maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Reapply 184685 after the SetVector iteration order fix. 

This should hopefully have fixed the stage2/stage3 miscompare on the dragonegg
testers.

"LoopVectorize: Use the dependence test utility class

We now no longer need alias analysis - the cases that alias analysis would
handle are now handled as accesses with a large dependence distance.

We can now vectorize loops with simple constant dependence distances.

  for (i = 8; i < 256; ++i) {
    a[i] = a[i+4] * a[i+8];
  }

  for (i = 8; i < 256; ++i) {
    a[i] = a[i-4] * a[i-8];
  }

We would be able to vectorize about 200 more loops (in many cases the cost model
instructs us no to) in the test suite now. Results on x86-64 are a wash.

I have seen one degradation in ammp. Interestingly, the function in which we
now vectorize a loop is never executed so we probably see some instruction
cache effects. There is a 2% improvement in h264ref. There is one or the other
TSCV loop kernel that speeds up.

radar://13681598"

llvm-svn: 184724
This commit is contained in:
Arnold Schwaighofer 2013-06-24 12:09:15 +00:00
parent 91472fa4fc
commit b252c11ccc
4 changed files with 328 additions and 234 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

336
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -55,7 +55,6 @@
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AliasSetTracker.h"
#include "llvm/Analysis/Dominators.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
@ -410,11 +409,10 @@ bool LoadHoisting::canHoistAllLoads() {
class LoopVectorizationLegality {
public:
LoopVectorizationLegality(Loop *L, ScalarEvolution *SE, DataLayout *DL,
DominatorTree *DT, TargetTransformInfo* TTI,
AliasAnalysis *AA, TargetLibraryInfo *TLI)
: TheLoop(L), SE(SE), DL(DL), DT(DT), TTI(TTI), AA(AA), TLI(TLI),
DominatorTree *DT, TargetLibraryInfo *TLI)
: TheLoop(L), SE(SE), DL(DL), DT(DT), TLI(TLI),
Induction(0), WidestIndTy(0), HasFunNoNaNAttr(false),
LoadSpeculation(L, DT) {}
MaxSafeDepDistBytes(-1U), LoadSpeculation(L, DT) {}
/// This enum represents the kinds of reductions that we support.
enum ReductionKind {
@ -501,7 +499,8 @@ public:
}
/// Insert a pointer and calculate the start and end SCEVs.
void insert(ScalarEvolution *SE, Loop *Lp, Value *Ptr, bool WritePtr);
void insert(ScalarEvolution *SE, Loop *Lp, Value *Ptr, bool WritePtr,
unsigned DepSetId);
/// This flag indicates if we need to add the runtime check.
bool Need;
@ -513,6 +512,9 @@ public:
SmallVector<const SCEV*, 2> Ends;
/// Holds the information if this pointer is used for writing to memory.
SmallVector<bool, 2> IsWritePtr;
/// Holds the id of the set of pointers that could be dependent because of a
/// shared underlying object.
SmallVector<unsigned, 2> DependencySetId;
};
/// A POD for saving information about induction variables.
@ -533,11 +535,6 @@ public:
/// induction descriptor.
typedef MapVector<PHINode*, InductionInfo> InductionList;
/// Alias(Multi)Map stores the values (GEPs or underlying objects and their
/// respective Store/Load instruction(s) to calculate aliasing.
typedef MapVector<Value*, Instruction* > AliasMap;
typedef DenseMap<Value*, std::vector<Instruction*> > AliasMultiMap;
/// 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.
@ -584,6 +581,9 @@ public:
/// This function returns the identity element (or neutral element) for
