C++ BranchInst::extractProfMetadata方法代码示例

Optional<unsigned> llvm::getLoopEstimatedTripCount(Loop *L) {
  // Only support loops with a unique exiting block, and a latch.
  if (!L->getExitingBlock())
    return None;

  // Get the branch weights for the the loop's backedge.
  BranchInst *LatchBR =
      dyn_cast<BranchInst>(L->getLoopLatch()->getTerminator());
  if (!LatchBR || LatchBR->getNumSuccessors() != 2)
    return None;

  assert((LatchBR->getSuccessor(0) == L->getHeader() ||
          LatchBR->getSuccessor(1) == L->getHeader()) &&
         "At least one edge out of the latch must go to the header");

  // To estimate the number of times the loop body was executed, we want to
  // know the number of times the backedge was taken, vs. the number of times
  // we exited the loop.
  uint64_t TrueVal, FalseVal;
  if (!LatchBR->extractProfMetadata(TrueVal, FalseVal))
    return None;

  if (!TrueVal || !FalseVal)
    return 0;

  // Divide the count of the backedge by the count of the edge exiting the loop,
  // rounding to nearest.
  if (LatchBR->getSuccessor(0) == L->getHeader())
    return (TrueVal + (FalseVal / 2)) / FalseVal;
  else
    return (FalseVal + (TrueVal / 2)) / TrueVal;
}

// Check if there is PGO data or user annoated branch data:
static bool hasProfileData(Function *F, FunctionOutliningInfo *OI) {
  if (F->getEntryCount())
    return true;
  // Now check if any of the entry block has MD_prof data:
  for (auto *E : OI->Entries) {
    BranchInst *BR = dyn_cast<BranchInst>(E->getTerminator());
    if (!BR || BR->isUnconditional())
      continue;
    uint64_t T, F;
    if (BR->extractProfMetadata(T, F))
      return true;
  }
  return false;
}

/// \brief Peel off the first \p PeelCount iterations of loop \p L.
///
/// Note that this does not peel them off as a single straight-line block.
/// Rather, each iteration is peeled off separately, and needs to check the
/// exit condition.
/// For loops that dynamically execute \p PeelCount iterations or less
/// this provides a benefit, since the peeled off iterations, which account
/// for the bulk of dynamic execution, can be further simplified by scalar
/// optimizations.
bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
                    ScalarEvolution *SE, DominatorTree *DT,
                    bool PreserveLCSSA) {
  if (!canPeel(L))
    return false;

  LoopBlocksDFS LoopBlocks(L);
  LoopBlocks.perform(LI);

  BasicBlock *Header = L->getHeader();
  BasicBlock *PreHeader = L->getLoopPreheader();
  BasicBlock *Latch = L->getLoopLatch();
  BasicBlock *Exit = L->getUniqueExitBlock();

  Function *F = Header->getParent();

  // Set up all the necessary basic blocks. It is convenient to split the
  // preheader into 3 parts - two blocks to anchor the peeled copy of the loop
  // body, and a new preheader for the "real" loop.

  // Peeling the first iteration transforms.
  //
  // PreHeader:
  // ...
  // Header:
  //   LoopBody
  //   If (cond) goto Header
  // Exit:
  //
  // into
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:
  //
  // Each following iteration will split the current bottom anchor in two,
  // and put the new copy of the loop body between these two blocks. That is,
  // after peeling another iteration from the example above, we'll split 
  // InsertBot, and get:
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot.next:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:

  BasicBlock *InsertTop = SplitEdge(PreHeader, Header, DT, LI);
  BasicBlock *InsertBot =
      SplitBlock(InsertTop, InsertTop->getTerminator(), DT, LI);
  BasicBlock *NewPreHeader =
      SplitBlock(InsertBot, InsertBot->getTerminator(), DT, LI);

  InsertTop->setName(Header->getName() + ".peel.begin");
  InsertBot->setName(Header->getName() + ".peel.next");
  NewPreHeader->setName(PreHeader->getName() + ".peel.newph");

  ValueToValueMapTy LVMap;

