LoopCacheAnalysis.cpp 23.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663
//===- LoopCacheAnalysis.cpp - Loop Cache Analysis -------------------------==//
//
//                     The LLVM Compiler Infrastructure
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file defines the implementation for the loop cache analysis.
/// The implementation is largely based on the following paper:
///
///       Compiler Optimizations for Improving Data Locality
///       By: Steve Carr, Katherine S. McKinley, Chau-Wen Tseng
///       http://www.cs.utexas.edu/users/mckinley/papers/asplos-1994.pdf
///
/// The general approach taken to estimate the number of cache lines used by the
/// memory references in an inner loop is:
///    1. Partition memory references that exhibit temporal or spacial reuse
///       into reference groups.
///    2. For each loop L in the a loop nest LN:
///       a. Compute the cost of the reference group
///       b. Compute the loop cost by summing up the reference groups costs
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/LoopCacheAnalysis.h"
#include "llvm/ADT/BreadthFirstIterator.h"
#include "llvm/ADT/Sequence.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"

using namespace llvm;

#define DEBUG_TYPE "loop-cache-cost"

static cl::opt<unsigned> DefaultTripCount(
    "default-trip-count", cl::init(100), cl::Hidden,
    cl::desc("Use this to specify the default trip count of a loop"));

// In this analysis two array references are considered to exhibit temporal
// reuse if they access either the same memory location, or a memory location
// with distance smaller than a configurable threshold.
static cl::opt<unsigned> TemporalReuseThreshold(
    "temporal-reuse-threshold", cl::init(2), cl::Hidden,
    cl::desc("Use this to specify the max. distance between array elements "
             "accessed in a loop so that the elements are classified to have "
             "temporal reuse"));

/// Retrieve the innermost loop in the given loop nest \p Loops. It returns a
/// nullptr if any loops in the loop vector supplied has more than one sibling.
/// The loop vector is expected to contain loops collected in breadth-first
/// order.
static Loop *getInnerMostLoop(const LoopVectorTy &Loops) {
  assert(!Loops.empty() && "Expecting a non-empy loop vector");

  Loop *LastLoop = Loops.back();
  Loop *ParentLoop = LastLoop->getParentLoop();

  if (ParentLoop == nullptr) {
    assert(Loops.size() == 1 && "Expecting a single loop");
    return LastLoop;
  }

  return (llvm::is_sorted(Loops,
                          [](const Loop *L1, const Loop *L2) {
                            return L1->getLoopDepth() < L2->getLoopDepth();
                          }))
             ? LastLoop
             : nullptr;
}

static bool isOneDimensionalArray(const SCEV &AccessFn, const SCEV &ElemSize,
                                  const Loop &L, ScalarEvolution &SE) {
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(&AccessFn);
  if (!AR || !AR->isAffine())
    return false;

  assert(AR->getLoop() && "AR should have a loop");

  // Check that start and increment are not add recurrences.
  const SCEV *Start = AR->getStart();
  const SCEV *Step = AR->getStepRecurrence(SE);
  if (isa<SCEVAddRecExpr>(Start) || isa<SCEVAddRecExpr>(Step))
    return false;

  // Check that start and increment are both invariant in the loop.
  if (!SE.isLoopInvariant(Start, &L) || !SE.isLoopInvariant(Step, &L))
    return false;

  const SCEV *StepRec = AR->getStepRecurrence(SE);
  if (StepRec && SE.isKnownNegative(StepRec))
    StepRec = SE.getNegativeSCEV(StepRec);

  return StepRec == &ElemSize;
}

/// Compute the trip count for the given loop \p L. Return the SCEV expression
/// for the trip count or nullptr if it cannot be computed.
static const SCEV *computeTripCount(const Loop &L, ScalarEvolution &SE) {
  const SCEV *BackedgeTakenCount = SE.getBackedgeTakenCount(&L);
  if (isa<SCEVCouldNotCompute>(BackedgeTakenCount) ||
      !isa<SCEVConstant>(BackedgeTakenCount))
    return nullptr;

  return SE.getAddExpr(BackedgeTakenCount,
                       SE.getOne(BackedgeTakenCount->getType()));
}

//===----------------------------------------------------------------------===//
// IndexedReference implementation
//
raw_ostream &llvm::operator<<(raw_ostream &OS, const IndexedReference &R) {
  if (!R.IsValid) {
    OS << R.StoreOrLoadInst;
    OS << ", IsValid=false.";
    return OS;
  }