/// the operation K.
static Constant *getReductionIdentity(ReductionKind K, Type *Tp);
unsigned getMaxSafeDepDistBytes() { return MaxSafeDepDistBytes; }
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
@ -624,16 +624,6 @@ private:
/// Returns the induction kind of Phi. This function may return NoInduction
/// if the PHI is not an induction variable.
InductionKind isInductionVariable(PHINode *Phi);
/// Return true if can compute the address bounds of Ptr within the loop.
bool hasComputableBounds(Value *Ptr);
/// Return true if there is the chance of write reorder.
bool hasPossibleGlobalWriteReorder(Value *Object,
Instruction *Inst,
AliasMultiMap &WriteObjects,
unsigned MaxByteWidth);
/// Return the AA location for a load or a store.
AliasAnalysis::Location getLoadStoreLocation(Instruction *Inst);
/// The loop that we evaluate.
Loop *TheLoop;
@ -643,10 +633,6 @@ private:
DataLayout *DL;
/// Dominators.
DominatorTree *DT;
/// Target Info.
TargetTransformInfo *TTI;
/// Alias Analysis.
AliasAnalysis *AA;
/// Target Library Info.
TargetLibraryInfo *TLI;
@ -676,6 +662,8 @@ private:
/// Can we assume the absence of NaNs.
bool HasFunNoNaNAttr;
unsigned MaxSafeDepDistBytes;
/// Utility to determine whether loads can be speculated.
LoadHoisting LoadSpeculation;
};
@ -904,7 +892,6 @@ struct LoopVectorize : public LoopPass {
LoopInfo *LI;
TargetTransformInfo *TTI;
DominatorTree *DT;
AliasAnalysis *AA;
TargetLibraryInfo *TLI;
virtual bool runOnLoop(Loop *L, LPPassManager &LPM) {
@ -917,7 +904,6 @@ struct LoopVectorize : public LoopPass {
LI = &getAnalysis<LoopInfo>();
TTI = &getAnalysis<TargetTransformInfo>();
DT = &getAnalysis<DominatorTree>();
AA = getAnalysisIfAvailable<AliasAnalysis>();
TLI = getAnalysisIfAvailable<TargetLibraryInfo>();
if (DL == NULL) {
@ -936,7 +922,7 @@ struct LoopVectorize : public LoopPass {
}
// Check if it is legal to vectorize the loop.
LoopVectorizationLegality LVL(L, SE, DL, DT, TTI, AA, TLI);
LoopVectorizationLegality LVL(L, SE, DL, DT, TLI);
if (!LVL.canVectorize()) {
DEBUG(dbgs() << "LV: Not vectorizing.\n");
return false;
@ -1011,7 +997,8 @@ struct LoopVectorize : public LoopPass {
void
LoopVectorizationLegality::RuntimePointerCheck::insert(ScalarEvolution *SE,
Loop *Lp, Value *Ptr,
bool WritePtr) {
bool WritePtr,
unsigned DepSetId) {
const SCEV *Sc = SE->getSCEV(Ptr);
const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Sc);
assert(AR && "Invalid addrec expression");
@ -1021,6 +1008,7 @@ LoopVectorizationLegality::RuntimePointerCheck::insert(ScalarEvolution *SE,
Starts.push_back(AR->getStart());
Ends.push_back(ScEnd);
IsWritePtr.push_back(WritePtr);
DependencySetId.push_back(DepSetId);
}
Value *InnerLoopVectorizer::getBroadcastInstrs(Value *V) {
@ -1358,10 +1346,9 @@ InnerLoopVectorizer::addRuntimeCheck(LoopVectorizationLegality *Legal,
if (!PtrRtCheck->Need)
return NULL;
Instruction *MemoryRuntimeCheck = 0;
unsigned NumPointers = PtrRtCheck->Pointers.size();
SmallVector<Value* , 2> Starts;
SmallVector<Value* , 2> Ends;
SmallVector<TrackingVH<Value> , 2> Starts;
SmallVector<TrackingVH<Value> , 2> Ends;
SCEVExpander Exp(*SE, "induction");
@ -1388,13 +1375,18 @@ InnerLoopVectorizer::addRuntimeCheck(LoopVectorizationLegality *Legal,
}
IRBuilder<> ChkBuilder(Loc);
// Our instructions might fold to a constant.
Value *MemoryRuntimeCheck = 0;
