[llvm] 644a965 - [LV] Vectorize cases with larger number of RT checks, execute only if profitable.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 4 07:12:01 PDT 2022
Author: Florian Hahn
Date: 2022-07-04T15:11:39+01:00
New Revision: 644a965c1efef68f22d9495e4cefbb599c214788
URL: https://github.com/llvm/llvm-project/commit/644a965c1efef68f22d9495e4cefbb599c214788
DIFF: https://github.com/llvm/llvm-project/commit/644a965c1efef68f22d9495e4cefbb599c214788.diff
LOG: [LV] Vectorize cases with larger number of RT checks, execute only if profitable.
This patch replaces the tight hard cut-off for the number of runtime
checks with a more accurate cost-driven approach.
The new approach allows vectorization with a larger number of runtime
checks in general, but only executes the vector loop (and runtime checks) if
considered profitable at runtime. Profitable here means that the cost-model
indicates that the runtime check cost + vector loop cost < scalar loop cost.
To do that, LV computes the minimum trip count for which runtime check cost
+ vector-loop-cost < scalar loop cost.
Note that there is still a hard cut-off to avoid excessive compile-time/code-size
increases, but it is much larger than the original limit.
The performance impact on standard test-suites like SPEC2006/SPEC2006/MultiSource
is mostly neutral, but the new approach can give substantial gains in cases where
we failed to vectorize before due to the over-aggressive cut-offs.
On AArch64 with -O3, I didn't observe any regressions outside the noise level (<0.4%)
and there are the following execution time improvements. Both `IRSmk` and `srad` are relatively short running, but the changes are far above the noise level for them on my benchmark system.
```
CFP2006/447.dealII/447.dealII -1.9%
CINT2017rate/525.x264_r/525.x264_r -2.2%
ASC_Sequoia/IRSmk/IRSmk -9.2%
Rodinia/srad/srad -36.1%
```
`size` regressions on AArch64 with -O3 are
```
MultiSource/Applications/hbd/hbd 90256.00 106768.00 18.3%
MultiSourc...ks/ASCI_Purple/SMG2000/smg2000 240676.00 257268.00 6.9%
MultiSourc...enchmarks/mafft/pairlocalalign 472603.00 489131.00 3.5%
External/S...2017rate/525.x264_r/525.x264_r 613831.00 630343.00 2.7%
External/S...NT2006/464.h264ref/464.h264ref 818920.00 835448.00 2.0%
External/S...te/538.imagick_r/538.imagick_r 1994730.00 2027754.00 1.7%
MultiSourc...nchmarks/tramp3d-v4/tramp3d-v4 1236471.00 1253015.00 1.3%
MultiSource/Applications/oggenc/oggenc 2108147.00 2124675.00 0.8%
External/S.../CFP2006/447.dealII/447.dealII 4742999.00 4759559.00 0.3%
External/S...rate/510.parest_r/510.parest_r 14206377.00 14239433.00 0.2%
```
Reviewed By: lebedev.ri, ebrevnov, dmgreen
Differential Revision: https://reviews.llvm.org/D109368
Added:
Modified:
llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll
llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll
llvm/test/Transforms/LoopVectorize/X86/pr23997.ll
llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
llvm/test/Transforms/LoopVectorize/X86/pr54634.ll
llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll
Removed:
################################################################################
diff --git a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
index b01bd222b252e..2d69c2f866422 100644
--- a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
+++ b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
@@ -219,16 +219,9 @@ class LoopVectorizationRequirements {
ExactFPMathInst = I;
}
- void addRuntimePointerChecks(unsigned Num) { NumRuntimePointerChecks = Num; }
-
Instruction *getExactFPInst() { return ExactFPMathInst; }
- unsigned getNumRuntimePointerChecks() const {
- return NumRuntimePointerChecks;
- }
-
private:
- unsigned NumRuntimePointerChecks = 0;
Instruction *ExactFPMathInst = nullptr;
};
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index 6242d9a93fc1a..8b5aca8d2ade2 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -993,7 +993,6 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
}
}
- Requirements->addRuntimePointerChecks(LAI->getNumRuntimePointerChecks());
PSE.addPredicate(LAI->getPSE().getPredicate());
return true;
}
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
index 0cb2032fa45ab..933ea9e023021 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -33,7 +33,6 @@ class LoopInfo;
class LoopVectorizationLegality;
class LoopVectorizationCostModel;
class PredicatedScalarEvolution;
-class LoopVectorizationRequirements;
class LoopVectorizeHints;
class OptimizationRemarkEmitter;
class TargetTransformInfo;
@@ -191,6 +190,10 @@ struct VectorizationFactor {
/// Cost of the scalar loop.