  OS << *R.BasePointer;
  for (const SCEV *Subscript : R.Subscripts)
    OS << "[" << *Subscript << "]";

  OS << ", Sizes: ";
  for (const SCEV *Size : R.Sizes)
    OS << "[" << *Size << "]";

  return OS;
}

IndexedReference::IndexedReference(Instruction &StoreOrLoadInst,
                                   const LoopInfo &LI, ScalarEvolution &SE)
    : StoreOrLoadInst(StoreOrLoadInst), SE(SE) {
  assert((isa<StoreInst>(StoreOrLoadInst) || isa<LoadInst>(StoreOrLoadInst)) &&
         "Expecting a load or store instruction");

  IsValid = delinearize(LI);
  if (IsValid)
    LLVM_DEBUG(dbgs().indent(2) << "Succesfully delinearized: " << *this
                                << "\n");
}

Optional<bool> IndexedReference::hasSpacialReuse(const IndexedReference &Other,
                                                 unsigned CLS,
                                                 AliasAnalysis &AA) const {
  assert(IsValid && "Expecting a valid reference");

  if (BasePointer != Other.getBasePointer() && !isAliased(Other, AA)) {
    LLVM_DEBUG(dbgs().indent(2)
               << "No spacial reuse: different base pointers\n");
    return false;
  }

  unsigned NumSubscripts = getNumSubscripts();
  if (NumSubscripts != Other.getNumSubscripts()) {
    LLVM_DEBUG(dbgs().indent(2)
               << "No spacial reuse: different number of subscripts\n");
    return false;
  }

  // all subscripts must be equal, except the leftmost one (the last one).
  for (auto SubNum : seq<unsigned>(0, NumSubscripts - 1)) {
    if (getSubscript(SubNum) != Other.getSubscript(SubNum)) {
      LLVM_DEBUG(dbgs().indent(2) << "No spacial reuse, different subscripts: "
                                  << "\n\t" << *getSubscript(SubNum) << "\n\t"
                                  << *Other.getSubscript(SubNum) << "\n");
      return false;
    }
  }

  // the difference between the last subscripts must be less than the cache line
  // size.
  const SCEV *LastSubscript = getLastSubscript();
  const SCEV *OtherLastSubscript = Other.getLastSubscript();
  const SCEVConstant *Diff = dyn_cast<SCEVConstant>(
      SE.getMinusSCEV(LastSubscript, OtherLastSubscript));

  if (Diff == nullptr) {
    LLVM_DEBUG(dbgs().indent(2)
               << "No spacial reuse, difference between subscript:\n\t"
               << *LastSubscript << "\n\t" << OtherLastSubscript
               << "\nis not constant.\n");
    return None;
  }

  bool InSameCacheLine = (Diff->getValue()->getSExtValue() < CLS);

  LLVM_DEBUG({
    if (InSameCacheLine)
      dbgs().indent(2) << "Found spacial reuse.\n";
    else
      dbgs().indent(2) << "No spacial reuse.\n";
  });

  return InSameCacheLine;
}

Optional<bool> IndexedReference::hasTemporalReuse(const IndexedReference &Other,
                                                  unsigned MaxDistance,
                                                  const Loop &L,
                                                  DependenceInfo &DI,
                                                  AliasAnalysis &AA) const {
  assert(IsValid && "Expecting a valid reference");

  if (BasePointer != Other.getBasePointer() && !isAliased(Other, AA)) {
    LLVM_DEBUG(dbgs().indent(2)
               << "No temporal reuse: different base pointer\n");
    return false;
  }

  std::unique_ptr<Dependence> D =
      DI.depends(&StoreOrLoadInst, &Other.StoreOrLoadInst, true);

  if (D == nullptr) {
    LLVM_DEBUG(dbgs().indent(2) << "No temporal reuse: no dependence\n");
    return false;
  }

  if (D->isLoopIndependent()) {
    LLVM_DEBUG(dbgs().indent(2) << "Found temporal reuse\n");
    return true;
  }

