use this IR builder to create the loop instructions (Phi, Br, Cmp)
- // inside the loop.
- Builder.SetInsertPoint(VecBody->getFirstNonPHI());
-
- // Generate the induction variable.
- setDebugLocFromInst(Builder, getDebugLocFromInstOrOperands(OldInduction));
- Induction = Builder.CreatePHI(IdxTy, 2, "index");
- // The loop step is equal to the vectorization factor (num of SIMD elements)
- // times the unroll factor (num of SIMD instructions).
- Constant *Step = ConstantInt::get(IdxTy, VF * UF);
-
- // This is the IR builder that we use to add all of the logic for bypassing
- // the new vector loop.
- IRBuilder<> BypassBuilder(BypassBlock->getTerminator());
- setDebugLocFromInst(BypassBuilder,
- getDebugLocFromInstOrOperands(OldInduction));
-
- // We may need to extend the index in case there is a type mismatch.
- // We know that the count starts at zero and does not overflow.
- if (Count->getType() != IdxTy) {
- // The exit count can be of pointer type. Convert it to the correct
- // integer type.
- if (ExitCount->getType()->isPointerTy())
- Count = BypassBuilder.CreatePointerCast(Count, IdxTy, "ptrcnt.to.int");
- else
- Count = BypassBuilder.CreateZExtOrTrunc(Count, IdxTy, "cnt.cast");
- }
-
- // Add the start index to the loop count to get the new end index.
- Value *IdxEnd = BypassBuilder.CreateAdd(Count, StartIdx, "end.idx");
+ // Find the loop boundaries.
+ Value *Count = getOrCreateTripCount(Lp);
- // Now we need to generate the expression for N - (N % VF), which is
- // the part that the vectorized body will execute.
- Value *R = BypassBuilder.CreateURem(Count, Step, "n.mod.vf");
- Value *CountRoundDown = BypassBuilder.CreateSub(Count, R, "n.vec");
- Value *IdxEndRoundDown = BypassBuilder.CreateAdd(CountRoundDown, StartIdx,
- "end.idx.rnd.down");
+ Value *StartIdx = ConstantInt::get(IdxTy, 0);
+ // We need to test whether the backedge-taken count is uint##_max. Adding one
+ // to it will cause overflow and an incorrect loop trip count in the vector
+ // body. In case of overflow we want to directly jump to the scalar remainder
+ // loop.
+ emitMinimumIterationCountCheck(Lp, ScalarPH);
// Now, compare the new count to zero. If it is zero skip the vector loop and
// jump to the scalar loop.
- Value *Cmp =
- BypassBuilder.CreateICmpEQ(IdxEndRoundDown, StartIdx, "cmp.zero");
-
- BasicBlock *LastBypassBlock = BypassBlock;
-
- // Generate code to check that the loops trip count that we computed by adding
- // one to the backedge-taken count will not overflow.
- {
- auto PastOverflowCheck =
- std::next(BasicBlock::iterator(OverflowCheckAnchor));
- BasicBlock *CheckBlock =
- LastBypassBlock->splitBasicBlock(PastOverflowCheck, "overflow.checked");
- if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
- LoopBypassBlocks.push_back(CheckBlock);
- Instruction *OldTerm = LastBypassBlock->getTerminator();
- BranchInst::Create(ScalarPH, CheckBlock, CheckBCOverflow, OldTerm);
- OldTerm->eraseFromParent();
- LastBypassBlock = CheckBlock;
- }
-
+ emitVectorLoopEnteredCheck(Lp, ScalarPH);
// Generate the code to check that the strides we assumed to be one are really
// one. We want the new basic block to start at the first instruction in a
// sequence of instructions that form a check.
- Instruction *StrideCheck;
- Instruction *FirstCheckInst;
- std::tie(FirstCheckInst, StrideCheck) =
- addStrideCheck(LastBypassBlock->getTerminator());
- if (StrideCheck) {
- AddedSafetyChecks = true;
- // Create a new block containing the stride check.
- BasicBlock *CheckBlock =
- LastBypassBlock->splitBasicBlock(FirstCheckInst, "vector.stridecheck");
- if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
- LoopBypassBlocks.push_back(CheckBlock);
-
- // Replace the branch into the memory check block with a conditional branch
- // for the "few elements case".
- Instruction *OldTerm = LastBypassBlock->getTerminator();
- BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm);
- OldTerm->eraseFromParent();
-
- Cmp = StrideCheck;
- LastBypassBlock = CheckBlock;
- }
-
+ emitStrideChecks(Lp, ScalarPH);
// Generate the code that checks in runtime if arrays overlap. We put the
// checks into a separate block to make the more common case of few elements
// faster.
- Instruction *MemRuntimeCheck;
- std::tie(FirstCheckInst, MemRuntimeCheck) =
- Legal->getLAI()->addRuntimeCheck(LastBypassBlock->getTerminator());
- if (MemRuntimeCheck) {
- AddedSafetyChecks = true;
- // Create a new block containing the memory check.
- BasicBlock *CheckBlock =
- LastBypassBlock->splitBasicBlock(FirstCheckInst, "vector.memcheck");
- if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
- LoopBypassBlocks.push_back(CheckBlock);
-
- // Replace the branch into the memory check block with a conditional branch
- // for the "few elements case".
- Instruction *OldTerm = LastBypassBlock->getTerminator();
- BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm);
- OldTerm->eraseFromParent();
-
- Cmp = MemRuntimeCheck;
- LastBypassBlock = CheckBlock;
- }
-
- LastBypassBlock->getTerminator()->eraseFromParent();
- BranchInst::Create(MiddleBlock, VectorPH, Cmp,
- LastBypassBlock);
+ emitMemRuntimeChecks(Lp, ScalarPH);
+
+ // Generate the induction variable.
+ // The loop step is equal to the vectorization factor (num of SIMD elements)
+ // times the unroll factor (num of SIMD instructions).
+ Value *CountRoundDown = getOrCreateVectorTripCount(Lp);
+ Constant *Step = ConstantInt::get(IdxTy, VF * UF);
+ Induction =
+ createInductionVariable(Lp, StartIdx, CountRoundDown, Step,
+ getDebugLocFromInstOrOperands(OldInduction));
// We are going to resume the execution of the scalar loop.
// Go over all of the induction variables that we found and fix the
// If we come from a bypass edge then we need to start from the original
// start value.
- // This variable saves the new starting index for the scalar loop.
- PHINode *ResumeIndex = nullptr;
+ // This variable saves the new starting index for the scalar loop. It is used
+ // to test if there are any tail iterations left once the vector loop has
+ // completed.
LoopVectorizationLegality::InductionList::iterator I, E;
LoopVectorizationLegality::InductionList *List = Legal->getInductionVars();
- // Set builder to point to last bypass block.
- BypassBuilder.SetInsertPoint(LoopBypassBlocks.back()->getTerminator());
for (I = List->begin(), E = List->end(); I != E; ++I) {
PHINode *OrigPhi = I->first;
- LoopVectorizationLegality::InductionInfo II = I->second;
-
- Type *ResumeValTy = (OrigPhi == OldInduction) ? IdxTy : OrigPhi->getType();
- PHINode *ResumeVal = PHINode::Create(ResumeValTy, 2, "resume.val",
- MiddleBlock->getTerminator());
- // We might have extended the type of the induction variable but we need a
- // truncated version for the scalar loop.
- PHINode *TruncResumeVal = (OrigPhi == OldInduction) ?
- PHINode::Create(OrigPhi->getType(), 2, "trunc.resume.val",
- MiddleBlock->getTerminator()) : nullptr;
+ InductionDescriptor II = I->second;
// Create phi nodes to merge from the backedge-taken check block.
- PHINode *BCResumeVal = PHINode::Create(ResumeValTy, 3, "bc.resume.val",
+ PHINode *BCResumeVal = PHINode::Create(OrigPhi->getType(), 3,
+ "bc.resume.val",
ScalarPH->getTerminator());
- BCResumeVal->addIncoming(ResumeVal, MiddleBlock);
-
- PHINode *BCTruncResumeVal = nullptr;
+ Value *EndValue;
if (OrigPhi == OldInduction) {
- BCTruncResumeVal =
- PHINode::Create(OrigPhi->getType(), 2, "bc.trunc.resume.val",
- ScalarPH->getTerminator());
- BCTruncResumeVal->addIncoming(TruncResumeVal, MiddleBlock);
- }
-
- Value *EndValue = nullptr;
- switch (II.IK) {
- case LoopVectorizationLegality::IK_NoInduction:
- llvm_unreachable("Unknown induction");
- case LoopVectorizationLegality::IK_IntInduction: {
- // Handle the integer induction counter.
- assert(OrigPhi->getType()->isIntegerTy() && "Invalid type");
-
- // We have the canonical induction variable.
- if (OrigPhi == OldInduction) {
- // Create a truncated version of the resume value for the scalar loop,
- // we might have promoted the type to a larger width.
- EndValue =
- BypassBuilder.CreateTrunc(IdxEndRoundDown, OrigPhi->getType());
- // The new PHI merges the original incoming value, in case of a bypass,
- // or the value at the end of the vectorized loop.
- for (unsigned I = 1, E = LoopBypassBlocks.size(); I != E; ++I)
- TruncResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[I]);
- TruncResumeVal->addIncoming(EndValue, VecBody);
-
- BCTruncResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[0]);
-
- // We know what the end value is.
- EndValue = IdxEndRoundDown;
- // We also know which PHI node holds it.
- ResumeIndex = ResumeVal;
- break;
- }
-
- // Not the canonical induction variable - add the vector loop count to the
- // start value.
- Value *CRD = BypassBuilder.CreateSExtOrTrunc(CountRoundDown,
- II.StartValue->getType(),
- "cast.crd");
- EndValue = II.transform(BypassBuilder, CRD);
+ // We know what the end value is.
+ EndValue = CountRoundDown;
+ } else {
+ IRBuilder<> B(LoopBypassBlocks.back()->getTerminator());
+ Value *CRD = B.CreateSExtOrTrunc(CountRoundDown,
+ II.getStepValue()->getType(),
+ "cast.crd");
+ EndValue = II.transform(B, CRD);
EndValue->setName("ind.end");
- break;
- }
- case LoopVectorizationLegality::IK_PtrInduction: {
- EndValue = II.transform(BypassBuilder, CountRoundDown);
- EndValue->setName("ptr.ind.end");
- break;
}
- }// end of case
// The new PHI merges the original incoming value, in case of a bypass,
// or the value at the end of the vectorized loop.