InstructionCost ScalarCost;
+ /// The minimum trip count required to make vectorization profitable, e.g. due
+ /// to runtime checks.
+ ElementCount MinProfitableTripCount;
+
VectorizationFactor(ElementCount Width, InstructionCost Cost,
InstructionCost ScalarCost)
: Width(Width), Cost(Cost), ScalarCost(ScalarCost) {}
@@ -268,8 +271,6 @@ class LoopVectorizationPlanner {
const LoopVectorizeHints &Hints;
- LoopVectorizationRequirements &Requirements;
-
OptimizationRemarkEmitter *ORE;
SmallVector<VPlanPtr, 4> VPlans;
@@ -285,10 +286,9 @@ class LoopVectorizationPlanner {
InterleavedAccessInfo &IAI,
PredicatedScalarEvolution &PSE,
const LoopVectorizeHints &Hints,
- LoopVectorizationRequirements &Requirements,
OptimizationRemarkEmitter *ORE)
: OrigLoop(L), LI(LI), TLI(TLI), TTI(TTI), Legal(Legal), CM(CM), IAI(IAI),
- PSE(PSE), Hints(Hints), Requirements(Requirements), ORE(ORE) {}
+ PSE(PSE), Hints(Hints), ORE(ORE) {}
/// Plan how to best vectorize, return the best VF and its cost, or None if
/// vectorization and interleaving should be avoided up front.
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index b637b2d5ddaed..25ec712f43ddf 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -196,10 +196,9 @@ static cl::opt<unsigned> TinyTripCountVectorThreshold(
"value are vectorized only if no scalar iteration overheads "
"are incurred."));
-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."));
+static cl::opt<unsigned> VectorizeMemoryCheckThreshold(
+ "vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
+ cl::desc("The maximum allowed number of runtime memory checks"));
// Option prefer-predicate-over-epilogue indicates that an epilogue is undesired,
// that predication is preferred, and this lists all options. I.e., the
@@ -442,6 +441,7 @@ class InnerLoopVectorizer {
const TargetLibraryInfo *TLI,
const TargetTransformInfo *TTI, AssumptionCache *AC,
OptimizationRemarkEmitter *ORE, ElementCount VecWidth,
+ ElementCount MinProfitableTripCount,
unsigned UnrollFactor, LoopVectorizationLegality *LVL,
LoopVectorizationCostModel *CM, BlockFrequencyInfo *BFI,
ProfileSummaryInfo *PSI, GeneratedRTChecks &RTChecks)
@@ -453,6 +453,11 @@ class InnerLoopVectorizer {
// of the original loop header may change as the transformation happens.
OptForSizeBasedOnProfile = llvm::shouldOptimizeForSize(
OrigLoop->getHeader(), PSI, BFI, PGSOQueryType::IRPass);
+
+ if (MinProfitableTripCount.isZero())
+ this->MinProfitableTripCount = VecWidth;
+ else
+ this->MinProfitableTripCount = MinProfitableTripCount;
}
virtual ~InnerLoopVectorizer() = default;
@@ -656,6 +661,8 @@ class InnerLoopVectorizer {
/// vector elements.
ElementCount VF;
+ ElementCount MinProfitableTripCount;
+
/// The vectorization unroll factor to use. Each scalar is vectorized to this
/// many
diff erent vector instructions.