  // Check the dependence distance at every loop level. There is temporal reuse
  // if the distance at the given loop's depth is small (|d| <= MaxDistance) and
  // it is zero at every other loop level.
  int LoopDepth = L.getLoopDepth();
  int Levels = D->getLevels();
  for (int Level = 1; Level <= Levels; ++Level) {
    const SCEV *Distance = D->getDistance(Level);
    const SCEVConstant *SCEVConst = dyn_cast_or_null<SCEVConstant>(Distance);

    if (SCEVConst == nullptr) {
      LLVM_DEBUG(dbgs().indent(2) << "No temporal reuse: distance unknown\n");
      return None;
    }

    const ConstantInt &CI = *SCEVConst->getValue();
    if (Level != LoopDepth && !CI.isZero()) {
      LLVM_DEBUG(dbgs().indent(2)
                 << "No temporal reuse: distance is not zero at depth=" << Level
                 << "\n");
      return false;
    } else if (Level == LoopDepth && CI.getSExtValue() > MaxDistance) {
      LLVM_DEBUG(
          dbgs().indent(2)
          << "No temporal reuse: distance is greater than MaxDistance at depth="
          << Level << "\n");
      return false;
    }
  }

  LLVM_DEBUG(dbgs().indent(2) << "Found temporal reuse\n");
  return true;
}

CacheCostTy IndexedReference::computeRefCost(const Loop &L,
                                             unsigned CLS) const {
  assert(IsValid && "Expecting a valid reference");
  LLVM_DEBUG({
    dbgs().indent(2) << "Computing cache cost for:\n";
    dbgs().indent(4) << *this << "\n";
  });

  // If the indexed reference is loop invariant the cost is one.
  if (isLoopInvariant(L)) {
    LLVM_DEBUG(dbgs().indent(4) << "Reference is loop invariant: RefCost=1\n");
    return 1;
  }

  const SCEV *TripCount = computeTripCount(L, SE);
  if (!TripCount) {
    LLVM_DEBUG(dbgs() << "Trip count of loop " << L.getName()
                      << " could not be computed, using DefaultTripCount\n");
    const SCEV *ElemSize = Sizes.back();
    TripCount = SE.getConstant(ElemSize->getType(), DefaultTripCount);
  }
  LLVM_DEBUG(dbgs() << "TripCount=" << *TripCount << "\n");

  // If the indexed reference is 'consecutive' the cost is
  // (TripCount*Stride)/CLS, otherwise the cost is TripCount.
  const SCEV *RefCost = TripCount;

  if (isConsecutive(L, CLS)) {
    const SCEV *Coeff = getLastCoefficient();
    const SCEV *ElemSize = Sizes.back();
    const SCEV *Stride = SE.getMulExpr(Coeff, ElemSize);
    const SCEV *CacheLineSize = SE.getConstant(Stride->getType(), CLS);
    Type *WiderType = SE.getWiderType(Stride->getType(), TripCount->getType());
    if (SE.isKnownNegative(Stride))
      Stride = SE.getNegativeSCEV(Stride);
    Stride = SE.getNoopOrAnyExtend(Stride, WiderType);
    TripCount = SE.getNoopOrAnyExtend(TripCount, WiderType);
    const SCEV *Numerator = SE.getMulExpr(Stride, TripCount);
    RefCost = SE.getUDivExpr(Numerator, CacheLineSize);

    LLVM_DEBUG(dbgs().indent(4)
               << "Access is consecutive: RefCost=(TripCount*Stride)/CLS="
               << *RefCost << "\n");
  } else
    LLVM_DEBUG(dbgs().indent(4)
               << "Access is not consecutive: RefCost=TripCount=" << *RefCost
               << "\n");

  // Attempt to fold RefCost into a constant.
  if (auto ConstantCost = dyn_cast<SCEVConstant>(RefCost))
    return ConstantCost->getValue()->getSExtValue();

  LLVM_DEBUG(dbgs().indent(4)
             << "RefCost is not a constant! Setting to RefCost=InvalidCost "
                "(invalid value).\n");

  return CacheCost::InvalidCost;
}

bool IndexedReference::delinearize(const LoopInfo &LI) {
  assert(Subscripts.empty() && "Subscripts should be empty");
  assert(Sizes.empty() && "Sizes should be empty");
  assert(!IsValid && "Should be called once from the constructor");
  LLVM_DEBUG(dbgs() << "Delinearizing: " << StoreOrLoadInst << "\n");

  const SCEV *ElemSize = SE.getElementSize(&StoreOrLoadInst);
  const BasicBlock *BB = StoreOrLoadInst.getParent();

  if (Loop *L = LI.getLoopFor(BB)) {
    const SCEV *AccessFn =
        SE.getSCEVAtScope(getPointerOperand(&StoreOrLoadInst), L);