- for (unsigned I = 1, E = LoopBypassBlocks.size(); I != E; ++I) {
- if (OrigPhi == OldInduction)
- ResumeVal->addIncoming(StartIdx, LoopBypassBlocks[I]);
- else
- ResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[I]);
- }
- ResumeVal->addIncoming(EndValue, VecBody);
+ BCResumeVal->addIncoming(EndValue, MiddleBlock);
// Fix the scalar body counter (PHI node).
unsigned BlockIdx = OrigPhi->getBasicBlockIndex(ScalarPH);
// The old induction's phi node in the scalar body needs the truncated
// value.
- if (OrigPhi == OldInduction) {
- BCResumeVal->addIncoming(StartIdx, LoopBypassBlocks[0]);
- OrigPhi->setIncomingValue(BlockIdx, BCTruncResumeVal);
- } else {
- BCResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[0]);
- OrigPhi->setIncomingValue(BlockIdx, BCResumeVal);
- }
+ for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I)
+ BCResumeVal->addIncoming(II.getStartValue(), LoopBypassBlocks[I]);
+ OrigPhi->setIncomingValue(BlockIdx, BCResumeVal);
}
- // If we are generating a new induction variable then we also need to
- // generate the code that calculates the exit value. This value is not
- // simply the end of the counter because we may skip the vectorized body
- // in case of a runtime check.
- if (!OldInduction){
- assert(!ResumeIndex && "Unexpected resume value found");
- ResumeIndex = PHINode::Create(IdxTy, 2, "new.indc.resume.val",
- MiddleBlock->getTerminator());
- for (unsigned I = 1, E = LoopBypassBlocks.size(); I != E; ++I)
- ResumeIndex->addIncoming(StartIdx, LoopBypassBlocks[I]);
- ResumeIndex->addIncoming(IdxEndRoundDown, VecBody);
- }
-
- // Make sure that we found the index where scalar loop needs to continue.
- assert(ResumeIndex && ResumeIndex->getType()->isIntegerTy() &&
- "Invalid resume Index");
-
// Add a check in the middle block to see if we have completed
// all of the iterations in the first vector loop.
// If (N - N%VF) == N, then we *don't* need to run the remainder.
- Value *CmpN = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, IdxEnd,
- ResumeIndex, "cmp.n",
+ Value *CmpN = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, Count,
+ CountRoundDown, "cmp.n",
MiddleBlock->getTerminator());
-
- BranchInst::Create(ExitBlock, ScalarPH, CmpN, MiddleBlock->getTerminator());
- // Remove the old terminator.
- MiddleBlock->getTerminator()->eraseFromParent();
-
- // Create i+1 and fill the PHINode.
- Value *NextIdx = Builder.CreateAdd(Induction, Step, "index.next");
- Induction->addIncoming(StartIdx, VectorPH);
- Induction->addIncoming(NextIdx, VecBody);
- // Create the compare.
- Value *ICmp = Builder.CreateICmpEQ(NextIdx, IdxEndRoundDown);
- Builder.CreateCondBr(ICmp, MiddleBlock, VecBody);
-
- // Now we have two terminators. Remove the old one from the block.
- VecBody->getTerminator()->eraseFromParent();
+ ReplaceInstWithInst(MiddleBlock->getTerminator(),
+ BranchInst::Create(ExitBlock, ScalarPH, CmpN));
// Get ready to start creating new instructions into the vectorized body.
- Builder.SetInsertPoint(VecBody->getFirstInsertionPt());
+ Builder.SetInsertPoint(&*VecBody->getFirstInsertionPt());
// Save the state.
- LoopVectorPreHeader = VectorPH;
+ LoopVectorPreHeader = Lp->getLoopPreheader();
LoopScalarPreHeader = ScalarPH;
LoopMiddleBlock = MiddleBlock;
LoopExitBlock = ExitBlock;
for (unsigned i = 0, e = BBs.size(); i != e; ++i) {
BasicBlock *BB = BBs[i];
for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) {
- Instruction *In = I++;
+ Instruction *In = &*I++;
if (!CSEDenseMapInfo::canHandle(In))
continue;
return TTI.getIntrinsicInstrCost(ID, RetTy, Tys);
}
+static Type *smallestIntegerVectorType(Type *T1, Type *T2) {
+ IntegerType *I1 = cast<IntegerType>(T1->getVectorElementType());
+ IntegerType *I2 = cast<IntegerType>(T2->getVectorElementType());
+ return I1->getBitWidth() < I2->getBitWidth() ? T1 : T2;
+}
+static Type *largestIntegerVectorType(Type *T1, Type *T2) {
+ IntegerType *I1 = cast<IntegerType>(T1->getVectorElementType());
+ IntegerType *I2 = cast<IntegerType>(T2->getVectorElementType());
+ return I1->getBitWidth() > I2->getBitWidth() ? T1 : T2;
+}
+
+void InnerLoopVectorizer::truncateToMinimalBitwidths() {
+ // For every instruction `I` in MinBWs, truncate the operands, create a
+ // truncated version of `I` and reextend its result. InstCombine runs
+ // later and will remove any ext/trunc pairs.
+ //
+ for (auto &KV : MinBWs) {
+ VectorParts &Parts = WidenMap.get(KV.first);
+ for (Value *&I : Parts) {
+ if (I->use_empty())
+ continue;
+ Type *OriginalTy = I->getType();
+ Type *ScalarTruncatedTy = IntegerType::get(OriginalTy->getContext(),
+ KV.second);
+ Type *TruncatedTy = VectorType::get(ScalarTruncatedTy,
+ OriginalTy->getVectorNumElements());
+ if (TruncatedTy == OriginalTy)
+ continue;
+
+ IRBuilder<> B(cast<Instruction>(I));
+ auto ShrinkOperand = [&](Value *V) -> Value* {
+ if (auto *ZI = dyn_cast<ZExtInst>(V))
+ if (ZI->getSrcTy() == TruncatedTy)
+ return ZI->getOperand(0);
+ return B.CreateZExtOrTrunc(V, TruncatedTy);
+ };
+
+ // The actual instruction modification depends on the instruction type,
+ // unfortunately.
+ Value *NewI = nullptr;
+ if (BinaryOperator *BO = dyn_cast<BinaryOperator>(I)) {
+ NewI = B.CreateBinOp(BO->getOpcode(),
+ ShrinkOperand(BO->getOperand(0)),
+ ShrinkOperand(BO->getOperand(1)));
+ cast<BinaryOperator>(NewI)->copyIRFlags(I);
+ } else if (ICmpInst *CI = dyn_cast<ICmpInst>(I)) {
+ NewI = B.CreateICmp(CI->getPredicate(),
+ ShrinkOperand(CI->getOperand(0)),
+ ShrinkOperand(CI->getOperand(1)));
+ } else if (SelectInst *SI = dyn_cast<SelectInst>(I)) {
+ NewI = B.CreateSelect(SI->getCondition(),
+ ShrinkOperand(SI->getTrueValue()),
+ ShrinkOperand(SI->getFalseValue()));
+ } else if (CastInst *CI = dyn_cast<CastInst>(I)) {
+ switch (CI->getOpcode()) {
+ default: llvm_unreachable("Unhandled cast!");
+ case Instruction::Trunc:
+ NewI = ShrinkOperand(CI->getOperand(0));
+ break;
+ case Instruction::SExt:
+ NewI = B.CreateSExtOrTrunc(CI->getOperand(0),
+ smallestIntegerVectorType(OriginalTy,
+ TruncatedTy));
+ break;
+ case Instruction::ZExt:
+ NewI = B.CreateZExtOrTrunc(CI->getOperand(0),
+ smallestIntegerVectorType(OriginalTy,
+ TruncatedTy));
+ break;
+ }
+ } else if (ShuffleVectorInst *SI = dyn_cast<ShuffleVectorInst>(I)) {
+ auto Elements0 = SI->getOperand(0)->getType()->getVectorNumElements();
+ auto *O0 =
+ B.CreateZExtOrTrunc(SI->getOperand(0),
+ VectorType::get(ScalarTruncatedTy, Elements0));
+ auto Elements1 = SI->getOperand(1)->getType()->getVectorNumElements();
+ auto *O1 =
+ B.CreateZExtOrTrunc(SI->getOperand(1),
+ VectorType::get(ScalarTruncatedTy, Elements1));
+
+ NewI = B.CreateShuffleVector(O0, O1, SI->getMask());
+ } else if (isa<LoadInst>(I)) {
+ // Don't do anything with the operands, just extend the result.
+ continue;
+ } else {
+ llvm_unreachable("Unhandled instruction type!");
+ }
+
+ // Lastly, extend the result.
+ NewI->takeName(cast<Instruction>(I));
+ Value *Res = B.CreateZExtOrTrunc(NewI, OriginalTy);
+ I->replaceAllUsesWith(Res);
+ cast<Instruction>(I)->eraseFromParent();
+ I = Res;
+ }
+ }
+
+ // We'll have created a bunch of ZExts that are now parentless. Clean up.
+ for (auto &KV : MinBWs) {
+ VectorParts &Parts = WidenMap.get(KV.first);
+ for (Value *&I : Parts) {
+ ZExtInst *Inst = dyn_cast<ZExtInst>(I);
+ if (Inst && Inst->use_empty()) {
+ Value *NewI = Inst->getOperand(0);
+ Inst->eraseFromParent();
+ I = NewI;
+ }
+ }
+ }
+}
+
void InnerLoopVectorizer::vectorizeLoop() {
//===------------------------------------------------===//
//
be = DFS.endRPO(); bb != be; ++bb)
vectorizeBlockInLoop(*bb, &RdxPHIsToFix);
+ // Insert truncates and extends for any truncated instructions as hints to
+ // InstCombine.