unsigned UF;
@@ -735,6 +742,7 @@ class InnerLoopUnroller : public InnerLoopVectorizer {
LoopVectorizationCostModel *CM, BlockFrequencyInfo *BFI,
ProfileSummaryInfo *PSI, GeneratedRTChecks &Check)
: InnerLoopVectorizer(OrigLoop, PSE, LI, DT, TLI, TTI, AC, ORE,
+ ElementCount::getFixed(1),
ElementCount::getFixed(1), UnrollFactor, LVL, CM,
BFI, PSI, Check) {}
@@ -783,8 +791,8 @@ class InnerLoopAndEpilogueVectorizer : public InnerLoopVectorizer {
BlockFrequencyInfo *BFI, ProfileSummaryInfo *PSI,
GeneratedRTChecks &Checks)
: InnerLoopVectorizer(OrigLoop, PSE, LI, DT, TLI, TTI, AC, ORE,
- EPI.MainLoopVF, EPI.MainLoopUF, LVL, CM, BFI, PSI,
- Checks),
+ EPI.MainLoopVF, EPI.MainLoopVF, EPI.MainLoopUF, LVL,
+ CM, BFI, PSI, Checks),
EPI(EPI) {}
// Override this function to handle the more complex control flow around the
@@ -1849,14 +1857,17 @@ class GeneratedRTChecks {
DominatorTree *DT;
LoopInfo *LI;
+ TargetTransformInfo *TTI;
SCEVExpander SCEVExp;
SCEVExpander MemCheckExp;
+ bool CostTooHigh = false;
+
public:
GeneratedRTChecks(ScalarEvolution &SE, DominatorTree *DT, LoopInfo *LI,
- const DataLayout &DL)
- : DT(DT), LI(LI), SCEVExp(SE, DL, "scev.check"),
+ TargetTransformInfo *TTI, const DataLayout &DL)
+ : DT(DT), LI(LI), TTI(TTI), SCEVExp(SE, DL, "scev.check"),
MemCheckExp(SE, DL, "scev.check") {}
/// Generate runtime checks in SCEVCheckBlock and MemCheckBlock, so we can
@@ -1867,6 +1878,15 @@ class GeneratedRTChecks {
void Create(Loop *L, const LoopAccessInfo &LAI,
const SCEVPredicate &UnionPred, ElementCount VF, unsigned IC) {
+ // Hard cutoff to limit compile-time increase in case a very large number of
+ // runtime checks needs to be generated.
+ // TODO: Skip cutoff if the loop is guaranteed to execute, e.g. due to
+ // profile info.
+ CostTooHigh =
+ LAI.getNumRuntimePointerChecks() > VectorizeMemoryCheckThreshold;
+ if (CostTooHigh)
+ return;
+
BasicBlock *LoopHeader = L->getHeader();
BasicBlock *Preheader = L->getLoopPreheader();
@@ -1938,6 +1958,44 @@ class GeneratedRTChecks {
}
}
+ InstructionCost getCost() {
+ if (SCEVCheckBlock || MemCheckBlock)
+ LLVM_DEBUG(dbgs() << "Calculating cost of runtime checks:\n");
+
+ if (CostTooHigh) {
+ InstructionCost Cost;
+ Cost.setInvalid();
+ LLVM_DEBUG(dbgs() << " number of checks exceeded threshold\n");
+ return Cost;
+ }
+
+ InstructionCost RTCheckCost = 0;
+ if (SCEVCheckBlock)
+ for (Instruction &I : *SCEVCheckBlock) {
+ if (SCEVCheckBlock->getTerminator() == &I)
+ continue;
+ InstructionCost C =
+ TTI->getInstructionCost(&I, TTI::TCK_RecipThroughput);
+ LLVM_DEBUG(dbgs() << " " << C << " for " << I << "\n");
+ RTCheckCost += C;
+ }
+ if (MemCheckBlock)
+ for (Instruction &I : *MemCheckBlock) {
+ if (MemCheckBlock->getTerminator() == &I)
+ continue;
+ InstructionCost C =
+ TTI->getInstructionCost(&I, TTI::TCK_RecipThroughput);
+ LLVM_DEBUG(dbgs() << " " << C << " for " << I << "\n");
+ RTCheckCost += C;
+ }
+
+ if (SCEVCheckBlock || MemCheckBlock)
+ LLVM_DEBUG(dbgs() << "Total cost of runtime checks: " << RTCheckCost
+ << "\n");
+
+ return RTCheckCost;
+ }
+
/// Remove the created SCEV & memory runtime check blocks & instructions, if
/// unused.
~GeneratedRTChecks() {
@@ -2880,9 +2938,16 @@ void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) {
// If tail is to be folded, vector loop takes care of all iterations.
Type *CountTy = Count->getType();
Value *CheckMinIters = Builder.getFalse();
- Value *Step = createStepForVF(Builder, CountTy, VF, UF);
+ auto CreateStep = [&]() {
+ // Create step with max(MinProTripCount, UF * VF).
+ if (UF * VF.getKnownMinValue() < MinProfitableTripCount.getKnownMinValue())
+ return createStepForVF(Builder, CountTy, MinProfitableTripCount, 1);
+ return createStepForVF(Builder, CountTy, VF, UF);
+ };
+
if (!Cost->foldTailByMasking())
- CheckMinIters = Builder.CreateICmp(P, Count, Step, "min.iters.check");
+ CheckMinIters =
+ Builder.CreateICmp(P, Count, CreateStep(), "min.iters.check");
else if (VF.isScalable()) {
// vscale is not necessarily a power-of-2, which means we cannot guarantee
// an overflow to zero when updating induction variables and so an
@@ -2894,8 +2959,9 @@ void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) {
Value *LHS = Builder.CreateSub(MaxUIntTripCount, Count);
// Don't execute the vector loop if (UMax - n) < (VF * UF).