for (unsigned i = 0; i < NumPointers; ++i) {
for (unsigned j = i+1; j < NumPointers; ++j) {
// No need to check if two readonly pointers intersect.
if (!PtrRtCheck->IsWritePtr[i] && !PtrRtCheck->IsWritePtr[j])
continue;
// Only need to check pointers between two different dependency sets.
if (PtrRtCheck->DependencySetId[i] == PtrRtCheck->DependencySetId[j])
continue;
Value *Start0 = ChkBuilder.CreateBitCast(Starts[i], PtrArithTy, "bc");
Value *Start1 = ChkBuilder.CreateBitCast(Starts[j], PtrArithTy, "bc");
Value *End0 = ChkBuilder.CreateBitCast(Ends[i], PtrArithTy, "bc");
@ -1406,12 +1398,18 @@ InnerLoopVectorizer::addRuntimeCheck(LoopVectorizationLegality *Legal,
if (MemoryRuntimeCheck)
IsConflict = ChkBuilder.CreateOr(MemoryRuntimeCheck, IsConflict,
"conflict.rdx");
MemoryRuntimeCheck = cast<Instruction>(IsConflict);
MemoryRuntimeCheck = IsConflict;
}
}
return MemoryRuntimeCheck;
// We have to do this trickery because the IRBuilder might fold the check to a
// constant expression in which case there is no Instruction anchored in a
// the block.
LLVMContext &Ctx = Loc->getContext();
Instruction * Check = BinaryOperator::CreateAnd(MemoryRuntimeCheck,
ConstantInt::getTrue(Ctx));
ChkBuilder.Insert(Check, "memcheck.conflict");
return Check;
}
void
@ -2982,7 +2980,7 @@ bool AccessAnalysis::canCheckPtrAtRT(
// Each access has its own dependence set.
DepId = RunningDepId++;
//RtCheck.insert(SE, TheLoop, Ptr, IsWrite, DepId);
RtCheck.insert(SE, TheLoop, Ptr, IsWrite, DepId);
DEBUG(dbgs() << "LV: Found a runtime check ptr:" << *Ptr <<"\n");
} else {
@ -3464,53 +3462,29 @@ MemoryDepChecker::areDepsSafe(AccessAnalysis::DepCandidates &AccessSets,
return true;
}
AliasAnalysis::Location
LoopVectorizationLegality::getLoadStoreLocation(Instruction *Inst) {
if (StoreInst *Store = dyn_cast<StoreInst>(Inst))
return AA->getLocation(Store);
else if (LoadInst *Load = dyn_cast<LoadInst>(Inst))
return AA->getLocation(Load);
llvm_unreachable("Should be either load or store instruction");
}
bool
LoopVectorizationLegality::hasPossibleGlobalWriteReorder(
Value *Object,
Instruction *Inst,
AliasMultiMap& WriteObjects,
unsigned MaxByteWidth) {
AliasAnalysis::Location ThisLoc = getLoadStoreLocation(Inst);
std::vector<Instruction*>::iterator
it = WriteObjects[Object].begin(),
end = WriteObjects[Object].end();
for (; it != end; ++it) {
Instruction* I = *it;
if (I == Inst)
continue;
AliasAnalysis::Location ThatLoc = getLoadStoreLocation(I);
if (AA->alias(ThisLoc.getWithNewSize(MaxByteWidth),
ThatLoc.getWithNewSize(MaxByteWidth)))
return true;
}
return false;
}
bool LoopVectorizationLegality::canVectorizeMemory() {
typedef SmallVector<Value*, 16> ValueVector;
typedef SmallPtrSet<Value*, 16> ValueSet;
// Stores a pair of memory access location and whether the access is a store
// (true) or a load (false).
typedef std::pair<Value*, char> MemAccessInfo;
typedef DenseSet<MemAccessInfo> PtrAccessSet;
// Holds the Load and Store *instructions*.
ValueVector Loads;
ValueVector Stores;
// Holds all the different accesses in the loop.
unsigned NumReads = 0;
unsigned NumReadWrites = 0;
PtrRtCheck.Pointers.clear();
PtrRtCheck.Need = false;
const bool IsAnnotatedParallel = TheLoop->isAnnotatedParallel();
MemoryDepChecker DepChecker(SE, DL, TheLoop);
// For each block.
for (Loop::block_iterator bb = TheLoop->block_begin(),