+ if (VF > 1)
+ truncateToMinimalBitwidths();
+
// At this point every instruction in the original loop is widened to
// a vector form. We are almost done. Now, we need to fix the PHI nodes
// that we vectorized. The PHI nodes are currently empty because we did
// Find the reduction variable descriptor.
assert(Legal->getReductionVars()->count(RdxPhi) &&
"Unable to find the reduction variable");
- ReductionDescriptor RdxDesc = (*Legal->getReductionVars())[RdxPhi];
+ RecurrenceDescriptor RdxDesc = (*Legal->getReductionVars())[RdxPhi];
- ReductionDescriptor::ReductionKind RK = RdxDesc.getReductionKind();
- TrackingVH<Value> ReductionStartValue = RdxDesc.getReductionStartValue();
+ RecurrenceDescriptor::RecurrenceKind RK = RdxDesc.getRecurrenceKind();
+ TrackingVH<Value> ReductionStartValue = RdxDesc.getRecurrenceStartValue();
Instruction *LoopExitInst = RdxDesc.getLoopExitInstr();
- ReductionInstDesc::MinMaxReductionKind MinMaxKind =
- RdxDesc.getMinMaxReductionKind();
+ RecurrenceDescriptor::MinMaxRecurrenceKind MinMaxKind =
+ RdxDesc.getMinMaxRecurrenceKind();
setDebugLocFromInst(Builder, ReductionStartValue);
// We need to generate a reduction vector from the incoming scalar.
// one for multiplication, -1 for And.
Value *Identity;
Value *VectorStart;
- if (RK == ReductionDescriptor::RK_IntegerMinMax ||
- RK == ReductionDescriptor::RK_FloatMinMax) {
+ if (RK == RecurrenceDescriptor::RK_IntegerMinMax ||
+ RK == RecurrenceDescriptor::RK_FloatMinMax) {
// MinMax reduction have the start value as their identify.
if (VF == 1) {
VectorStart = Identity = ReductionStartValue;
}
} else {
// Handle other reduction kinds:
- Constant *Iden =
- ReductionDescriptor::getReductionIdentity(RK, VecTy->getScalarType());
+ Constant *Iden = RecurrenceDescriptor::getRecurrenceIdentity(
+ RK, VecTy->getScalarType());
if (VF == 1) {
Identity = Iden;
// This vector is the Identity vector where the first element is the
// the PHIs and the values we are going to write.
// This allows us to write both PHINodes and the extractelement
// instructions.
- Builder.SetInsertPoint(LoopMiddleBlock->getFirstInsertionPt());
+ Builder.SetInsertPoint(&*LoopMiddleBlock->getFirstInsertionPt());
- VectorParts RdxParts;
+ VectorParts RdxParts = getVectorValue(LoopExitInst);
setDebugLocFromInst(Builder, LoopExitInst);
- for (unsigned part = 0; part < UF; ++part) {
- // This PHINode contains the vectorized reduction variable, or
- // the initial value vector, if we bypass the vector loop.
- VectorParts &RdxExitVal = getVectorValue(LoopExitInst);
- PHINode *NewPhi = Builder.CreatePHI(VecTy, 2, "rdx.vec.exit.phi");
- Value *StartVal = (part == 0) ? VectorStart : Identity;
- for (unsigned I = 1, E = LoopBypassBlocks.size(); I != E; ++I)
- NewPhi->addIncoming(StartVal, LoopBypassBlocks[I]);
- NewPhi->addIncoming(RdxExitVal[part],
- LoopVectorBody.back());
- RdxParts.push_back(NewPhi);
+
+ // If the vector reduction can be performed in a smaller type, we truncate
+ // then extend the loop exit value to enable InstCombine to evaluate the
+ // entire expression in the smaller type.
+ if (VF > 1 && RdxPhi->getType() != RdxDesc.getRecurrenceType()) {
+ Type *RdxVecTy = VectorType::get(RdxDesc.getRecurrenceType(), VF);
+ Builder.SetInsertPoint(LoopVectorBody.back()->getTerminator());
+ for (unsigned part = 0; part < UF; ++part) {
+ Value *Trunc = Builder.CreateTrunc(RdxParts[part], RdxVecTy);
+ Value *Extnd = RdxDesc.isSigned() ? Builder.CreateSExt(Trunc, VecTy)
+ : Builder.CreateZExt(Trunc, VecTy);
+ for (Value::user_iterator UI = RdxParts[part]->user_begin();
+ UI != RdxParts[part]->user_end();)
+ if (*UI != Trunc) {
+ (*UI++)->replaceUsesOfWith(RdxParts[part], Extnd);
+ RdxParts[part] = Extnd;
+ } else {
+ ++UI;
+ }
+ }
+ Builder.SetInsertPoint(&*LoopMiddleBlock->getFirstInsertionPt());
+ for (unsigned part = 0; part < UF; ++part)
+ RdxParts[part] = Builder.CreateTrunc(RdxParts[part], RdxVecTy);
}
// Reduce all of the unrolled parts into a single vector.
Value *ReducedPartRdx = RdxParts[0];
- unsigned Op = ReductionDescriptor::getReductionBinOp(RK);
+ unsigned Op = RecurrenceDescriptor::getRecurrenceBinOp(RK);
setDebugLocFromInst(Builder, ReducedPartRdx);
for (unsigned part = 1; part < UF; ++part) {
if (Op != Instruction::ICmp && Op != Instruction::FCmp)
Builder.CreateBinOp((Instruction::BinaryOps)Op, RdxParts[part],
ReducedPartRdx, "bin.rdx"));
else
- ReducedPartRdx = ReductionDescriptor::createMinMaxOp(
+ ReducedPartRdx = RecurrenceDescriptor::createMinMaxOp(
Builder, MinMaxKind, ReducedPartRdx, RdxParts[part]);
}
TmpVec = addFastMathFlag(Builder.CreateBinOp(
(Instruction::BinaryOps)Op, TmpVec, Shuf, "bin.rdx"));
else
- TmpVec = ReductionDescriptor::createMinMaxOp(Builder, MinMaxKind,
- TmpVec, Shuf);
+ TmpVec = RecurrenceDescriptor::createMinMaxOp(Builder, MinMaxKind,
+ TmpVec, Shuf);
}
// The result is in the first element of the vector.
ReducedPartRdx = Builder.CreateExtractElement(TmpVec,
Builder.getInt32(0));
+
+ // If the reduction can be performed in a smaller type, we need to extend
+ // the reduction to the wider type before we branch to the original loop.
+ if (RdxPhi->getType() != RdxDesc.getRecurrenceType())
+ ReducedPartRdx =
+ RdxDesc.isSigned()
+ ? Builder.CreateSExt(ReducedPartRdx, RdxPhi->getType())
+ : Builder.CreateZExt(ReducedPartRdx, RdxPhi->getType());
}
// Create a phi node that merges control-flow from the backedge-taken check
// block and the middle block.
PHINode *BCBlockPhi = PHINode::Create(RdxPhi->getType(), 2, "bc.merge.rdx",
LoopScalarPreHeader->getTerminator());
- BCBlockPhi->addIncoming(ReductionStartValue, LoopBypassBlocks[0]);
+ for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I)
+ BCBlockPhi->addIncoming(ReductionStartValue, LoopBypassBlocks[I]);
BCBlockPhi->addIncoming(ReducedPartRdx, LoopMiddleBlock);
// Now, we need to fix the users of the reduction variable
fixLCSSAPHIs();
+ // Make sure DomTree is updated.
+ updateAnalysis();
+
+ // Predicate any stores.
+ for (auto KV : PredicatedStores) {
+ BasicBlock::iterator I(KV.first);
+ auto *BB = SplitBlock(I->getParent(), &*std::next(I), DT, LI);
+ auto *T = SplitBlockAndInsertIfThen(KV.second, &*I, /*Unreachable=*/false,
+ /*BranchWeights=*/nullptr, DT);
+ I->moveBefore(T);
+ I->getParent()->setName("pred.store.if");
+ BB->setName("pred.store.continue");
+ }
+ DEBUG(DT->verifyDomTree());
// Remove redundant induction instructions.
cse(LoopVectorBody);
}
// This is phase one of vectorizing PHIs.
Type *VecTy = (VF == 1) ? PN->getType() :
VectorType::get(PN->getType(), VF);
- Entry[part] = PHINode::Create(VecTy, 2, "vec.phi",
- LoopVectorBody.back()-> getFirstInsertionPt());
+ Entry[part] = PHINode::Create(
+ VecTy, 2, "vec.phi", &*LoopVectorBody.back()->getFirstInsertionPt());
}
PV->push_back(P);
return;
assert(Legal->getInductionVars()->count(P) &&
"Not an induction variable");
- LoopVectorizationLegality::InductionInfo II =
- Legal->getInductionVars()->lookup(P);
+ InductionDescriptor II = Legal->getInductionVars()->lookup(P);
// FIXME: The newly created binary instructions should contain nsw/nuw flags,
// which can be found from the original scalar operations.
- switch (II.IK) {
- case LoopVectorizationLegality::IK_NoInduction:
+ switch (II.getKind()) {
+ case InductionDescriptor::IK_NoInduction:
llvm_unreachable("Unknown induction");
- case LoopVectorizationLegality::IK_IntInduction: {
- assert(P->getType() == II.StartValue->getType() && "Types must match");
- Type *PhiTy = P->getType();
- Value *Broadcasted;
- if (P == OldInduction) {
- // Handle the canonical induction variable. We might have had to
- // extend the type.
- Broadcasted = Builder.CreateTrunc(Induction, PhiTy);
- } else {
- // Handle other induction variables that are now based on the
- // canonical one.
- Value *NormalizedIdx = Builder.CreateSub(Induction, ExtendedIdx,
- "normalized.idx");
- NormalizedIdx = Builder.CreateSExtOrTrunc(NormalizedIdx, PhiTy);
- Broadcasted = II.transform(Builder, NormalizedIdx);
- Broadcasted->setName("offset.idx");
+ case InductionDescriptor::IK_IntInduction: {
+ assert(P->getType() == II.getStartValue()->getType() && "Types must match");
+ // Handle other induction variables that are now based on the
+ // canonical one.