- CheckMinIters = Builder.CreateICmp(ICmpInst::ICMP_ULT, LHS, Step);
+ CheckMinIters = Builder.CreateICmp(ICmpInst::ICMP_ULT, LHS, CreateStep());
}
+
// Create new preheader for vector loop.
LoopVectorPreHeader =
SplitBlock(TCCheckBlock, TCCheckBlock->getTerminator(), DT, LI, nullptr,
@@ -2920,7 +2986,6 @@ void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) {
}
BasicBlock *InnerLoopVectorizer::emitSCEVChecks(BasicBlock *Bypass) {
-
BasicBlock *const SCEVCheckBlock =
RTChecks.emitSCEVChecks(Bypass, LoopVectorPreHeader, LoopExitBlock);
if (!SCEVCheckBlock)
@@ -7363,14 +7428,6 @@ LoopVectorizationPlanner::planInVPlanNativePath(ElementCount UserVF) {
return VectorizationFactor::Disabled();
}
-bool LoopVectorizationPlanner::requiresTooManyRuntimeChecks() const {
- unsigned NumRuntimePointerChecks = Requirements.getNumRuntimePointerChecks();
- return (NumRuntimePointerChecks >
- VectorizerParams::RuntimeMemoryCheckThreshold &&
- !Hints.allowReordering()) ||
- NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold;
-}
-
Optional<VectorizationFactor>
LoopVectorizationPlanner::plan(ElementCount UserVF, unsigned UserIC) {
assert(OrigLoop->isInnermost() && "Inner loop expected.");
@@ -10103,8 +10160,7 @@ static bool processLoopInVPlanNativePath(
// Use the planner for outer loop vectorization.
// TODO: CM is not used at this point inside the planner. Turn CM into an
// optional argument if we don't need it in the future.
- LoopVectorizationPlanner LVP(L, LI, TLI, TTI, LVL, CM, IAI, PSE, Hints,
- Requirements, ORE);
+ LoopVectorizationPlanner LVP(L, LI, TLI, TTI, LVL, CM, IAI, PSE, Hints, ORE);
// Get user vectorization factor.
ElementCount UserVF = Hints.getWidth();
@@ -10123,10 +10179,10 @@ static bool processLoopInVPlanNativePath(
VPlan &BestPlan = LVP.getBestPlanFor(VF.Width);
{
- GeneratedRTChecks Checks(*PSE.getSE(), DT, LI,
+ GeneratedRTChecks Checks(*PSE.getSE(), DT, LI, TTI,
F->getParent()->getDataLayout());
- InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, AC, ORE, VF.Width, 1, LVL,
- &CM, BFI, PSI, Checks);
+ InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, AC, ORE, VF.Width,
+ VF.Width, 1, LVL, &CM, BFI, PSI, Checks);
LLVM_DEBUG(dbgs() << "Vectorizing outer loop in \""
<< L->getHeader()->getParent()->getName() << "\"\n");
LVP.executePlan(VF.Width, 1, BestPlan, LB, DT, false);
@@ -10183,6 +10239,94 @@ static void checkMixedPrecision(Loop *L, OptimizationRemarkEmitter *ORE) {
}
}
+static bool areRuntimeChecksProfitable(GeneratedRTChecks &Checks,
+ VectorizationFactor &VF, Loop *L,
+ ScalarEvolution &SE) {
+ InstructionCost CheckCost = Checks.getCost();
+ if (!CheckCost.isValid())
+ return false;
+
+ // When interleaving only scalar and vector cost will be equal, which in turn
+ // would lead to a divide by 0. Fall back to hard threshold.
+ if (VF.Width.isScalar()) {
+ if (CheckCost > VectorizeMemoryCheckThreshold) {
+ LLVM_DEBUG(
+ dbgs()
+ << "LV: Interleaving only is not profitable due to runtime checks\n");
+ return false;
+ }
+ return true;
+ }
+
+ // First, compute the minimum iteration count required so that the vector
+ // loop outperforms the scalar loop.
+ // The total cost of the scalar loop is
+ // ScalarC * TC
+ // where
+ // * TC is the actual trip count of the loop.
+ // * ScalarC is the cost of a single scalar iteration.
+ //
+ // The total cost of the vector loop is
+ // RtC + VecC * (TC / VF) + EpiC
+ // where
+ // * RtC is the cost of the generated runtime checks
+ // * VecC is the cost of a single vector iteration.
+ // * TC is the actual trip count of the loop
+ // * VF is the vectorization factor
+ // * EpiCost is the cost of the generated epilogue, including the cost
+ // of the remaining scalar operations.