@ -3531,6 +3505,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return false;
}
Loads.push_back(Ld);
DepChecker.addAccess(Ld);
continue;
}
@ -3543,6 +3518,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return false;
}
Stores.push_back(St);
DepChecker.addAccess(St);
}
} // next instr.
} // next block.
@ -3557,10 +3533,8 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return true;
}
// Holds the read and read-write *pointers* that we find. These maps hold
// unique values for pointers (so no need for multi-map).
AliasMap Reads;
AliasMap ReadWrites;
AccessAnalysis::DepCandidates DependentAccesses;
AccessAnalysis Accesses(DL, DependentAccesses);
// Holds the analyzed pointers. We don't want to call GetUnderlyingObjects
// multiple times on the same object. If the ptr is accessed twice, once
@ -3579,10 +3553,12 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return false;
}
// If we did *not* see this pointer before, insert it to
// the read-write list. At this phase it is only a 'write' list.
if (Seen.insert(Ptr))
ReadWrites.insert(std::make_pair(Ptr, ST));
// If we did *not* see this pointer before, insert it to the read-write
// list. At this phase it is only a 'write' list.
if (Seen.insert(Ptr)) {
++NumReadWrites;
Accesses.addStore(Ptr);
}
}
if (IsAnnotatedParallel) {
@ -3592,6 +3568,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return true;
}
SmallPtrSet<Value *, 16> ReadOnlyPtr;
for (I = Loads.begin(), IE = Loads.end(); I != IE; ++I) {
LoadInst *LD = cast<LoadInst>(*I);
Value* Ptr = LD->getPointerOperand();
@ -3603,51 +3580,44 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
// If the address of i is unknown (for example A[B[i]]) then we may
// read a few words, modify, and write a few words, and some of the
// words may be written to the same address.
if (Seen.insert(Ptr) || 0 == isConsecutivePtr(Ptr))
Reads.insert(std::make_pair(Ptr, LD));
bool IsReadOnlyPtr = false;
if (Seen.insert(Ptr) || !isStridedPtr(SE, DL, Ptr, TheLoop)) {
++NumReads;
IsReadOnlyPtr = true;
}
Accesses.addLoad(Ptr, IsReadOnlyPtr);
}
// If we write (or read-write) to a single destination and there are no
// other reads in this loop then is it safe to vectorize.
if (ReadWrites.size() == 1 && Reads.size() == 0) {
if (NumReadWrites == 1 && NumReads == 0) {
DEBUG(dbgs() << "LV: Found a write-only loop!\n");
return true;
}
unsigned NumReadPtrs = 0;
unsigned NumWritePtrs = 0;
// Build dependence sets and check whether we need a runtime pointer bounds
// check.
Accesses.buildDependenceSets();
bool NeedRTCheck = Accesses.isRTCheckNeeded();
// Find pointers with computable bounds. We are going to use this information
// to place a runtime bound check.
bool CanDoRT = true;
AliasMap::iterator MI, ME;
for (MI = ReadWrites.begin(), ME = ReadWrites.end(); MI != ME; ++MI) {
Value *V = (*MI).first;
if (hasComputableBounds(V)) {
PtrRtCheck.insert(SE, TheLoop, V, true);
NumWritePtrs++;
DEBUG(dbgs() << "LV: Found a runtime check ptr:" << *V <<"\n");
} else {
CanDoRT = false;
break;
}
}
for (MI = Reads.begin(), ME = Reads.end(); MI != ME; ++MI) {
Value *V = (*MI).first;
if (hasComputableBounds(V)) {
PtrRtCheck.insert(SE, TheLoop, V, false);
NumReadPtrs++;
DEBUG(dbgs() << "LV: Found a runtime check ptr:" << *V <<"\n");
} else {
CanDoRT = false;
break;
}
}
unsigned NumComparisons = 0;
bool CanDoRT = false;
if (NeedRTCheck)