+ Value *V = Induction;
+ if (P != OldInduction) {
+ V = Builder.CreateSExtOrTrunc(Induction, P->getType());
+ V = II.transform(Builder, V);
+ V->setName("offset.idx");
}
- Broadcasted = getBroadcastInstrs(Broadcasted);
+ Value *Broadcasted = getBroadcastInstrs(V);
// After broadcasting the induction variable we need to make the vector
// consecutive by adding 0, 1, 2, etc.
for (unsigned part = 0; part < UF; ++part)
- Entry[part] = getStepVector(Broadcasted, VF * part, II.StepValue);
+ Entry[part] = getStepVector(Broadcasted, VF * part, II.getStepValue());
return;
}
- case LoopVectorizationLegality::IK_PtrInduction:
+ case InductionDescriptor::IK_PtrInduction:
// Handle the pointer induction variable case.
assert(P->getType()->isPointerTy() && "Unexpected type.");
// This is the normalized GEP that starts counting at zero.
- Value *NormalizedIdx =
- Builder.CreateSub(Induction, ExtendedIdx, "normalized.idx");
+ Value *PtrInd = Induction;
+ PtrInd = Builder.CreateSExtOrTrunc(PtrInd, II.getStepValue()->getType());
// This is the vector of results. Notice that we don't generate
// vector geps because scalar geps result in better code.
for (unsigned part = 0; part < UF; ++part) {
if (VF == 1) {
int EltIndex = part;
- Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
- Value *GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx);
+ Constant *Idx = ConstantInt::get(PtrInd->getType(), EltIndex);
+ Value *GlobalIdx = Builder.CreateAdd(PtrInd, Idx);
Value *SclrGep = II.transform(Builder, GlobalIdx);
SclrGep->setName("next.gep");
Entry[part] = SclrGep;
Value *VecVal = UndefValue::get(VectorType::get(P->getType(), VF));
for (unsigned int i = 0; i < VF; ++i) {
int EltIndex = i + part * VF;
- Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
- Value *GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx);
+ Constant *Idx = ConstantInt::get(PtrInd->getType(), EltIndex);
+ Value *GlobalIdx = Builder.CreateAdd(PtrInd, Idx);
Value *SclrGep = II.transform(Builder, GlobalIdx);
SclrGep->setName("next.gep");
VecVal = Builder.CreateInsertElement(VecVal, SclrGep,
void InnerLoopVectorizer::vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV) {
// For each instruction in the old loop.
for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
- VectorParts &Entry = WidenMap.get(it);
+ VectorParts &Entry = WidenMap.get(&*it);
+
switch (it->getOpcode()) {
case Instruction::Br:
// Nothing to do for PHIs and BR, since we already took care of the
continue;
case Instruction::PHI: {
// Vectorize PHINodes.
- widenPHIInstruction(it, Entry, UF, VF, PV);
+ widenPHIInstruction(&*it, Entry, UF, VF, PV);
continue;
}// End of PHI.
Entry[Part] = V;
}
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
case Instruction::Select: {
// instruction with a scalar condition. Otherwise, use vector-select.
bool InvariantCond = SE->isLoopInvariant(SE->getSCEV(it->getOperand(0)),
OrigLoop);
- setDebugLocFromInst(Builder, it);
+ setDebugLocFromInst(Builder, &*it);
// The condition can be loop invariant but still defined inside the
// loop. This means that we can't just use the original 'cond' value.
VectorParts &Cond = getVectorValue(it->getOperand(0));
VectorParts &Op0 = getVectorValue(it->getOperand(1));
VectorParts &Op1 = getVectorValue(it->getOperand(2));
-
+
Value *ScalarCond = (VF == 1) ? Cond[0] :
Builder.CreateExtractElement(Cond[0], Builder.getInt32(0));
Op1[Part]);
}
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
// Widen compares. Generate vector compares.
bool FCmp = (it->getOpcode() == Instruction::FCmp);
CmpInst *Cmp = dyn_cast<CmpInst>(it);
- setDebugLocFromInst(Builder, it);
+ setDebugLocFromInst(Builder, &*it);
VectorParts &A = getVectorValue(it->getOperand(0));
VectorParts &B = getVectorValue(it->getOperand(1));
for (unsigned Part = 0; Part < UF; ++Part) {
Value *C = nullptr;
- if (FCmp)
+ if (FCmp) {
C = Builder.CreateFCmp(Cmp->getPredicate(), A[Part], B[Part]);
- else
+ cast<FCmpInst>(C)->copyFastMathFlags(&*it);
+ } else {
C = Builder.CreateICmp(Cmp->getPredicate(), A[Part], B[Part]);
+ }
Entry[Part] = C;
}
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
case Instruction::Store:
case Instruction::Load:
- vectorizeMemoryInstruction(it);
+ vectorizeMemoryInstruction(&*it);
break;
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::FPTrunc:
case Instruction::BitCast: {
CastInst *CI = dyn_cast<CastInst>(it);
- setDebugLocFromInst(Builder, it);
+ setDebugLocFromInst(Builder, &*it);
/// Optimize the special case where the source is the induction
/// variable. Notice that we can only optimize the 'trunc' case
/// because: a. FP conversions lose precision, b. sext/zext may wrap,
Value *ScalarCast = Builder.CreateCast(CI->getOpcode(), Induction,
CI->getType());
Value *Broadcasted = getBroadcastInstrs(ScalarCast);
- LoopVectorizationLegality::InductionInfo II =
- Legal->getInductionVars()->lookup(OldInduction);
+ InductionDescriptor II = Legal->getInductionVars()->lookup(OldInduction);
Constant *Step =
- ConstantInt::getSigned(CI->getType(), II.StepValue->getSExtValue());
+ ConstantInt::getSigned(CI->getType(), II.getStepValue()->getSExtValue());
for (unsigned Part = 0; Part < UF; ++Part)
Entry[Part] = getStepVector(Broadcasted, VF * Part, Step);
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
/// Vectorize casts.
VectorParts &A = getVectorValue(it->getOperand(0));
for (unsigned Part = 0; Part < UF; ++Part)
Entry[Part] = Builder.CreateCast(CI->getOpcode(), A[Part], DestTy);
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
// Ignore dbg intrinsics.
if (isa<DbgInfoIntrinsic>(it))
break;
- setDebugLocFromInst(Builder, it);
+ setDebugLocFromInst(Builder, &*it);
Module *M = BB->getParent()->getParent();
CallInst *CI = cast<CallInst>(it);
if (ID &&
(ID == Intrinsic::assume || ID == Intrinsic::lifetime_end ||
ID == Intrinsic::lifetime_start)) {
- scalarizeInstruction(it);
+ scalarizeInstruction(&*it);
break;
}
// The flag shows whether we use Intrinsic or a usual Call for vectorized
bool UseVectorIntrinsic =
ID && getVectorIntrinsicCost(CI, VF, *TTI, TLI) <= CallCost;
if (!UseVectorIntrinsic && NeedToScalarize) {
- scalarizeInstruction(it);
+ scalarizeInstruction(&*it);
break;
}
Entry[Part] = Builder.CreateCall(VectorF, Args);
}
- propagateMetadata(Entry, it);
+ propagateMetadata(Entry, &*it);
break;
}
default:
// All other instructions are unsupported. Scalarize them.
- scalarizeInstruction(it);
+ scalarizeInstruction(&*it);
break;
}// end of switch.
}// end of for_each instr.
DT->addNewBlock(LoopBypassBlocks[I], LoopBypassBlocks[I-1]);
DT->addNewBlock(LoopVectorPreHeader, LoopBypassBlocks.back());
- // Due to if predication of stores we might create a sequence of "if(pred)
- // a[i] = ...; " blocks.
- for (unsigned i = 0, e = LoopVectorBody.size(); i != e; ++i) {
- if (i == 0)
- DT->addNewBlock(LoopVectorBody[0], LoopVectorPreHeader);
- else if (isPredicatedBlock(i)) {
- DT->addNewBlock(LoopVectorBody[i], LoopVectorBody[i-1]);
- } else {
- DT->addNewBlock(LoopVectorBody[i], LoopVectorBody[i-2]);
- }
- }
+ // We don't predicate stores by this point, so the vector body should be a
+ // single loop.
+ assert(LoopVectorBody.size() == 1 && "Expected single block loop!");
+ DT->addNewBlock(LoopVectorBody[0], LoopVectorPreHeader);
- DT->addNewBlock(LoopMiddleBlock, LoopBypassBlocks[1]);
+ DT->addNewBlock(LoopMiddleBlock, LoopVectorBody.back());
DT->addNewBlock(LoopScalarPreHeader, LoopBypassBlocks[0]);
DT->changeImmediateDominator(LoopScalarBody, LoopScalarPreHeader);
DT->changeImmediateDominator(LoopExitBlock, LoopBypassBlocks[0]);
}
// We can only vectorize innermost loops.
- if (!TheLoop->getSubLoopsVector().empty()) {
+ if (!TheLoop->empty()) {
emitAnalysis(VectorizationReport() << "loop is not the innermost loop");
return false;
}
// Collect all of the variables that remain uniform after vectorization.
collectLoopUniforms();
- DEBUG(dbgs() << "LV: We can vectorize this loop" <<
- (LAI->getRuntimePointerCheck()->Need ? " (with a runtime bound check)" :
- "")
- <<"!\n");
+ DEBUG(dbgs() << "LV: We can vectorize this loop"
+ << (LAI->getRuntimePointerChecking()->Need
+ ? " (with a runtime bound check)"
+ : "")
+ << "!\n");
+
+ bool UseInterleaved = TTI->enableInterleavedAccessVectorization();
+
+ // If an override option has been passed in for interleaved accesses, use it.
+ if (EnableInterleavedMemAccesses.getNumOccurrences() > 0)
+ UseInterleaved = EnableInterleavedMemAccesses;
+
+ // Analyze interleaved memory accesses.
+ if (UseInterleaved)
+ InterleaveInfo.analyzeInterleaving(Strides);
// Okay! We can vectorize. At this point we don't have any other mem analysis
// which may limit our maximum vectorization factor, so just return true with
}
bool LoopVectorizationLegality::canVectorizeInstrs() {
- BasicBlock *PreHeader = TheLoop->getLoopPreheader();
BasicBlock *Header = TheLoop->getHeader();
// Look for the attribute signaling the absence of NaNs.
if (!PhiTy->isIntegerTy() &&
!PhiTy->isFloatingPointTy() &&
!PhiTy->isPointerTy()) {
- emitAnalysis(VectorizationReport(it)
+ emitAnalysis(VectorizationReport(&*it)
<< "loop control flow is not understood by vectorizer");
DEBUG(dbgs() << "LV: Found an non-int non-pointer PHI.\n");
return false;
if (*bb != Header) {
// Check that this instruction has no outside users or is an
// identified reduction value with an outside user.