+ //
+ // Vectorization is profitable once the total vector cost is less than the
+ // total scalar cost:
+ // RtC + VecC * (TC / VF) + EpiC < ScalarC * TC
+ //
+ // Now we can compute the minimum required trip count TC as
+ // (RtC + EpiC) / (ScalarC - (VecC / VF)) < TC
+ //
+ // For now we assume the epilogue cost EpiC = 0 for simplicity. Note that
+ // the computations are performed on doubles, not integers and the result
+ // is rounded up, hence we get an upper estimate of the TC.
+ unsigned IntVF = VF.Width.getKnownMinValue();
+ double ScalarC = *VF.ScalarCost.getValue();
+ double VecCOverVF = double(*VF.Cost.getValue()) / IntVF;
+ double RtC = *CheckCost.getValue();
+ double MinTC1 = RtC / (ScalarC - VecCOverVF);
+
+ // Second, compute a minimum iteration count so that the cost of the
+ // runtime checks is only a fraction of the total scalar loop cost. This
+ // adds a loop-dependent bound on the overhead incurred if the runtime
+ // checks fail. In case the runtime checks fail, the cost is RtC + ScalarC
+ // * TC. To bound the runtime check to be a fraction 1/X of the scalar
+ // cost, compute
+ // RtC < ScalarC * TC * (1 / X) ==> RtC * X / ScalarC < TC
+ double MinTC2 = RtC * 10 / ScalarC;
+
+ // Now pick the larger minimum. If it is not a multiple of VF, choose the
+ // next closest multiple of VF. This should partly compensate for ignoring
+ // the epilogue cost.
+ uint64_t MinTC = std::ceil(std::max(MinTC1, MinTC2));
+ VF.MinProfitableTripCount = ElementCount::getFixed(alignTo(MinTC, IntVF));
+
+ LLVM_DEBUG(
+ dbgs() << "LV: Minimum required TC for runtime checks to be profitable:"
+ << VF.MinProfitableTripCount << "\n");
+
+ // Skip vectorization if the expected trip count is less than the minimum
+ // required trip count.
+ if (auto ExpectedTC = getSmallBestKnownTC(SE, L)) {
+ if (ElementCount::isKnownLT(ElementCount::getFixed(*ExpectedTC),
+ VF.MinProfitableTripCount)) {
+ LLVM_DEBUG(dbgs() << "LV: Vectorization is not beneficial: expected "
+ "trip count < minimum profitable VF ("
+ << *ExpectedTC << " < " << VF.MinProfitableTripCount
+ << ")\n");
+
+ return false;
+ }
+ }
+ return true;
+}
+
LoopVectorizePass::LoopVectorizePass(LoopVectorizeOptions Opts)
: InterleaveOnlyWhenForced(Opts.InterleaveOnlyWhenForced ||
!EnableLoopInterleaving),
@@ -10340,8 +10484,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
CM.collectElementTypesForWidening();
// Use the planner for vectorization.
- LoopVectorizationPlanner LVP(L, LI, TLI, TTI, &LVL, CM, IAI, PSE, Hints,
- Requirements, ORE);
+ LoopVectorizationPlanner LVP(L, LI, TLI, TTI, &LVL, CM, IAI, PSE, Hints, ORE);
// Get user vectorization factor and interleave count.
ElementCount UserVF = Hints.getWidth();
@@ -10353,21 +10496,9 @@ bool LoopVectorizePass::processLoop(Loop *L) {
VectorizationFactor VF = VectorizationFactor::Disabled();
unsigned IC = 1;
- GeneratedRTChecks Checks(*PSE.getSE(), DT, LI,
+ GeneratedRTChecks Checks(*PSE.getSE(), DT, LI, TTI,
F->getParent()->getDataLayout());
if (MaybeVF) {
- if (LVP.requiresTooManyRuntimeChecks()) {
- ORE->emit([&]() {
- return OptimizationRemarkAnalysisAliasing(
- DEBUG_TYPE, "CantReorderMemOps", L->getStartLoc(),
- L->getHeader())
- << "loop not vectorized: cannot prove it is safe to reorder "
- "memory operations";
- });
- LLVM_DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
- Hints.emitRemarkWithHints();
- return false;
- }
VF = *MaybeVF;
// Select the interleave count.
IC = CM.selectInterleaveCount(VF.Width, *VF.Cost.getValue());
@@ -10377,6 +10508,13 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// they turn out to not be profitable.
if (VF.Width.isVector() || SelectedIC > 1)
Checks.Create(L, *LVL.getLAI(), PSE.getPredicate(), VF.Width, SelectedIC);
+
+ // Check if it is profitable to vectorize with runtime checks.