    BasePointer = dyn_cast<SCEVUnknown>(SE.getPointerBase(AccessFn));
    if (BasePointer == nullptr) {
      LLVM_DEBUG(
          dbgs().indent(2)
          << "ERROR: failed to delinearize, can't identify base pointer\n");
      return false;
    }

    AccessFn = SE.getMinusSCEV(AccessFn, BasePointer);

    LLVM_DEBUG(dbgs().indent(2) << "In Loop '" << L->getName()
                                << "', AccessFn: " << *AccessFn << "\n");

    SE.delinearize(AccessFn, Subscripts, Sizes,
                   SE.getElementSize(&StoreOrLoadInst));

    if (Subscripts.empty() || Sizes.empty() ||
        Subscripts.size() != Sizes.size()) {
      // Attempt to determine whether we have a single dimensional array access.
      // before giving up.
      if (!isOneDimensionalArray(*AccessFn, *ElemSize, *L, SE)) {
        LLVM_DEBUG(dbgs().indent(2)
                   << "ERROR: failed to delinearize reference\n");
        Subscripts.clear();
        Sizes.clear();
        return false;
      }

      // The array may be accessed in reverse, for example:
      //   for (i = N; i > 0; i--)
      //     A[i] = 0;
      // In this case, reconstruct the access function using the absolute value
      // of the step recurrence.
      const SCEVAddRecExpr *AccessFnAR = dyn_cast<SCEVAddRecExpr>(AccessFn);
      const SCEV *StepRec = AccessFnAR ? AccessFnAR->getStepRecurrence(SE) : nullptr;

      if (StepRec && SE.isKnownNegative(StepRec))
        AccessFn = SE.getAddRecExpr(AccessFnAR->getStart(),
                                    SE.getNegativeSCEV(StepRec),
                                    AccessFnAR->getLoop(),
                                    AccessFnAR->getNoWrapFlags());
      const SCEV *Div = SE.getUDivExactExpr(AccessFn, ElemSize);
      Subscripts.push_back(Div);
      Sizes.push_back(ElemSize);
    }

    return all_of(Subscripts, [&](const SCEV *Subscript) {
      return isSimpleAddRecurrence(*Subscript, *L);
    });
  }

  return false;
}

bool IndexedReference::isLoopInvariant(const Loop &L) const {
  Value *Addr = getPointerOperand(&StoreOrLoadInst);
  assert(Addr != nullptr && "Expecting either a load or a store instruction");
  assert(SE.isSCEVable(Addr->getType()) && "Addr should be SCEVable");

  if (SE.isLoopInvariant(SE.getSCEV(Addr), &L))
    return true;

  // The indexed reference is loop invariant if none of the coefficients use
  // the loop induction variable.
  bool allCoeffForLoopAreZero = all_of(Subscripts, [&](const SCEV *Subscript) {
    return isCoeffForLoopZeroOrInvariant(*Subscript, L);
  });

  return allCoeffForLoopAreZero;
}

bool IndexedReference::isConsecutive(const Loop &L, unsigned CLS) const {
  // The indexed reference is 'consecutive' if the only coefficient that uses
  // the loop induction variable is the last one...
  const SCEV *LastSubscript = Subscripts.back();
  for (const SCEV *Subscript : Subscripts) {
    if (Subscript == LastSubscript)
      continue;
    if (!isCoeffForLoopZeroOrInvariant(*Subscript, L))
      return false;
  }

  // ...and the access stride is less than the cache line size.
  const SCEV *Coeff = getLastCoefficient();
  const SCEV *ElemSize = Sizes.back();
  const SCEV *Stride = SE.getMulExpr(Coeff, ElemSize);
  const SCEV *CacheLineSize = SE.getConstant(Stride->getType(), CLS);

  Stride = SE.isKnownNegative(Stride) ? SE.getNegativeSCEV(Stride) : Stride;
  return SE.isKnownPredicate(ICmpInst::ICMP_ULT, Stride, CacheLineSize);
}

const SCEV *IndexedReference::getLastCoefficient() const {
  const SCEV *LastSubscript = getLastSubscript();
  assert(isa<SCEVAddRecExpr>(LastSubscript) &&
         "Expecting a SCEV add recurrence expression");
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(LastSubscript);
  return AR->getStepRecurrence(SE);
}

bool IndexedReference::isCoeffForLoopZeroOrInvariant(const SCEV &Subscript,
                                                     const Loop &L) const {
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(&Subscript);
  return (AR != nullptr) ? AR->getLoop() != &L
                         : SE.isLoopInvariant(&Subscript, &L);
}

bool IndexedReference::isSimpleAddRecurrence(const SCEV &Subscript,
                                             const Loop &L) const {
  if (!isa<SCEVAddRecExpr>(Subscript))
    return false;

  const SCEVAddRecExpr *AR = cast<SCEVAddRecExpr>(&Subscript);
  assert(AR->getLoop() && "AR should have a loop");

  if (!AR->isAffine())
    return false;

  const SCEV *Start = AR->getStart();
  const SCEV *Step = AR->getStepRecurrence(SE);

  if (!SE.isLoopInvariant(Start, &L) || !SE.isLoopInvariant(Step, &L))
    return false;

  return true;
}

bool IndexedReference::isAliased(const IndexedReference &Other,
                                 AliasAnalysis &AA) const {
  const auto &Loc1 = MemoryLocation::get(&StoreOrLoadInst);
  const auto &Loc2 = MemoryLocation::get(&Other.StoreOrLoadInst);
  return AA.isMustAlias(Loc1, Loc2);
}

//===----------------------------------------------------------------------===//
// CacheCost implementation
//
raw_ostream &llvm::operator<<(raw_ostream &OS, const CacheCost &CC) {
  for (const auto &LC : CC.LoopCosts) {
    const Loop *L = LC.first;
    OS << "Loop '" << L->getName() << "' has cost = " << LC.second << "\n";
  }
  return OS;
}

CacheCost::CacheCost(const LoopVectorTy &Loops, const LoopInfo &LI,
                     ScalarEvolution &SE, TargetTransformInfo &TTI,
                     AliasAnalysis &AA, DependenceInfo &DI,
                     Optional<unsigned> TRT)
    : Loops(Loops), TripCounts(), LoopCosts(),
      TRT((TRT == None) ? Optional<unsigned>(TemporalReuseThreshold) : TRT),
      LI(LI), SE(SE), TTI(TTI), AA(AA), DI(DI) {
  assert(!Loops.empty() && "Expecting a non-empty loop vector.");

  for (const Loop *L : Loops) {
    unsigned TripCount = SE.getSmallConstantTripCount(L);
    TripCount = (TripCount == 0) ? DefaultTripCount : TripCount;
    TripCounts.push_back({L, TripCount});
  }

  calculateCacheFootprint();
}

std::unique_ptr<CacheCost>
CacheCost::getCacheCost(Loop &Root, LoopStandardAnalysisResults &AR,
                        DependenceInfo &DI, Optional<unsigned> TRT) {
  if (Root.getParentLoop()) {
    LLVM_DEBUG(dbgs() << "Expecting the outermost loop in a loop nest\n");
    return nullptr;
  }

  LoopVectorTy Loops;
  for (Loop *L : breadth_first(&Root))
    Loops.push_back(L);

  if (!getInnerMostLoop(Loops)) {
    LLVM_DEBUG(dbgs() << "Cannot compute cache cost of loop nest with more "
                         "than one innermost loop\n");
    return nullptr;
  }

  return std::make_unique<CacheCost>(Loops, AR.LI, AR.SE, AR.TTI, AR.AA, DI, TRT);
}

void CacheCost::calculateCacheFootprint() {
  LLVM_DEBUG(dbgs() << "POPULATING REFERENCE GROUPS\n");
  ReferenceGroupsTy RefGroups;
  if (!populateReferenceGroups(RefGroups))
    return;

  LLVM_DEBUG(dbgs() << "COMPUTING LOOP CACHE COSTS\n");
  for (const Loop *L : Loops) {
    assert((std::find_if(LoopCosts.begin(), LoopCosts.end(),
                         [L](const LoopCacheCostTy &LCC) {
                           return LCC.first == L;
                         }) == LoopCosts.end()) &&
           "Should not add duplicate element");
    CacheCostTy LoopCost = computeLoopCacheCost(*L, RefGroups);
    LoopCosts.push_back(std::make_pair(L, LoopCost));
  }

  sortLoopCosts();
  RefGroups.clear();
}

bool CacheCost::populateReferenceGroups(ReferenceGroupsTy &RefGroups) const {
  assert(RefGroups.empty() && "Reference groups should be empty");

  unsigned CLS = TTI.getCacheLineSize();
  Loop *InnerMostLoop = getInnerMostLoop(Loops);
  assert(InnerMostLoop != nullptr && "Expecting a valid innermost loop");

  for (BasicBlock *BB : InnerMostLoop->getBlocks()) {
    for (Instruction &I : *BB) {
      if (!isa<StoreInst>(I) && !isa<LoadInst>(I))
        continue;

      std::unique_ptr<IndexedReference> R(new IndexedReference(I, LI, SE));
      if (!R->isValid())
        continue;

      bool Added = false;
      for (ReferenceGroupTy &RefGroup : RefGroups) {
        const IndexedReference &Representative = *RefGroup.front().get();
        LLVM_DEBUG({
          dbgs() << "References:\n";
          dbgs().indent(2) << *R << "\n";
          dbgs().indent(2) << Representative << "\n";
        });


       // FIXME: Both positive and negative access functions will be placed
       // into the same reference group, resulting in a bi-directional array
       // access such as:
       //   for (i = N; i > 0; i--)
       //     A[i] = A[N - i];
       // having the same cost calculation as a single dimention access pattern
       //   for (i = 0; i < N; i++)
       //     A[i] = A[i];
       // when in actuality, depending on the array size, the first example
       // should have a cost closer to 2x the second due to the two cache
       // access per iteration from opposite ends of the array
        Optional<bool> HasTemporalReuse =
            R->hasTemporalReuse(Representative, *TRT, *InnerMostLoop, DI, AA);
        Optional<bool> HasSpacialReuse =
            R->hasSpacialReuse(Representative, CLS, AA);

        if ((HasTemporalReuse.hasValue() && *HasTemporalReuse) ||
            (HasSpacialReuse.hasValue() && *HasSpacialReuse)) {
          RefGroup.push_back(std::move(R));
          Added = true;
          break;
        }
      }

      if (!Added) {
        ReferenceGroupTy RG;
        RG.push_back(std::move(R));
        RefGroups.push_back(std::move(RG));
      }
    }
  }

  if (RefGroups.empty())
    return false;

  LLVM_DEBUG({
    dbgs() << "\nIDENTIFIED REFERENCE GROUPS:\n";
    int n = 1;
    for (const ReferenceGroupTy &RG : RefGroups) {
      dbgs().indent(2) << "RefGroup " << n << ":\n";
      for (const auto &IR : RG)
        dbgs().indent(4) << *IR << "\n";
      n++;
    }
    dbgs() << "\n";
  });

  return true;
}

CacheCostTy
CacheCost::computeLoopCacheCost(const Loop &L,
                                const ReferenceGroupsTy &RefGroups) const {
  if (!L.isLoopSimplifyForm())
    return InvalidCost;

  LLVM_DEBUG(dbgs() << "Considering loop '" << L.getName()
                    << "' as innermost loop.\n");

  // Compute the product of the trip counts of each other loop in the nest.
  CacheCostTy TripCountsProduct = 1;
  for (const auto &TC : TripCounts) {
    if (TC.first == &L)
      continue;
    TripCountsProduct *= TC.second;
  }

  CacheCostTy LoopCost = 0;
  for (const ReferenceGroupTy &RG : RefGroups) {
    CacheCostTy RefGroupCost = computeRefGroupCacheCost(RG, L);
    LoopCost += RefGroupCost * TripCountsProduct;
  }

  LLVM_DEBUG(dbgs().indent(2) << "Loop '" << L.getName()
                              << "' has cost=" << LoopCost << "\n");

  return LoopCost;
}

CacheCostTy CacheCost::computeRefGroupCacheCost(const ReferenceGroupTy &RG,
                                                const Loop &L) const {
  assert(!RG.empty() && "Reference group should have at least one member.");

  const IndexedReference *Representative = RG.front().get();
  return Representative->computeRefCost(L, TTI.getCacheLineSize());
}

//===----------------------------------------------------------------------===//
// LoopCachePrinterPass implementation
//
PreservedAnalyses LoopCachePrinterPass::run(Loop &L, LoopAnalysisManager &AM,
                                            LoopStandardAnalysisResults &AR,
                                            LPMUpdater &U) {
  Function *F = L.getHeader()->getParent();
  DependenceInfo DI(F, &AR.AA, &AR.SE, &AR.LI);

  if (auto CC = CacheCost::getCacheCost(L, AR, DI))
    OS << *CC;

  return PreservedAnalyses::all();
}