CanDoRT = Accesses.canCheckPtrAtRT(PtrRtCheck, NumComparisons, SE, TheLoop);
// Check that we did not collect too many pointers or found a
// unsizeable pointer.
unsigned NumComparisons = (NumWritePtrs * (NumReadPtrs + NumWritePtrs - 1));
DEBUG(dbgs() << "LV: We need to compare " << NumComparisons << " ptrs.\n");
DEBUG(dbgs() << "LV: We need to do " << NumComparisons <<
" pointer comparisons.\n");
// If we only have one set of dependences to check pointers among we don't
// need a runtime check.
if (NumComparisons == 0 && NeedRTCheck)
NeedRTCheck = false;
// Check that we did not collect too many pointers or found a unsizeable
// pointer.
if (!CanDoRT || NumComparisons > RuntimeMemoryCheckThreshold) {
PtrRtCheck.reset();
CanDoRT = false;
@ -3657,113 +3627,6 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
DEBUG(dbgs() << "LV: We can perform a memory runtime check if needed.\n");
}
bool NeedRTCheck = false;
// Biggest vectorized access possible, vector width * unroll factor.
// TODO: We're being very pessimistic here, find a way to know the
// real access width before getting here.
unsigned MaxByteWidth = (TTI->getRegisterBitWidth(true) / 8) *
TTI->getMaximumUnrollFactor();
// Now that the pointers are in two lists (Reads and ReadWrites), we
// can check that there are no conflicts between each of the writes and
// between the writes to the reads.
// Note that WriteObjects duplicates the stores (indexed now by underlying
// objects) to avoid pointing to elements inside ReadWrites.
// TODO: Maybe create a new type where they can interact without duplication.
AliasMultiMap WriteObjects;
ValueVector TempObjects;
// Check that the read-writes do not conflict with other read-write
// pointers.
bool AllWritesIdentified = true;
for (MI = ReadWrites.begin(), ME = ReadWrites.end(); MI != ME; ++MI) {
Value *Val = (*MI).first;
Instruction *Inst = (*MI).second;
GetUnderlyingObjects(Val, TempObjects, DL);
for (ValueVector::iterator UI=TempObjects.begin(), UE=TempObjects.end();
UI != UE; ++UI) {
if (!isIdentifiedObject(*UI)) {
DEBUG(dbgs() << "LV: Found an unidentified write ptr:"<< **UI <<"\n");
NeedRTCheck = true;
AllWritesIdentified = false;
}
// Never seen it before, can't alias.
if (WriteObjects[*UI].empty()) {
DEBUG(dbgs() << "LV: Adding Underlying value:" << **UI <<"\n");
WriteObjects[*UI].push_back(Inst);
continue;
}
// Direct alias found.
if (!AA || dyn_cast<GlobalValue>(*UI) == NULL) {
DEBUG(dbgs() << "LV: Found a possible write-write reorder:"
<< **UI <<"\n");
return false;
}
DEBUG(dbgs() << "LV: Found a conflicting global value:"
<< **UI <<"\n");
DEBUG(dbgs() << "LV: While examining store:" << *Inst <<"\n");
DEBUG(dbgs() << "LV: On value:" << *Val <<"\n");
// If global alias, make sure they do alias.
if (hasPossibleGlobalWriteReorder(*UI,
Inst,
WriteObjects,
MaxByteWidth)) {
DEBUG(dbgs() << "LV: Found a possible write-write reorder:" << **UI
<< "\n");
return false;
}
// Didn't alias, insert into map for further reference.
WriteObjects[*UI].push_back(Inst);
}
TempObjects.clear();
}
/// Check that the reads don't conflict with the read-writes.
for (MI = Reads.begin(), ME = Reads.end(); MI != ME; ++MI) {
Value *Val = (*MI).first;
GetUnderlyingObjects(Val, TempObjects, DL);
for (ValueVector::iterator UI=TempObjects.begin(), UE=TempObjects.end();
UI != UE; ++UI) {
// If all of the writes are identified then we don't care if the read