+ bool ForceVectorization =
+ Hints.getForce() == LoopVectorizeHints::FK_Enabled;
+ if (!ForceVectorization &&
+ !areRuntimeChecksProfitable(Checks, VF, L, *PSE.getSE()))
+ return false;
}
// Identify the diagnostic messages that should be produced.
@@ -10533,8 +10671,9 @@ bool LoopVectorizePass::processLoop(Loop *L) {
if (!MainILV.areSafetyChecksAdded())
DisableRuntimeUnroll = true;
} else {
- InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, AC, ORE, VF.Width, IC,
- &LVL, &CM, BFI, PSI, Checks);
+ InnerLoopVectorizer LB(L, PSE, LI, DT, TLI, TTI, AC, ORE, VF.Width,
+ VF.MinProfitableTripCount, IC, &LVL, &CM, BFI,
+ PSI, Checks);
VPlan &BestPlan = LVP.getBestPlanFor(VF.Width);
LVP.executePlan(VF.Width, IC, BestPlan, LB, DT, false);
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll b/llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll
index afea25a635723..20182dbbf0acc 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll
@@ -1,4 +1,5 @@
-; RUN: opt -loop-vectorize -mtriple=arm64-apple-iphoneos -vectorizer-min-trip-count=8 -S %s | FileCheck %s
+; RUN: opt -loop-vectorize -mtriple=arm64-apple-iphoneos -vectorizer-min-trip-count=8 -S %s | FileCheck --check-prefixes=CHECK,DEFAULT %s
+; RUN: opt -loop-vectorize -mtriple=arm64-apple-iphoneos -vectorizer-min-trip-count=8 -vectorize-memory-check-threshold=1 -S %s | FileCheck --check-prefixes=CHECK,THRESHOLD %s
; Tests for loops with large numbers of runtime checks. Check that loops are
; vectorized, if the loop trip counts are large and the impact of the runtime
@@ -57,11 +58,13 @@ exit:
ret void
}
-; FIXME
; The trip count in the loop in this function high enough to warrant large runtime checks.
; CHECK-LABEL: define {{.*}} @test_tc_big_enough
-; CHECK-NOT: vector.memcheck
-; CHECK-NOT: vector.body
+; DEFAULT: vector.memcheck
+; DEFAULT: vector.body
+; THRESHOLD-NOT: vector.memcheck
+; THRESHOLD-NOT: vector.body
+;
define void @test_tc_big_enough(i16* %ptr.1, i16* %ptr.2, i16* %ptr.3, i16* %ptr.4, i64 %off.1, i64 %off.2) {
entry:
br label %loop
@@ -112,8 +115,11 @@ exit:
define void @test_tc_unknown(i16* %ptr.1, i16* %ptr.2, i16* %ptr.3, i16* %ptr.4, i64 %off.1, i64 %off.2, i64 %N) {
; CHECK-LABEL: define void @test_tc_unknown
-; CHECK-NOT: vector.memcheck
-; CHECK-NOT: vector.body
+; DEFAULT: [[ADD:%.+]] = add i64 %N, 1
+; DEFAULT-NEXT: [[C:%.+]] = icmp ult i64 [[ADD]], 16
+; DEFAULT-NEXT: br i1 [[C]], label %scalar.ph, label %vector.memcheck
+; THRESHOLD-NOT: vector.memcheck
+; THRESHOLD-NOT: vector.body
;
entry:
br label %loop
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
index 03061361b390e..ec7732f4d4e9d 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
@@ -10,9 +10,9 @@ define void @simple_memset(i32 %val, i32* %ptr, i64 %n) #0 {
; CHECK-LABEL: @simple_memset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
index e5f6d46202e43..7c7f171ab431b 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-unroll.ll
@@ -8,9 +8,9 @@ define void @simple_memset(i32 %val, i32* %ptr, i64 %n) #0 {
; CHECK-LABEL: @simple_memset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -102,9 +102,9 @@ define void @cond_memset(i32 %val, i32* noalias readonly %cond_ptr, i32* noalias
; CHECK-LABEL: @cond_memset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
index af7d92ecbb194..7d4ddaf2c4568 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
@@ -10,9 +10,9 @@ define void @simple_memset(i32 %val, i32* %ptr, i64 %n) #0 {
; CHECK-LABEL: @simple_memset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -63,9 +63,9 @@ define void @simple_memcpy(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