- if (!hasOutsideLoopUser(TheLoop, it, AllowedExit))
+ if (!hasOutsideLoopUser(TheLoop, &*it, AllowedExit))
continue;
- emitAnalysis(VectorizationReport(it) <<
+ emitAnalysis(VectorizationReport(&*it) <<
"value could not be identified as "
"an induction or reduction variable");
return false;
// We only allow if-converted PHIs with exactly two incoming values.
if (Phi->getNumIncomingValues() != 2) {
- emitAnalysis(VectorizationReport(it)
+ emitAnalysis(VectorizationReport(&*it)
<< "control flow not understood by vectorizer");
DEBUG(dbgs() << "LV: Found an invalid PHI.\n");
return false;
}
- // This is the value coming from the preheader.
- Value *StartValue = Phi->getIncomingValueForBlock(PreHeader);
- ConstantInt *StepValue = nullptr;
- // Check if this is an induction variable.
- InductionKind IK = isInductionVariable(Phi, StepValue);
-
- if (IK_NoInduction != IK) {
+ InductionDescriptor ID;
+ if (InductionDescriptor::isInductionPHI(Phi, SE, ID)) {
+ Inductions[Phi] = ID;
// Get the widest type.
if (!WidestIndTy)
WidestIndTy = convertPointerToIntegerType(DL, PhiTy);
WidestIndTy = getWiderType(DL, PhiTy, WidestIndTy);
// Int inductions are special because we only allow one IV.
- if (IK == IK_IntInduction && StepValue->isOne()) {
+ if (ID.getKind() == InductionDescriptor::IK_IntInduction &&
+ ID.getStepValue()->isOne() &&
+ isa<Constant>(ID.getStartValue()) &&
+ cast<Constant>(ID.getStartValue())->isNullValue()) {
// Use the phi node with the widest type as induction. Use the last
// one if there are multiple (no good reason for doing this other
- // than it is expedient).
+ // than it is expedient). We've checked that it begins at zero and
+ // steps by one, so this is a canonical induction variable.
if (!Induction || PhiTy == WidestIndTy)
Induction = Phi;
}
DEBUG(dbgs() << "LV: Found an induction variable.\n");
- Inductions[Phi] = InductionInfo(StartValue, IK, StepValue);
// Until we explicitly handle the case of an induction variable with
// an outside loop user we have to give up vectorizing this loop.
- if (hasOutsideLoopUser(TheLoop, it, AllowedExit)) {
- emitAnalysis(VectorizationReport(it) <<
+ if (hasOutsideLoopUser(TheLoop, &*it, AllowedExit)) {
+ emitAnalysis(VectorizationReport(&*it) <<
"use of induction value outside of the "
"loop is not handled by vectorizer");
return false;
continue;
}
- if (ReductionDescriptor::isReductionPHI(Phi, TheLoop,
- Reductions[Phi])) {
+ if (RecurrenceDescriptor::isReductionPHI(Phi, TheLoop,
+ Reductions[Phi])) {
+ if (Reductions[Phi].hasUnsafeAlgebra())
+ Requirements->addUnsafeAlgebraInst(
+ Reductions[Phi].getUnsafeAlgebraInst());
AllowedExit.insert(Reductions[Phi].getLoopExitInstr());
continue;
}
- emitAnalysis(VectorizationReport(it) <<
+ emitAnalysis(VectorizationReport(&*it) <<
"value that could not be identified as "
"reduction is used outside the loop");
DEBUG(dbgs() << "LV: Found an unidentified PHI."<< *Phi <<"\n");
if (CI && !getIntrinsicIDForCall(CI, TLI) && !isa<DbgInfoIntrinsic>(CI) &&
!(CI->getCalledFunction() && TLI &&
TLI->isFunctionVectorizable(CI->getCalledFunction()->getName()))) {
- emitAnalysis(VectorizationReport(it) <<
- "call instruction cannot be vectorized");
+ emitAnalysis(VectorizationReport(&*it)
+ << "call instruction cannot be vectorized");
DEBUG(dbgs() << "LV: Found a non-intrinsic, non-libfunc callsite.\n");
return false;
}
if (CI &&
hasVectorInstrinsicScalarOpd(getIntrinsicIDForCall(CI, TLI), 1)) {
if (!SE->isLoopInvariant(SE->getSCEV(CI->getOperand(1)), TheLoop)) {
- emitAnalysis(VectorizationReport(it)
+ emitAnalysis(VectorizationReport(&*it)
<< "intrinsic instruction cannot be vectorized");
DEBUG(dbgs() << "LV: Found unvectorizable intrinsic " << *CI << "\n");
return false;
// Also, we can't vectorize extractelement instructions.
if ((!VectorType::isValidElementType(it->getType()) &&
!it->getType()->isVoidTy()) || isa<ExtractElementInst>(it)) {
- emitAnalysis(VectorizationReport(it)
+ emitAnalysis(VectorizationReport(&*it)
<< "instruction return type cannot be vectorized");
DEBUG(dbgs() << "LV: Found unvectorizable type.\n");
return false;
// Reduction instructions are allowed to have exit users.
// All other instructions must not have external users.
- if (hasOutsideLoopUser(TheLoop, it, AllowedExit)) {
- emitAnalysis(VectorizationReport(it) <<
+ if (hasOutsideLoopUser(TheLoop, &*it, AllowedExit)) {
+ emitAnalysis(VectorizationReport(&*it) <<
"value cannot be used outside the loop");
return false;
}
}
}
- return true;
-}
-
-///\brief Remove GEPs whose indices but the last one are loop invariant and
-/// return the induction operand of the gep pointer.
-static Value *stripGetElementPtr(Value *Ptr, ScalarEvolution *SE, Loop *Lp) {
- GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Ptr);
- if (!GEP)
- return Ptr;
-
- unsigned InductionOperand = getGEPInductionOperand(GEP);
-
- // Check that all of the gep indices are uniform except for our induction
- // operand.
- for (unsigned i = 0, e = GEP->getNumOperands(); i != e; ++i)
- if (i != InductionOperand &&
- !SE->isLoopInvariant(SE->getSCEV(GEP->getOperand(i)), Lp))
- return Ptr;
- return GEP->getOperand(InductionOperand);
-}
-
-///\brief Look for a cast use of the passed value.
-static Value *getUniqueCastUse(Value *Ptr, Loop *Lp, Type *Ty) {
- Value *UniqueCast = nullptr;
- for (User *U : Ptr->users()) {
- CastInst *CI = dyn_cast<CastInst>(U);
- if (CI && CI->getType() == Ty) {
- if (!UniqueCast)
- UniqueCast = CI;
- else
- return nullptr;
- }
- }
- return UniqueCast;
-}
-
-///\brief Get the stride of a pointer access in a loop.
-/// Looks for symbolic strides "a[i*stride]". Returns the symbolic stride as a
-/// pointer to the Value, or null otherwise.
-static Value *getStrideFromPointer(Value *Ptr, ScalarEvolution *SE, Loop *Lp) {
- const PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
- if (!PtrTy || PtrTy->isAggregateType())
- return nullptr;
-
- // Try to remove a gep instruction to make the pointer (actually index at this
- // point) easier analyzable. If OrigPtr is equal to Ptr we are analzying the
- // pointer, otherwise, we are analyzing the index.
- Value *OrigPtr = Ptr;
-
- // The size of the pointer access.
- int64_t PtrAccessSize = 1;
-
- Ptr = stripGetElementPtr(Ptr, SE, Lp);
- const SCEV *V = SE->getSCEV(Ptr);
-
- if (Ptr != OrigPtr)
- // Strip off casts.
- while (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(V))
- V = C->getOperand();
-
- const SCEVAddRecExpr *S = dyn_cast<SCEVAddRecExpr>(V);
- if (!S)
- return nullptr;
-
- V = S->getStepRecurrence(*SE);
- if (!V)
- return nullptr;
-
- // Strip off the size of access multiplication if we are still analyzing the
- // pointer.
- if (OrigPtr == Ptr) {
- const DataLayout &DL = Lp->getHeader()->getModule()->getDataLayout();
- DL.getTypeAllocSize(PtrTy->getElementType());
- if (const SCEVMulExpr *M = dyn_cast<SCEVMulExpr>(V)) {
- if (M->getOperand(0)->getSCEVType() != scConstant)
- return nullptr;
-
- const APInt &APStepVal =
- cast<SCEVConstant>(M->getOperand(0))->getValue()->getValue();
-
- // Huge step value - give up.
- if (APStepVal.getBitWidth() > 64)
- return nullptr;
-
- int64_t StepVal = APStepVal.getSExtValue();
- if (PtrAccessSize != StepVal)
- return nullptr;
- V = M->getOperand(1);
- }
- }
-
- // Strip off casts.
- Type *StripedOffRecurrenceCast = nullptr;
- if (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(V)) {
- StripedOffRecurrenceCast = C->getType();
- V = C->getOperand();
- }
-
- // Look for the loop invariant symbolic value.
- const SCEVUnknown *U = dyn_cast<SCEVUnknown>(V);
- if (!U)
- return nullptr;
-
- Value *Stride = U->getValue();
- if (!Lp->isLoopInvariant(Stride))
- return nullptr;
-
- // If we have stripped off the recurrence cast we have to make sure that we
- // return the value that is used in this loop so that we can replace it later.
- if (StripedOffRecurrenceCast)
- Stride = getUniqueCastUse(Stride, Lp, StripedOffRecurrenceCast);
+ // Now we know the widest induction type, check if our found induction
+ // is the same size. If it's not, unset it here and InnerLoopVectorizer
+ // will create another.
+ if (Induction && WidestIndTy != Induction->getType())
+ Induction = nullptr;
- return Stride;
+ return true;
}
void LoopVectorizationLegality::collectStridedAccess(Value *MemAccess) {
BE = TheLoop->block_end(); B != BE; ++B)
for (BasicBlock::iterator I = (*B)->begin(), IE = (*B)->end();
I != IE; ++I)
- if (I->getType()->isPointerTy() && isConsecutivePtr(I))
+ if (I->getType()->isPointerTy() && isConsecutivePtr(&*I))
Worklist.insert(Worklist.end(), I->op_begin(), I->op_end());
while (!Worklist.empty()) {
return false;
}
- if (LAI->getNumRuntimePointerChecks() >
- VectorizerParams::RuntimeMemoryCheckThreshold) {
- emitAnalysis(VectorizationReport()
- << LAI->getNumRuntimePointerChecks() << " exceeds limit of "
- << VectorizerParams::RuntimeMemoryCheckThreshold
- << " dependent memory operations checked at runtime");
- DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
- return false;
- }
- return true;
-}
-
-bool llvm::isInductionPHI(PHINode *Phi, ScalarEvolution *SE,
- ConstantInt *&StepValue) {
- Type *PhiTy = Phi->getType();
- // We only handle integer and pointer inductions variables.
- if (!PhiTy->isIntegerTy() && !PhiTy->isPointerTy())
- return false;
-
- // Check that the PHI is consecutive.
- const SCEV *PhiScev = SE->getSCEV(Phi);
- const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PhiScev);
- if (!AR) {
- DEBUG(dbgs() << "LV: PHI is not a poly recurrence.\n");
- return false;
- }
-
- const SCEV *Step = AR->getStepRecurrence(*SE);
- // Calculate the pointer stride and check if it is consecutive.
- const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
- if (!C)
- return false;
-
- ConstantInt *CV = C->getValue();
- if (PhiTy->isIntegerTy()) {
- StepValue = CV;
- return true;
- }
-
- assert(PhiTy->isPointerTy() && "The PHI must be a pointer");
- Type *PointerElementType = PhiTy->getPointerElementType();
- // The pointer stride cannot be determined if the pointer element type is not
- // sized.
- if (!PointerElementType->isSized())
- return false;
+ Requirements->addRuntimePointerChecks(LAI->getNumRuntimePointerChecks());
- const DataLayout &DL = Phi->getModule()->getDataLayout();
- int64_t Size = static_cast<int64_t>(DL.getTypeAllocSize(PointerElementType));
- int64_t CVSize = CV->getSExtValue();
- if (CVSize % Size)
- return false;
- StepValue = ConstantInt::getSigned(CV->getType(), CVSize / Size);
return true;
}
-LoopVectorizationLegality::InductionKind
-LoopVectorizationLegality::isInductionVariable(PHINode *Phi,
- ConstantInt *&StepValue) {
- if (!isInductionPHI(Phi, SE, StepValue))
- return IK_NoInduction;
-
- Type *PhiTy = Phi->getType();
- // Found an Integer induction variable.
- if (PhiTy->isIntegerTy())
- return IK_IntInduction;
- // Found an Pointer induction variable.
- return IK_PtrInduction;
-}
-
bool LoopVectorizationLegality::isInductionVariable(const Value *V) {
Value *In0 = const_cast<Value*>(V);
PHINode *PN = dyn_cast_or_null<PHINode>(In0);
return true;
}
+void InterleavedAccessInfo::collectConstStridedAccesses(
+ MapVector<Instruction *, StrideDescriptor> &StrideAccesses,
+ const ValueToValueMap &Strides) {
+ // Holds load/store instructions in program order.
+ SmallVector<Instruction *, 16> AccessList;
+
+ for (auto *BB : TheLoop->getBlocks()) {
+ bool IsPred = LoopAccessInfo::blockNeedsPredication(BB, TheLoop, DT);
+
+ for (auto &I : *BB) {
+ if (!isa<LoadInst>(&I) && !isa<StoreInst>(&I))
+ continue;
+ // FIXME: Currently we can't handle mixed accesses and predicated accesses
+ if (IsPred)
+ return;
+
+ AccessList.push_back(&I);
+ }
+ }
+
+ if (AccessList.empty())
+ return;
+
+ auto &DL = TheLoop->getHeader()->getModule()->getDataLayout();
+ for (auto I : AccessList) {
+ LoadInst *LI = dyn_cast<LoadInst>(I);
+ StoreInst *SI = dyn_cast<StoreInst>(I);
+
+ Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
+ int Stride = isStridedPtr(SE, Ptr, TheLoop, Strides);
+
+ // The factor of the corresponding interleave group.
+ unsigned Factor = std::abs(Stride);
+
+ // Ignore the access if the factor is too small or too large.
+ if (Factor < 2 || Factor > MaxInterleaveGroupFactor)
+ continue;
+
+ const SCEV *Scev = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
+ PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
+ unsigned Size = DL.getTypeAllocSize(PtrTy->getElementType());
+
+ // An alignment of 0 means target ABI alignment.
+ unsigned Align = LI ? LI->getAlignment() : SI->getAlignment();
+ if (!Align)
+ Align = DL.getABITypeAlignment(PtrTy->getElementType());
+
+ StrideAccesses[I] = StrideDescriptor(Stride, Scev, Size, Align);
+ }
+}
+
+// Analyze interleaved accesses and collect them into interleave groups.
+//
+// Notice that the vectorization on interleaved groups will change instruction
+// orders and may break dependences. But the memory dependence check guarantees
+// that there is no overlap between two pointers of different strides, element
+// sizes or underlying bases.
+//
+// For pointers sharing the same stride, element size and underlying base, no
+// need to worry about Read-After-Write dependences and Write-After-Read
+// dependences.
+//
+// E.g. The RAW dependence: A[i] = a;
+// b = A[i];
+// This won't exist as it is a store-load forwarding conflict, which has
+// already been checked and forbidden in the dependence check.
+//
+// E.g. The WAR dependence: a = A[i]; // (1)
+// A[i] = b; // (2)
+// The store group of (2) is always inserted at or below (2), and the load group
+// of (1) is always inserted at or above (1). The dependence is safe.
+void InterleavedAccessInfo::analyzeInterleaving(
+ const ValueToValueMap &Strides) {
+ DEBUG(dbgs() << "LV: Analyzing interleaved accesses...\n");
+
+ // Holds all the stride accesses.
+ MapVector<Instruction *, StrideDescriptor> StrideAccesses;
+ collectConstStridedAccesses(StrideAccesses, Strides);
+
+ if (StrideAccesses.empty())
+ return;
+
+ // Holds all interleaved store groups temporarily.
+ SmallSetVector<InterleaveGroup *, 4> StoreGroups;
+
+ // Search the load-load/write-write pair B-A in bottom-up order and try to
+ // insert B into the interleave group of A according to 3 rules:
+ // 1. A and B have the same stride.
+ // 2. A and B have the same memory object size.
+ // 3. B belongs to the group according to the distance.
+ //
+ // The bottom-up order can avoid breaking the Write-After-Write dependences
+ // between two pointers of the same base.
+ // E.g. A[i] = a; (1)
+ // A[i] = b; (2)
+ // A[i+1] = c (3)
+ // We form the group (2)+(3) in front, so (1) has to form groups with accesses
+ // above (1), which guarantees that (1) is always above (2).
+ for (auto I = StrideAccesses.rbegin(), E = StrideAccesses.rend(); I != E;
+ ++I) {
+ Instruction *A = I->first;
+ StrideDescriptor DesA = I->second;
+
+ InterleaveGroup *Group = getInterleaveGroup(A);
+ if (!Group) {
+ DEBUG(dbgs() << "LV: Creating an interleave group with:" << *A << '\n');
+ Group = createInterleaveGroup(A, DesA.Stride, DesA.Align);
+ }
+
+ if (A->mayWriteToMemory())
+ StoreGroups.insert(Group);
+
+ for (auto II = std::next(I); II != E; ++II) {
+ Instruction *B = II->first;
+ StrideDescriptor DesB = II->second;
+
+ // Ignore if B is already in a group or B is a different memory operation.
+ if (isInterleaved(B) || A->mayReadFromMemory() != B->mayReadFromMemory())
+ continue;
+
+ // Check the rule 1 and 2.
+ if (DesB.Stride != DesA.Stride || DesB.Size != DesA.Size)
+ continue;
+
+ // Calculate the distance and prepare for the rule 3.
+ const SCEVConstant *DistToA =
+ dyn_cast<SCEVConstant>(SE->getMinusSCEV(DesB.Scev, DesA.Scev));
+ if (!DistToA)
+ continue;
+
+ int DistanceToA = DistToA->getValue()->getValue().getSExtValue();
+
+ // Skip if the distance is not multiple of size as they are not in the
+ // same group.
+ if (DistanceToA % static_cast<int>(DesA.Size))
+ continue;
+
+ // The index of B is the index of A plus the related index to A.
+ int IndexB =
+ Group->getIndex(A) + DistanceToA / static_cast<int>(DesA.Size);
+
+ // Try to insert B into the group.
+ if (Group->insertMember(B, IndexB, DesB.Align)) {
+ DEBUG(dbgs() << "LV: Inserted:" << *B << '\n'
+ << " into the interleave group with" << *A << '\n');
+ InterleaveGroupMap[B] = Group;
+
+ // Set the first load in program order as the insert position.
+ if (B->mayReadFromMemory())
+ Group->setInsertPos(B);
+ }
+ } // Iteration on instruction B
+ } // Iteration on instruction A
+
+ // Remove interleaved store groups with gaps.
+ for (InterleaveGroup *Group : StoreGroups)
+ if (Group->getNumMembers() != Group->getFactor())
+ releaseGroup(Group);
+}
+
LoopVectorizationCostModel::VectorizationFactor
LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize) {
// Width 1 means no vectorize
VectorizationFactor Factor = { 1U, 0U };
- if (OptForSize && Legal->getRuntimePointerCheck()->Need) {
+ if (OptForSize && Legal->getRuntimePointerChecking()->Need) {
emitAnalysis(VectorizationReport() <<
"runtime pointer checks needed. Enable vectorization of this "
"loop with '#pragma clang loop vectorize(enable)' when "
- "compiling with -Os");
- DEBUG(dbgs() << "LV: Aborting. Runtime ptr check is required in Os.\n");
+ "compiling with -Os/-Oz");
+ DEBUG(dbgs() <<
+ "LV: Aborting. Runtime ptr check is required with -Os/-Oz.\n");
return Factor;
}
unsigned TC = SE->getSmallConstantTripCount(TheLoop);
DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
+ MinBWs = computeMinimumValueSizes(TheLoop->getBlocks(), *DB, &TTI);
unsigned WidestType = getWidestType();
unsigned WidestRegister = TTI.getRegisterBitWidth(true);
unsigned MaxSafeDepDist = -1U;
emitAnalysis
(VectorizationReport() <<
"unable to calculate the loop count due to complex control flow");
- DEBUG(dbgs() << "LV: Aborting. A tail loop is required in Os.\n");
+ DEBUG(dbgs() << "LV: Aborting. A tail loop is required with -Os/-Oz.\n");
return Factor;
}
if (VF == 0)
VF = MaxVectorSize;
-
- // If the trip count that we found modulo the vectorization factor is not
- // zero then we require a tail.