// pointer is identified or not.
if (!AllWritesIdentified && !isIdentifiedObject(*UI)) {
DEBUG(dbgs() << "LV: Found an unidentified read ptr:"<< **UI <<"\n");
NeedRTCheck = true;
}
// Never seen it before, can't alias.
if (WriteObjects[*UI].empty())
continue;
// Direct alias found.
if (!AA || dyn_cast<GlobalValue>(*UI) == NULL) {
DEBUG(dbgs() << "LV: Found a possible write-write reorder:"
<< **UI <<"\n");
return false;
}
DEBUG(dbgs() << "LV: Found a global value: "
<< **UI <<"\n");
Instruction *Inst = (*MI).second;
DEBUG(dbgs() << "LV: While examining load:" << *Inst <<"\n");
DEBUG(dbgs() << "LV: On value:" << *Val <<"\n");
// If global alias, make sure they do alias.
if (hasPossibleGlobalWriteReorder(*UI,
Inst,
WriteObjects,
MaxByteWidth)) {
DEBUG(dbgs() << "LV: Found a possible read-write reorder:" << **UI
<< "\n");
return false;
}
}
TempObjects.clear();
}
PtrRtCheck.Need = NeedRTCheck;
if (NeedRTCheck && !CanDoRT) {
DEBUG(dbgs() << "LV: We can't vectorize because we can't find " <<
"the array bounds.\n");
@ -3771,9 +3634,20 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
return false;
}
PtrRtCheck.Need = NeedRTCheck;
bool CanVecMem = true;
if (Accesses.isDependencyCheckNeeded()) {
DEBUG(dbgs() << "LV: Checking memory dependencies\n");
CanVecMem = DepChecker.areDepsSafe(DependentAccesses,
Accesses.getDependenciesToCheck());
MaxSafeDepDistBytes = DepChecker.getMaxSafeDepDistBytes();
}
DEBUG(dbgs() << "LV: We "<< (NeedRTCheck ? "" : "don't") <<
" need a runtime memory check.\n");
return true;
return CanVecMem;
}
static bool hasMultipleUsesOf(Instruction *I,
@ -4126,15 +4000,6 @@ bool LoopVectorizationLegality::blockCanBePredicated(BasicBlock *BB) {
return true;
}
bool LoopVectorizationLegality::hasComputableBounds(Value *Ptr) {
const SCEV *PhiScev = SE->getSCEV(Ptr);
const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PhiScev);
if (!AR)
return false;
return AR->isAffine();
}
LoopVectorizationCostModel::VectorizationFactor
LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize,
unsigned UserVF) {
@ -4151,6 +4016,10 @@ LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize,
unsigned WidestType = getWidestType();
unsigned WidestRegister = TTI.getRegisterBitWidth(true);
unsigned MaxSafeDepDist = -1U;
if (Legal->getMaxSafeDepDistBytes() != -1U)
MaxSafeDepDist = Legal->getMaxSafeDepDistBytes() * 8;
WidestRegister = WidestRegister < MaxSafeDepDist ? WidestRegister : MaxSafeDepDist;
unsigned MaxVectorSize = WidestRegister / WidestType;
DEBUG(dbgs() << "LV: The Widest type: " << WidestType << " bits.\n");
DEBUG(dbgs() << "LV: The Widest register is:" << WidestRegister << "bits.\n");
@ -4284,6 +4153,10 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
if (OptForSize)
return 1;
// We used the distance for the unroll factor.
if (Legal->getMaxSafeDepDistBytes() != -1U)
return 1;
// Do not unroll loops with a relatively small trip count.
unsigned TC = SE->getSmallConstantTripCount(TheLoop,
TheLoop->getLoopLatch());
@ -4680,7 +4553,6 @@ Type* LoopVectorizationCostModel::ToVectorTy(Type *Scalar, unsigned VF) {
char LoopVectorize::ID = 0;
static const char lv_name[] = "Loop Vectorization";
INITIALIZE_PASS_BEGIN(LoopVectorize, LV_NAME, lv_name, false, false)
INITIALIZE_AG_DEPENDENCY(AliasAnalysis)
INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)