; CHECK-LABEL: @simple_memcpy(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -123,9 +123,9 @@ define void @copy_stride4(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[UMAX]], -1
; CHECK-NEXT: [[TMP1:%.*]] = lshr i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
+; CHECK-NEXT: [[TMP5:%.*]] = sub i64 -1, [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT: [[TMP5:%.*]] = sub i64 -1, [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = icmp ult i64 [[TMP5]], [[TMP4]]
; CHECK-NEXT: br i1 [[TMP6]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -193,9 +193,9 @@ define void @simple_gather_scatter(i32* noalias %dst, i32* noalias %src, i32* no
; CHECK-LABEL: @simple_gather_scatter(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -253,9 +253,9 @@ while.end.loopexit: ; preds = %while.body
define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
; CHECK-LABEL: @uniform_load(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -312,9 +312,9 @@ for.end: ; preds = %for.body, %entry
define void @cond_uniform_load(i32* noalias %dst, i32* noalias readonly %src, i32* noalias readonly %cond, i64 %n) #0 {
; CHECK-LABEL: @cond_uniform_load(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -389,9 +389,9 @@ for.end: ; preds = %for.inc, %entry
define void @uniform_store(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
; CHECK-LABEL: @uniform_store(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -445,9 +445,9 @@ define void @simple_fdiv(float* noalias %dst, float* noalias %src, i64 %n) #0 {
; CHECK-LABEL: @simple_fdiv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -507,9 +507,9 @@ define i32 @add_reduction_i32(i32* %ptr, i64 %n) #0 {
; CHECK-LABEL: @add_reduction_i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -563,9 +563,9 @@ define float @add_reduction_f32(float* %ptr, i64 %n) #0 {
; CHECK-LABEL: @add_reduction_f32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
@@ -617,9 +617,9 @@ while.end.loopexit: ; preds = %while.body
define i32 @cond_xor_reduction(i32* noalias %a, i32* noalias %cond, i64 %N) #0 {
; CHECK-LABEL: @cond_xor_reduction(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT: [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
; CHECK-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll b/llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll
index 0007427eecb96..3c88257940b3b 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll
@@ -863,7 +863,7 @@ define void @test_gather_not_profitable_pr48429(i32 %d, float* readonly noalias
; AVX512-NEXT: [[TMP1:%.*]] = add nsw i64 [[TMP0]], -4
; AVX512-NEXT: [[TMP2:%.*]] = lshr i64 [[TMP1]], 2
; AVX512-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
-; AVX512-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 16
+; AVX512-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 32
; AVX512-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; AVX512: vector.memcheck:
; AVX512-NEXT: [[TMP4:%.*]] = shl nsw i64 [[IDX_EXT]], 2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll b/llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll
index 31a70a36763b7..d0cf24d690fc2 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll
@@ -1,6 +1,6 @@
; REQUIRES: asserts
-; RUN: opt -runtime-memory-check-threshold=9 -passes='loop-vectorize' -mtriple=x86_64-unknown-linux -S -debug %s 2>&1 | FileCheck %s
+; RUN: opt -passes='loop-vectorize' -mtriple=x86_64-unknown-linux -S -debug %s 2>&1 | FileCheck %s
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"
@@ -10,11 +10,63 @@ declare double @llvm.pow.f64(double, double)
; Test case where the memory runtime checks and vector body is more expensive
; than running the scalar loop.
-; TODO: should not be vectorized.