- if (VF < 2) {
+ else {
+ // If the trip count that we found modulo the vectorization factor is not
+ // zero then we require a tail.
emitAnalysis(VectorizationReport() <<
"cannot optimize for size and vectorize at the "
"same time. Enable vectorization of this loop "
"with '#pragma clang loop vectorize(enable)' "
- "when compiling with -Os");
- DEBUG(dbgs() << "LV: Aborting. A tail loop is required in Os.\n");
+ "when compiling with -Os/-Oz");
+ DEBUG(dbgs() << "LV: Aborting. A tail loop is required with -Os/-Oz.\n");
return Factor;
}
}
for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
Type *T = it->getType();
- // Ignore ephemeral values.
- if (EphValues.count(it))
+ // Skip ignored values.
+ if (ValuesToIgnore.count(&*it))
continue;
// Only examine Loads, Stores and PHINodes.
if (!isa<LoadInst>(it) && !isa<StoreInst>(it) && !isa<PHINode>(it))
continue;
- // Examine PHI nodes that are reduction variables.
- if (PHINode *PN = dyn_cast<PHINode>(it))
+ // Examine PHI nodes that are reduction variables. Update the type to
+ // account for the recurrence type.
+ if (PHINode *PN = dyn_cast<PHINode>(it)) {
if (!Legal->getReductionVars()->count(PN))
continue;
+ RecurrenceDescriptor RdxDesc = (*Legal->getReductionVars())[PN];
+ T = RdxDesc.getRecurrenceType();
+ }
// Examine the stored values.
if (StoreInst *ST = dyn_cast<StoreInst>(it))
// Ignore loaded pointer types and stored pointer types that are not
// consecutive. However, we do want to take consecutive stores/loads of
// pointer vectors into account.
- if (T->isPointerTy() && !isConsecutiveLoadOrStore(it))
+ if (T->isPointerTy() && !isConsecutiveLoadOrStore(&*it))
continue;
MaxWidth = std::max(MaxWidth,
return MaxWidth;
}
-unsigned
-LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
- unsigned VF,
- unsigned LoopCost) {
+unsigned LoopVectorizationCostModel::selectInterleaveCount(bool OptForSize,
+ unsigned VF,
+ unsigned LoopCost) {
- // -- The unroll heuristics --
- // We unroll the loop in order to expose ILP and reduce the loop overhead.
+ // -- The interleave heuristics --
+ // We interleave the loop in order to expose ILP and reduce the loop overhead.
// There are many micro-architectural considerations that we can't predict
// at this level. For example, frontend pressure (on decode or fetch) due to
// code size, or the number and capabilities of the execution ports.
//
- // We use the following heuristics to select the unroll factor:
- // 1. If the code has reductions, then we unroll in order to break the cross
+ // We use the following heuristics to select the interleave count:
+ // 1. If the code has reductions, then we interleave to break the cross
// iteration dependency.
- // 2. If the loop is really small, then we unroll in order to reduce the loop
+ // 2. If the loop is really small, then we interleave to reduce the loop
// overhead.
- // 3. We don't unroll if we think that we will spill registers to memory due
- // to the increased register pressure.
+ // 3. We don't interleave if we think that we will spill registers to memory
+ // due to the increased register pressure.
- // Use the user preference, unless 'auto' is selected.
- int UserUF = Hints->getInterleave();
- if (UserUF != 0)
- return UserUF;
-
- // When we optimize for size, we don't unroll.
+ // When we optimize for size, we don't interleave.
if (OptForSize)
return 1;
- // We used the distance for the unroll factor.
+ // We used the distance for the interleave count.
if (Legal->getMaxSafeDepDistBytes() != -1U)
return 1;
- // Do not unroll loops with a relatively small trip count.
+ // Do not interleave loops with a relatively small trip count.
unsigned TC = SE->getSmallConstantTripCount(TheLoop);
- if (TC > 1 && TC < TinyTripCountUnrollThreshold)
+ if (TC > 1 && TC < TinyTripCountInterleaveThreshold)
return 1;
unsigned TargetNumRegisters = TTI.getNumberOfRegisters(VF > 1);
R.MaxLocalUsers = std::max(R.MaxLocalUsers, 1U);
R.NumInstructions = std::max(R.NumInstructions, 1U);
- // We calculate the unroll factor using the following formula.
+ // We calculate the interleave count using the following formula.
// Subtract the number of loop invariants from the number of available
- // registers. These registers are used by all of the unrolled instances.
+ // registers. These registers are used by all of the interleaved instances.
// Next, divide the remaining registers by the number of registers that is
// required by the loop, in order to estimate how many parallel instances
// fit without causing spills. All of this is rounded down if necessary to be
- // a power of two. We want power of two unroll factors to simplify any
+ // a power of two. We want power of two interleave count to simplify any
// addressing operations or alignment considerations.
- unsigned UF = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs) /
+ unsigned IC = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs) /
R.MaxLocalUsers);
- // Don't count the induction variable as unrolled.
+ // Don't count the induction variable as interleaved.
if (EnableIndVarRegisterHeur)
- UF = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs - 1) /
+ IC = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs - 1) /
std::max(1U, (R.MaxLocalUsers - 1)));
- // Clamp the unroll factor ranges to reasonable factors.
- unsigned MaxInterleaveSize = TTI.getMaxInterleaveFactor();
+ // Clamp the interleave ranges to reasonable counts.
+ unsigned MaxInterleaveCount = TTI.getMaxInterleaveFactor(VF);
- // Check if the user has overridden the unroll max.
+ // Check if the user has overridden the max.
if (VF == 1) {
if (ForceTargetMaxScalarInterleaveFactor.getNumOccurrences() > 0)
- MaxInterleaveSize = ForceTargetMaxScalarInterleaveFactor;
+ MaxInterleaveCount = ForceTargetMaxScalarInterleaveFactor;
} else {
if (ForceTargetMaxVectorInterleaveFactor.getNumOccurrences() > 0)
- MaxInterleaveSize = ForceTargetMaxVectorInterleaveFactor;
+ MaxInterleaveCount = ForceTargetMaxVectorInterleaveFactor;
}
// If we did not calculate the cost for VF (because the user selected the VF)
if (LoopCost == 0)
LoopCost = expectedCost(VF);
- // Clamp the calculated UF to be between the 1 and the max unroll factor
+ // Clamp the calculated IC to be between the 1 and the max interleave count
// that the target allows.
- if (UF > MaxInterleaveSize)
- UF = MaxInterleaveSize;
- else if (UF < 1)
- UF = 1;
+ if (IC > MaxInterleaveCount)
+ IC = MaxInterleaveCount;
+ else if (IC < 1)
+ IC = 1;
- // Unroll if we vectorized this loop and there is a reduction that could
- // benefit from unrolling.
+ // Interleave if we vectorized this loop and there is a reduction that could
+ // benefit from interleaving.
if (VF > 1 && Legal->getReductionVars()->size()) {
- DEBUG(dbgs() << "LV: Unrolling because of reductions.\n");
- return UF;
+ DEBUG(dbgs() << "LV: Interleaving because of reductions.\n");
+ return IC;
}
// Note that if we've already vectorized the loop we will have done the
- // runtime check and so unrolling won't require further checks.
- bool UnrollingRequiresRuntimePointerCheck =
- (VF == 1 && Legal->getRuntimePointerCheck()->Need);
+ // runtime check and so interleaving won't require further checks.
+ bool InterleavingRequiresRuntimePointerCheck =
+ (VF == 1 && Legal->getRuntimePointerChecking()->Need);
- // We want to unroll small loops in order to reduce the loop overhead and
+ // We want to interleave small loops in order to reduce the loop overhead and
// potentially expose ILP opportunities.
DEBUG(dbgs() << "LV: Loop cost is " << LoopCost << '\n');
- if (!UnrollingRequiresRuntimePointerCheck &&
- LoopCost < SmallLoopCost) {
+ if (!InterleavingRequiresRuntimePointerCheck && LoopCost < SmallLoopCost) {
// We assume that the cost overhead is 1 and we use the cost model
- // to estimate the cost of the loop and unroll until the cost of the
+ // to estimate the cost of the loop and interleave until the cost of the
// loop overhead is about 5% of the cost of the loop.
- unsigned SmallUF = std::min(UF, (unsigned)PowerOf2Floor(SmallLoopCost / LoopCost));
+ unsigned SmallIC =
+ std::min(IC, (unsigned)PowerOf2Floor(SmallLoopCost / LoopCost));
- // Unroll until store/load ports (estimated by max unroll factor) are
+ // Interleave until store/load ports (estimated by max interleave count) are
// saturated.
unsigned NumStores = Legal->getNumStores();
unsigned NumLoads = Legal->getNumLoads();
- unsigned StoresUF = UF / (NumStores ? NumStores : 1);
- unsigned LoadsUF = UF / (NumLoads ? NumLoads : 1);
+ unsigned StoresIC = IC / (NumStores ? NumStores : 1);
+ unsigned LoadsIC = IC / (NumLoads ? NumLoads : 1);
// If we have a scalar reduction (vector reductions are already dealt with
// by this point), we can increase the critical path length if the loop
- // we're unrolling is inside another loop. Limit, by default to 2, so the
+ // we're interleaving is inside another loop. Limit, by default to 2, so the
// critical path only gets increased by one reduction operation.
if (Legal->getReductionVars()->size() &&
TheLoop->getLoopDepth() > 1) {
- unsigned F = static_cast<unsigned>(MaxNestedScalarReductionUF);
- SmallUF = std::min(SmallUF, F);
- StoresUF = std::min(StoresUF, F);
- LoadsUF = std::min(LoadsUF, F);
+ unsigned F = static_cast<unsigned>(MaxNestedScalarReductionIC);
+ SmallIC = std::min(SmallIC, F);
+ StoresIC = std::min(StoresIC, F);
+ LoadsIC = std::min(LoadsIC, F);
}
- if (EnableLoadStoreRuntimeUnroll && std::max(StoresUF, LoadsUF) > SmallUF) {
- DEBUG(dbgs() << "LV: Unrolling to saturate store or load ports.\n");
- return std::max(StoresUF, LoadsUF);
+ if (EnableLoadStoreRuntimeInterleave &&
+ std::max(StoresIC, LoadsIC) > SmallIC) {
+ DEBUG(dbgs() << "LV: Interleaving to saturate store or load ports.\n");
+ return std::max(StoresIC, LoadsIC);
}
- DEBUG(dbgs() << "LV: Unrolling to reduce branch cost.\n");
- return SmallUF;
+ DEBUG(dbgs() << "LV: Interleaving to reduce branch cost.\n");
+ return SmallIC;
}
- // Unroll if this is a large loop (small loops are already dealt with by this
- // point) that could benefit from interleaved unrolling.
+ // Interleave if this is a large loop (small loops are already dealt with by
+ // this
+ // point) that could benefit from interleaving.
bool HasReductions = (Legal->getReductionVars()->size() > 0);
if (TTI.enableAggressiveInterleaving(HasReductions)) {
- DEBUG(dbgs() << "LV: Unrolling to expose ILP.\n");
- return UF;
+ DEBUG(dbgs() << "LV: Interleaving to expose ILP.\n");
+ return IC;
}
- DEBUG(dbgs() << "LV: Not Unrolling.\n");
+ DEBUG(dbgs() << "LV: Not Interleaving.\n");
return 1;
}
for (LoopBlocksDFS::RPOIterator bb = DFS.beginRPO(),
be = DFS.endRPO(); bb != be; ++bb) {
R.NumInstructions += (*bb)->size();
- for (BasicBlock::iterator it = (*bb)->begin(), e = (*bb)->end(); it != e;
- ++it) {
- Instruction *I = it;
- IdxToInstr[Index++] = I;
+ for (Instruction &I : **bb) {
+ IdxToInstr[Index++] = &I;
// Save the end location of each USE.
- for (unsigned i = 0; i < I->getNumOperands(); ++i) {
- Value *U = I->getOperand(i);
+ for (unsigned i = 0; i < I.getNumOperands(); ++i) {
+ Value *U = I.getOperand(i);
Instruction *Instr = dyn_cast<Instruction>(U);
// Ignore non-instruction values such as arguments, constants, etc.
// Ignore instructions that are never used within the loop.
if (!Ends.count(I)) continue;
- // Ignore ephemeral values.
- if (EphValues.count(I))
+ // Skip ignored values.
+ if (ValuesToIgnore.count(I))
continue;
// Remove all of the instructions that end at this location.
if (isa<DbgInfoIntrinsic>(it))
continue;
- // Ignore ephemeral values.
- if (EphValues.count(it))
+ // Skip ignored values.
+ if (ValuesToIgnore.count(&*it))
continue;
- unsigned C = getInstructionCost(it, VF);
+ unsigned C = getInstructionCost(&*it, VF);
// Check if we should override the cost.
if (ForceTargetInstructionCost.getNumOccurrences() > 0)
}
static bool isStrideMul(Instruction *I, LoopVectorizationLegality *Legal) {
- if (Legal->hasStride(I->getOperand(0)) || Legal->hasStride(I->getOperand(1)))
- return true;
- return false;
+ return Legal->hasStride(I->getOperand(0)) ||
+ Legal->hasStride(I->getOperand(1));
}
unsigned
VF = 1;
Type *RetTy = I->getType();
+ if (VF > 1 && MinBWs.count(I))
+ RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
Type *VectorTy = ToVectorTy(RetTy, VF);
// TODO: We need to estimate the cost of intrinsic calls.
case Instruction::ICmp:
case Instruction::FCmp: {
Type *ValTy = I->getOperand(0)->getType();
+ if (VF > 1 && MinBWs.count(dyn_cast<Instruction>(I->getOperand(0))))
+ ValTy = IntegerType::get(ValTy->getContext(), MinBWs[I]);
VectorTy = ToVectorTy(ValTy, VF);
return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy);
}
return TTI.getAddressComputationCost(VectorTy) +
TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);
+ // For an interleaved access, calculate the total cost of the whole
+ // interleave group.
+ if (Legal->isAccessInterleaved(I)) {
+ auto Group = Legal->getInterleavedAccessGroup(I);
+ assert(Group && "Fail to get an interleaved access group.");
+
+ // Only calculate the cost once at the insert position.
+ if (Group->getInsertPos() != I)
+ return 0;
+
+ unsigned InterleaveFactor = Group->getFactor();
+ Type *WideVecTy =
+ VectorType::get(VectorTy->getVectorElementType(),
+ VectorTy->getVectorNumElements() * InterleaveFactor);
+
+ // Holds the indices of existing members in an interleaved load group.
+ // An interleaved store group doesn't need this as it dones't allow gaps.
+ SmallVector<unsigned, 4> Indices;
+ if (LI) {
+ for (unsigned i = 0; i < InterleaveFactor; i++)
+ if (Group->getMember(i))
+ Indices.push_back(i);
+ }
+
+ // Calculate the cost of the whole interleaved group.
+ unsigned Cost = TTI.getInterleavedMemoryOpCost(
+ I->getOpcode(), WideVecTy, Group->getFactor(), Indices,
+ Group->getAlignment(), AS);
+
+ if (Group->isReverse())
+ Cost +=
+ Group->getNumMembers() *
+ TTI.getShuffleCost(TargetTransformInfo::SK_Reverse, VectorTy, 0);
+
+ // FIXME: The interleaved load group with a huge gap could be even more
+ // expensive than scalar operations. Then we could ignore such group and
+ // use scalar operations instead.
+ return Cost;
+ }
+
// Scalarized loads/stores.
int ConsecutiveStride = Legal->isConsecutivePtr(Ptr);
bool Reverse = ConsecutiveStride < 0;
Legal->isInductionVariable(I->getOperand(0)))
return TTI.getCastInstrCost(I->getOpcode(), I->getType(),
I->getOperand(0)->getType());
-
- Type *SrcVecTy = ToVectorTy(I->getOperand(0)->getType(), VF);
+
+ Type *SrcScalarTy = I->getOperand(0)->getType();
+ Type *SrcVecTy = ToVectorTy(SrcScalarTy, VF);
+ if (VF > 1 && MinBWs.count(I)) {
+ // This cast is going to be shrunk. This may remove the cast or it might
+ // turn it into slightly different cast. For example, if MinBW == 16,
+ // "zext i8 %1 to i32" becomes "zext i8 %1 to i16".
+ //
+ // Calculate the modified src and dest types.
+ Type *MinVecTy = VectorTy;
+ if (I->getOpcode() == Instruction::Trunc) {
+ SrcVecTy = smallestIntegerVectorType(SrcVecTy, MinVecTy);
+ VectorTy = largestIntegerVectorType(ToVectorTy(I->getType(), VF),
+ MinVecTy);
+ } else if (I->getOpcode() == Instruction::ZExt ||
+ I->getOpcode() == Instruction::SExt) {
+ SrcVecTy = largestIntegerVectorType(SrcVecTy, MinVecTy);
+ VectorTy = smallestIntegerVectorType(ToVectorTy(I->getType(), VF),
+ MinVecTy);
+ }
+ }
+
return TTI.getCastInstrCost(I->getOpcode(), VectorTy, SrcVecTy);
}
case Instruction::Call: {
static const char lv_name[] = "Loop Vectorization";
INITIALIZE_PASS_BEGIN(LoopVectorize, LV_NAME, lv_name, false, false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
-INITIALIZE_AG_DEPENDENCY(AliasAnalysis)
+INITIALIZE_PASS_DEPENDENCY(BasicAAWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
-INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfo)
+INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
-INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
+INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_DEPENDENCY(LoopAccessAnalysis)
+INITIALIZE_PASS_DEPENDENCY(DemandedBits)
INITIALIZE_PASS_END(LoopVectorize, LV_NAME, lv_name, false, false)
namespace llvm {
// Create a new entry in the WidenMap and initialize it to Undef or Null.
VectorParts &VecResults = WidenMap.splat(Instr, UndefVec);
- Instruction *InsertPt = Builder.GetInsertPoint();
- BasicBlock *IfBlock = Builder.GetInsertBlock();
- BasicBlock *CondBlock = nullptr;
-
VectorParts Cond;
- Loop *VectorLp = nullptr;
if (IfPredicateStore) {
assert(Instr->getParent()->getSinglePredecessor() &&
"Only support single predecessor blocks");
Cond = createEdgeMask(Instr->getParent()->getSinglePredecessor(),
Instr->getParent());
- VectorLp = LI->getLoopFor(IfBlock);
- assert(VectorLp && "Must have a loop for this block");
}
// For each vector unroll 'part':
Builder.CreateExtractElement(Cond[Part], Builder.getInt32(0));
Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Cond[Part],
ConstantInt::get(Cond[Part]->getType(), 1));
- CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
- LoopVectorBody.push_back(CondBlock);
- VectorLp->addBasicBlockToLoop(CondBlock, *LI);
- // Update Builder with newly created basic block.
- Builder.SetInsertPoint(InsertPt);
}
Instruction *Cloned = Instr->clone();
if (!IsVoidRetTy)
VecResults[Part] = Cloned;
- // End if-block.
- if (IfPredicateStore) {
- BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
- LoopVectorBody.push_back(NewIfBlock);
- VectorLp->addBasicBlockToLoop(NewIfBlock, *LI);
- Builder.SetInsertPoint(InsertPt);
- Instruction *OldBr = IfBlock->getTerminator();
- BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
- OldBr->eraseFromParent();
- IfBlock = NewIfBlock;
- }
+ // End if-block.
+ if (IfPredicateStore)
+ PredicatedStores.push_back(std::make_pair(cast<StoreInst>(Cloned),
+ Cmp));
}
}
projects / oota-llvm.git / blobdiff