2
llvm/test/Transforms/LoopVectorize/12-12-11-if-conv.ll
View File

@ -30,7 +30,7 @@ if.then: ; preds = %for.body
if.end: ; preds = %for.body, %if.then
%z.0 = phi i32 [ %add1, %if.then ], [ 9, %for.body ]
store i32 %z.0, i32* %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%indvars.iv.next = add nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %x
br i1 %exitcond, label %for.end, label %for.body

222
llvm/test/Transforms/LoopVectorize/memdep.ll Normal file
View File

@ -0,0 +1,222 @@
; RUN: opt < %s -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S | FileCheck %s
; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 -S | FileCheck %s -check-prefix=WIDTH
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
; Vectorization with dependence checks.
; No plausible dependence - can be vectorized.
; for (i = 0; i < 1024; ++i)
; A[i] = A[i + 1] + 1;
; CHECK: f1_vec
; CHECK: <2 x i32>
define void @f1_vec(i32* %A) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%indvars.iv.next = add i32 %indvars.iv, 1
%arrayidx = getelementptr inbounds i32* %A, i32 %indvars.iv.next
%0 = load i32* %arrayidx, align 4
%add1 = add nsw i32 %0, 1
%arrayidx3 = getelementptr inbounds i32* %A, i32 %indvars.iv
store i32 %add1, i32* %arrayidx3, align 4
%exitcond = icmp ne i32 %indvars.iv.next, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
; Plausible dependence of distance 1 - can't be vectorized.
; for (i = 0; i < 1024; ++i)
; A[i+1] = A[i] + 1;
; CHECK: f2_novec
; CHECK-NOT: <2 x i32>
define void @f2_novec(i32* %A) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32* %A, i32 %indvars.iv
%0 = load i32* %arrayidx, align 4
%add = add nsw i32 %0, 1
%indvars.iv.next = add i32 %indvars.iv, 1
%arrayidx3 = getelementptr inbounds i32* %A, i32 %indvars.iv.next
store i32 %add, i32* %arrayidx3, align 4
%exitcond = icmp ne i32 %indvars.iv.next, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
; Plausible dependence of distance 2 - can be vectorized with a width of 2.
; for (i = 0; i < 1024; ++i)
; A[i+2] = A[i] + 1;
; CHECK: f3_vec_len
; CHECK: <2 x i32>
; WIDTH: f3_vec_len
; WIDTH-NOT: <4 x i32>
define void @f3_vec_len(i32* %A) {
entry:
br label %for.body
for.body:
%i.01 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%idxprom = sext i32 %i.01 to i64
%arrayidx = getelementptr inbounds i32* %A, i64 %idxprom
%0 = load i32* %arrayidx, align 4
%add = add nsw i32 %0, 1
%add1 = add nsw i32 %i.01, 2
%idxprom2 = sext i32 %add1 to i64
%arrayidx3 = getelementptr inbounds i32* %A, i64 %idxprom2
store i32 %add, i32* %arrayidx3, align 4
%inc = add nsw i32 %i.01, 1
%cmp = icmp slt i32 %inc, 1024
br i1 %cmp, label %for.body, label %for.end
for.end:
ret void
}
; Plausible dependence of distance 1 - cannot be vectorized (without reordering
; accesses).
; for (i = 0; i < 1024; ++i) {
; B[i] = A[i];
; A[i] = B[i + 1];
; }
; CHECK: f5
; CHECK-NOT: <2 x i32>
define void @f5(i32* %A, i32* %B) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv
store i32 %0, i32* %arrayidx2, align 4