define void @test(double* nocapture %A, double* nocapture %B, double* nocapture %C, double* nocapture %D, double* nocapture %E) {
+
+; CHECK: Calculating cost of runtime checks:
+; CHECK-NEXT: 0 for {{.+}} = getelementptr double, double* %A, i64 16
+; CHECK-NEXT: 0 for {{.+}} = bitcast double*
+; CHECK-NEXT: 0 for {{.+}} = getelementptr double, double* %B, i64 16
+; CHECK-NEXT: 0 for {{.+}} = bitcast double*
+; CHECK-NEXT: 0 for {{.+}} = getelementptr double, double* %E, i64 16
+; CHECK-NEXT: 0 for {{.+}} = bitcast double*
+; CHECK-NEXT: 0 for {{.+}} = getelementptr double, double* %C, i64 16
+; CHECK-NEXT: 0 for {{.+}} = bitcast double*
+; CHECK-NEXT: 0 for {{.+}} = getelementptr double, double* %D, i64 16
+; CHECK-NEXT: 0 for {{.+}} = bitcast double*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = icmp ult i8*
+; CHECK-NEXT: 1 for {{.+}} = and i1
+; CHECK-NEXT: 1 for {{.+}} = or i1
+; CHECK-NEXT: Total cost of runtime checks: 35
+
+; CHECK: LV: Vectorization is not beneficial: expected trip count < minimum profitable VF (16 < 70)
+;
; CHECK-LABEL: @test(
-; CHECK: vector.memcheck
-; CHECK: vector.body
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label %for.body
+; CHECK-NOT: vector.memcheck
+; CHECK-NOT: vector.body
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr23997.ll b/llvm/test/Transforms/LoopVectorize/X86/pr23997.ll
index 2fb6a13f9cf40..246b4e16e281a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/pr23997.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/pr23997.ll
@@ -15,7 +15,7 @@ define void @foo(i8 addrspace(1)* align 8 dereferenceable_or_null(16), i8 addrsp
; CHECK-NEXT: [[DOT12:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[TMP1:%.*]], i64 16
; CHECK-NEXT: [[DOT13:%.*]] = bitcast i8 addrspace(1)* [[DOT12]] to i8 addrspace(1)* addrspace(1)*
; CHECK-NEXT: [[UMAX2:%.*]] = call i64 @llvm.umax.i64(i64 [[TMP2:%.*]], i64 1)
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX2]], 16
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX2]], 20
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[TMP2]], i64 1)
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
index cf75d309d458f..12508734cd678 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
@@ -40,7 +40,7 @@ define i32 @main(i32* %ptr) {
; CHECK-NEXT: [[TMP5:%.*]] = add i32 [[TMP4]], 1
; CHECK-NEXT: [[UMIN1:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP2]], i32 [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 [[TMP5]], [[UMIN1]]
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP6]], 8
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP6]], 32
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[TMP7:%.*]] = add i8 [[CONV3]], -1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr54634.ll b/llvm/test/Transforms/LoopVectorize/X86/pr54634.ll
index 5419efd454c73..d03e7b96b58a9 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/pr54634.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/pr54634.ll
@@ -22,7 +22,7 @@ define {} addrspace(10)* @japi1_vect_42283({} addrspace(10)** nocapture readonly
; CHECK-NEXT: [[DOTELT1:%.*]] = getelementptr inbounds { {} addrspace(10)*, i64 }, { {} addrspace(10)*, i64 } addrspace(10)* [[TMP6]], i64 0, i32 1
; CHECK-NEXT: [[DOTUNPACK2:%.*]] = load i64, i64 addrspace(10)* [[DOTELT1]], align 8, !tbaa [[TBAA8]]
; CHECK-NEXT: [[TMP11:%.*]] = add nsw i64 [[TMP2]], 1
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP11]], 16
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP11]], 28
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[MUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[TMP2]])
diff --git a/llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll b/llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll
index 1b5622dbde7d1..86fae7804060e 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll
@@ -1,5 +1,4 @@
-; RUN: opt < %s -loop-vectorize -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s -check-prefix=OVERRIDE
-; RUN: opt < %s -loop-vectorize -pragma-vectorize-memory-check-threshold=6 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
+; RUN: opt < %s -loop-vectorize -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
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"
@@ -8,20 +7,12 @@ target triple = "x86_64-unknown-linux"
; First loop produced diagnostic pass remark.
;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 2)
; Second loop produces diagnostic analysis remark.
-;CHECK: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations
-
-; First loop produced diagnostic pass remark.
-;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 2)
-; Second loop produces diagnostic pass remark.
-;OVERRIDE: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations
+;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
; We are vectorizing with 6 runtime checks.
;CHECK-LABEL: func1x6(
;CHECK: <4 x i32>
;CHECK: ret
-;OVERRIDE-LABEL: func1x6(
-;OVERRIDE: <4 x i32>
-;OVERRIDE: ret
define i32 @func1x6(i32* nocapture %out, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
entry:
br label %for.body
@@ -52,14 +43,10 @@ for.end: ; preds = %for.body
ret i32 undef
}
-; We are not vectorizing with 12 runtime checks.
+; We are vectorizing with 12 runtime checks.
;CHECK-LABEL: func2x6(
-;CHECK-NOT: <4 x i32>
+;CHECK: <4 x i32>
;CHECK: ret
-; We vectorize with 12 checks if a vectorization hint is provided.
-;OVERRIDE-LABEL: func2x6(
-;OVERRIDE-NOT: <4 x i32>
-;OVERRIDE: ret
define i32 @func2x6(i32* nocapture %out, i32* nocapture %out2, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
entry:
br label %for.body
@@ -100,4 +87,3 @@ for.body: ; preds = %for.body, %entry
for.end: ; preds = %for.body
ret i32 undef
}
-
More information about the llvm-commits
mailing list