  // If we have branch weight information, we'll want to update it for the
  // newly created branches.
  BranchInst *LatchBR =
      cast<BranchInst>(cast<BasicBlock>(Latch)->getTerminator());
  unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);

  uint64_t TrueWeight, FalseWeight;
  uint64_t ExitWeight = 0, BackEdgeWeight = 0;
  if (LatchBR->extractProfMetadata(TrueWeight, FalseWeight)) {
    ExitWeight = HeaderIdx ? TrueWeight : FalseWeight;
    BackEdgeWeight = HeaderIdx ? FalseWeight : TrueWeight;
  }

  // For each peeled-off iteration, make a copy of the loop.
  for (unsigned Iter = 0; Iter < PeelCount; ++Iter) {
    SmallVector<BasicBlock *, 8> NewBlocks;
    ValueToValueMapTy VMap;

//.........这里部分代码省略.........

/// Peel off the first \p PeelCount iterations of loop \p L.
///
/// Note that this does not peel them off as a single straight-line block.
/// Rather, each iteration is peeled off separately, and needs to check the
/// exit condition.
/// For loops that dynamically execute \p PeelCount iterations or less
/// this provides a benefit, since the peeled off iterations, which account
/// for the bulk of dynamic execution, can be further simplified by scalar
/// optimizations.
bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
                    ScalarEvolution *SE, DominatorTree *DT,
                    AssumptionCache *AC, bool PreserveLCSSA) {
  assert(PeelCount > 0 && "Attempt to peel out zero iterations?");
  assert(canPeel(L) && "Attempt to peel a loop which is not peelable?");

  LoopBlocksDFS LoopBlocks(L);
  LoopBlocks.perform(LI);

  BasicBlock *Header = L->getHeader();
  BasicBlock *PreHeader = L->getLoopPreheader();
  BasicBlock *Latch = L->getLoopLatch();
  BasicBlock *Exit = L->getUniqueExitBlock();

  Function *F = Header->getParent();

  // Set up all the necessary basic blocks. It is convenient to split the
  // preheader into 3 parts - two blocks to anchor the peeled copy of the loop
  // body, and a new preheader for the "real" loop.

  // Peeling the first iteration transforms.
  //
  // PreHeader:
  // ...
  // Header:
  //   LoopBody
  //   If (cond) goto Header
  // Exit:
  //
  // into
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:
  //
  // Each following iteration will split the current bottom anchor in two,
  // and put the new copy of the loop body between these two blocks. That is,
  // after peeling another iteration from the example above, we'll split
  // InsertBot, and get:
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot.next:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:

  BasicBlock *InsertTop = SplitEdge(PreHeader, Header, DT, LI);
  BasicBlock *InsertBot =
      SplitBlock(InsertTop, InsertTop->getTerminator(), DT, LI);
  BasicBlock *NewPreHeader =
      SplitBlock(InsertBot, InsertBot->getTerminator(), DT, LI);

  InsertTop->setName(Header->getName() + ".peel.begin");
  InsertBot->setName(Header->getName() + ".peel.next");
  NewPreHeader->setName(PreHeader->getName() + ".peel.newph");

  ValueToValueMapTy LVMap;

  // If we have branch weight information, we'll want to update it for the
  // newly created branches.
  BranchInst *LatchBR =
      cast<BranchInst>(cast<BasicBlock>(Latch)->getTerminator());
  unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);

  uint64_t TrueWeight, FalseWeight;
  uint64_t ExitWeight = 0, CurHeaderWeight = 0;
  if (LatchBR->extractProfMetadata(TrueWeight, FalseWeight)) {
    ExitWeight = HeaderIdx ? TrueWeight : FalseWeight;
    // The # of times the loop body executes is the sum of the exit block
    // weight and the # of times the backedges are taken.
    CurHeaderWeight = TrueWeight + FalseWeight;
  }

  // For each peeled-off iteration, make a copy of the loop.
  for (unsigned Iter = 0; Iter < PeelCount; ++Iter) {
    SmallVector<BasicBlock *, 8> NewBlocks;
//.........这里部分代码省略.........