%indvars.iv.next = add nsw i64 %indvars.iv, 1
%arrayidx4 = getelementptr inbounds i32* %B, i64 %indvars.iv.next
%1 = load i32* %arrayidx4, align 4
store i32 %1, i32* %arrayidx, align 4
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
; Dependence through a phi node - must not vectorize.
; for (i = 0; i < 1024; ++i) {
; a[i+1] = tmp;
; tmp = a[i];
; }
; CHECK: f6
; CHECK-NOT: <2 x i32>
define i32 @f6(i32* %a, i32 %tmp) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%tmp.addr.08 = phi i32 [ %tmp, %entry ], [ %0, %for.body ]
%indvars.iv.next = add nsw i64 %indvars.iv, 1
%arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv.next
store i32 %tmp.addr.08, i32* %arrayidx, align 4
%arrayidx3 = getelementptr inbounds i32* %a, i64 %indvars.iv
%0 = load i32* %arrayidx3, align 4
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret i32 undef
}
; Don't vectorize true loop carried dependencies that are not a multiple of the
; vector width.
; Example:
; for (int i = ...; ++i) {
; a[i] = a[i-3] + ...;
; It is a bad idea to vectorize this loop because store-load forwarding will not
; happen.
;
; CHECK: @nostoreloadforward
; CHECK-NOT: <2 x i32>
define void @nostoreloadforward(i32* %A) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 16, %entry ], [ %indvars.iv.next, %for.body ]
%0 = add nsw i64 %indvars.iv, -3
%arrayidx = getelementptr inbounds i32* %A, i64 %0
%1 = load i32* %arrayidx, align 4
%2 = add nsw i64 %indvars.iv, 4
%arrayidx2 = getelementptr inbounds i32* %A, i64 %2
%3 = load i32* %arrayidx2, align 4
%add3 = add nsw i32 %3, %1
%arrayidx5 = getelementptr inbounds i32* %A, i64 %indvars.iv
store i32 %add3, i32* %arrayidx5, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
; Example:
; for (int i = ...; ++i) {
; a[i] = b[i];
; c[i] = a[i-3] + ...;
; It is a bad idea to vectorize this loop because store-load forwarding will not
; happen.
;
; CHECK: @nostoreloadforward2
; CHECK-NOT: <2 x i32>
define void @nostoreloadforward2(i32* noalias %A, i32* noalias %B, i32* noalias %C) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 16, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32* %B, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %A, i64 %indvars.iv
store i32 %0, i32* %arrayidx2, align 4
%1 = add nsw i64 %indvars.iv, -3
%arrayidx4 = getelementptr inbounds i32* %A, i64 %1
%2 = load i32* %arrayidx4, align 4
%arrayidx6 = getelementptr inbounds i32* %C, i64 %indvars.iv
store i32 %2, i32* %arrayidx6, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}

2
llvm/test/Transforms/LoopVectorize/runtime-check.ll
View File

@ -12,7 +12,7 @@ target triple = "x86_64-apple-macosx10.9.0"
;CHECK: for.body.preheader:
;CHECK: br i1 %cmp.zero, label %middle.block, label %vector.memcheck
;CHECK: vector.memcheck:
;CHECK: br i1 %found.conflict, label %middle.block, label %vector.ph
;CHECK: br i1 %memcheck.conflict, label %middle.block, label %vector.ph
;CHECK: load <4 x float>
define i32 @foo(float* nocapture %a, float* nocapture %b, i32 %n) nounwind uwtable ssp {
entry: