[LICM & MemorySSA] Make limit flags pass tuning options.

[asbirlea]

Summary

Make the flags in LICM + MemorySSA tuning options in the old and new
pass managers.

llvm/trunk/include/llvm/Passes/PassBuilder.h

public:
 
   /// Tuning option to set loop interleaving on/off. Its default value is that
   /// of the flag: `-interleave-loops`.
   bool LoopInterleaving;
 
   /// Tuning option to enable/disable loop vectorization. Its default value is
   /// that of the flag: `-vectorize-loops`.
   bool LoopVectorization;
+
+  /// Tuning option to cap the number of calls to retrive clobbering accesses in
+  /// MemorySSA, in LICM.
+  unsigned LicmMssaOptCap;
+
+  /// Tuning option to disable promotion to scalars in LICM with MemorySSA, if
+  /// the number of access is too large.
+  unsigned LicmMssaNoAccForPromotionCap;
 };
 
 /// This class provides access to building LLVM's passes.
 ///
 /// Its members provide the baseline state available to passes during their
 /// construction. The \c PassRegistry.def file specifies how to construct all
 /// of the built-in passes, and those may reference these members during
 /// construction.

llvm/trunk/include/llvm/Transforms/IPO/PassManagerBuilder.h

public:
   bool ForgetAllSCEVInLoopUnroll;
   bool VerifyInput;
   bool VerifyOutput;
   bool MergeFunctions;
   bool PrepareForLTO;
   bool PrepareForThinLTO;
   bool PerformThinLTO;
   bool DivergentTarget;
+  unsigned LicmMssaOptCap;
+  unsigned LicmMssaNoAccForPromotionCap;
 
   /// Enable profile instrumentation pass.
   bool EnablePGOInstrGen;
   /// Enable profile context sensitive instrumentation pass.
   bool EnablePGOCSInstrGen;
   /// Enable profile context sensitive profile use pass.
   bool EnablePGOCSInstrUse;
   /// Profile data file name that the instrumentation will be written to.

llvm/trunk/include/llvm/Transforms/Scalar.h

 //
 Pass *createIndVarSimplifyPass();
 
 //===----------------------------------------------------------------------===//
 //
 // LICM - This pass is a loop invariant code motion and memory promotion pass.
 //
 Pass *createLICMPass();
+Pass *createLICMPass(unsigned LicmMssaOptCap,
+                     unsigned LicmMssaNoAccForPromotionCap);
 
 //===----------------------------------------------------------------------===//
 //
 // LoopSink - This pass sinks invariants from preheader to loop body where
 // frequency is lower than loop preheader.
 //
 Pass *createLoopSinkPass();
 

llvm/trunk/include/llvm/Transforms/Scalar/LICM.h

 #define LLVM_TRANSFORMS_SCALAR_LICM_H
 
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Transforms/Scalar/LoopPassManager.h"
 
 namespace llvm {
 
+extern cl::opt<unsigned> SetLicmMssaOptCap;
+extern cl::opt<unsigned> SetLicmMssaNoAccForPromotionCap;
+
 /// Performs Loop Invariant Code Motion Pass.
 class LICMPass : public PassInfoMixin<LICMPass> {
+  unsigned LicmMssaOptCap;
+  unsigned LicmMssaNoAccForPromotionCap;
+
 public:
+  LICMPass()
+      : LicmMssaOptCap(SetLicmMssaOptCap),
+        LicmMssaNoAccForPromotionCap(SetLicmMssaNoAccForPromotionCap) {}
+  LICMPass(unsigned LicmMssaOptCap, unsigned LicmMssaNoAccForPromotionCap)
+      : LicmMssaOptCap(LicmMssaOptCap),
+        LicmMssaNoAccForPromotionCap(LicmMssaNoAccForPromotionCap) {}
   PreservedAnalyses run(Loop &L, LoopAnalysisManager &AM,
                         LoopStandardAnalysisResults &AR, LPMUpdater &U);
 };
 } // end namespace llvm
 
 #endif // LLVM_TRANSFORMS_SCALAR_LICM_H

llvm/trunk/include/llvm/Transforms/Utils/LoopUtils.h

 /// LoopInfo and DominatorTree are required and preserved.
 ///
 /// If ScalarEvolution is passed in, it will be preserved.
 ///
 /// Returns true if any modifications are made to the loop.
 bool formLCSSARecursively(Loop &L, DominatorTree &DT, LoopInfo *LI,
                           ScalarEvolution *SE);
 
+struct SinkAndHoistLICMFlags {
+  bool NoOfMemAccTooLarge;
+  unsigned LicmMssaOptCounter;
+  unsigned LicmMssaOptCap;
+  unsigned LicmMssaNoAccForPromotionCap;
+};
+
 /// Walk the specified region of the CFG (defined by all blocks
 /// dominated by the specified block, and that are in the current loop) in
 /// reverse depth first order w.r.t the DominatorTree. This allows us to visit
 /// uses before definitions, allowing us to sink a loop body in one pass without
 /// iteration. Takes DomTreeNode, AliasAnalysis, LoopInfo, DominatorTree,
 /// DataLayout, TargetLibraryInfo, Loop, AliasSet information for all
 /// instructions of the loop and loop safety information as
 /// arguments. Diagnostics is emitted via \p ORE. It returns changed status.
 bool sinkRegion(DomTreeNode *, AliasAnalysis *, LoopInfo *, DominatorTree *,
                 TargetLibraryInfo *, TargetTransformInfo *, Loop *,
                 AliasSetTracker *, MemorySSAUpdater *, ICFLoopSafetyInfo *,
-                bool, int &, OptimizationRemarkEmitter *);
+                SinkAndHoistLICMFlags &, OptimizationRemarkEmitter *);
 
 /// Walk the specified region of the CFG (defined by all blocks
 /// dominated by the specified block, and that are in the current loop) in depth
 /// first order w.r.t the DominatorTree.  This allows us to visit definitions
 /// before uses, allowing us to hoist a loop body in one pass without iteration.
 /// Takes DomTreeNode, AliasAnalysis, LoopInfo, DominatorTree, DataLayout,
 /// TargetLibraryInfo, Loop, AliasSet information for all instructions of the
 /// loop and loop safety information as arguments. Diagnostics is emitted via \p
 /// ORE. It returns changed status.
 bool hoistRegion(DomTreeNode *, AliasAnalysis *, LoopInfo *, DominatorTree *,
                  TargetLibraryInfo *, Loop *, AliasSetTracker *,
-                 MemorySSAUpdater *, ICFLoopSafetyInfo *, bool, int &,
-                 OptimizationRemarkEmitter *);
+                 MemorySSAUpdater *, ICFLoopSafetyInfo *,
+                 SinkAndHoistLICMFlags &, OptimizationRemarkEmitter *);
 
 /// This function deletes dead loops. The caller of this function needs to
 /// guarantee that the loop is infact dead.
 /// The function requires a bunch or prerequisites to be present:
 ///   - The loop needs to be in LCSSA form
 ///   - The loop needs to have a Preheader
 ///   - A unique dedicated exit block must exist
 ///

 /// \p TargetExecutesOncePerLoop is true only when it is guaranteed that the
 /// target executes at most once per execution of the loop body.  This is used
 /// to assess the legality of duplicating atomic loads.  Generally, this is
 /// true when moving out of loop and not true when moving into loops.
 /// If \p ORE is set use it to emit optimization remarks.
 bool canSinkOrHoistInst(Instruction &I, AAResults *AA, DominatorTree *DT,
                         Loop *CurLoop, AliasSetTracker *CurAST,
                         MemorySSAUpdater *MSSAU, bool TargetExecutesOncePerLoop,
-                        bool NoOfMemAccessesTooLarge,
-                        int *LicmMssaOptCap = nullptr,
+                        SinkAndHoistLICMFlags *LICMFlags = nullptr,
                         OptimizationRemarkEmitter *ORE = nullptr);
 
 /// Returns a Min/Max operation corresponding to MinMaxRecurrenceKind.
 Value *createMinMaxOp(IRBuilder<> &Builder,
                       RecurrenceDescriptor::MinMaxRecurrenceKind RK,
                       Value *Left, Value *Right);
 
 /// Generates an ordered vector reduction using extracts to reduce the value.

llvm/trunk/lib/Passes/PassBuilder.cpp

 // profile loading.
 static cl::opt<bool>
     EnableCHR("enable-chr-npm", cl::init(true), cl::Hidden,
               cl::desc("Enable control height reduction optimization (CHR)"));
 
 PipelineTuningOptions::PipelineTuningOptions() {
   LoopInterleaving = EnableLoopInterleaving;
   LoopVectorization = EnableLoopVectorization;
+  LicmMssaOptCap = SetLicmMssaOptCap;
+  LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
 }
 
 extern cl::opt<bool> EnableHotColdSplit;
 extern cl::opt<bool> EnableOrderFileInstrumentation;
 
 extern cl::opt<bool> FlattenedProfileUsed;
 
 static bool isOptimizingForSize(PassBuilder::OptimizationLevel Level) {
PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   // Simplify the loop body. We do this initially to clean up after other loop
   // passes run, either when iterating on a loop or on inner loops with
   // implications on the outer loop.
   LPM1.addPass(LoopInstSimplifyPass());
   LPM1.addPass(LoopSimplifyCFGPass());
 
   // Rotate Loop - disable header duplication at -Oz
   LPM1.addPass(LoopRotatePass(Level != Oz));
-  LPM1.addPass(LICMPass());
+  LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
   LPM1.addPass(SimpleLoopUnswitchPass());
   LPM2.addPass(IndVarSimplifyPass());
   LPM2.addPass(LoopIdiomRecognizePass());
 
   for (auto &C : LateLoopOptimizationsEPCallbacks)
     C(LPM2, Level);
 
   LPM2.addPass(LoopDeletionPass());
PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   FPM.addPass(InstCombinePass());
   invokePeepholeEPCallbacks(FPM, Level);
 
   // Re-consider control flow based optimizations after redundancy elimination,
   // redo DCE, etc.
   FPM.addPass(JumpThreadingPass());
   FPM.addPass(CorrelatedValuePropagationPass());
   FPM.addPass(DSEPass());
-  FPM.addPass(createFunctionToLoopPassAdaptor(LICMPass(), DebugLogging));
+  FPM.addPass(createFunctionToLoopPassAdaptor(
+      LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap),
+      DebugLogging));
 
   for (auto &C : ScalarOptimizerLateEPCallbacks)
     C(FPM, Level);
 
   // Finally, do an expensive DCE pass to catch all the dead code exposed by
   // the simplifications and basic cleanup after all the simplifications.
   FPM.addPass(ADCEPass());
   FPM.addPass(SimplifyCFGPass());
ModulePassManager PassBuilder::buildModuleOptimizationPipeline(
   if (EnableUnrollAndJam) {
     OptimizePM.addPass(
         createFunctionToLoopPassAdaptor(LoopUnrollAndJamPass(Level)));
   }
   OptimizePM.addPass(LoopUnrollPass(LoopUnrollOptions(Level)));
   OptimizePM.addPass(WarnMissedTransformationsPass());
   OptimizePM.addPass(InstCombinePass());
   OptimizePM.addPass(RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
-  OptimizePM.addPass(createFunctionToLoopPassAdaptor(LICMPass(), DebugLogging));
+  OptimizePM.addPass(createFunctionToLoopPassAdaptor(
+      LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap),
+      DebugLogging));
 
   // Now that we've vectorized and unrolled loops, we may have more refined
   // alignment information, try to re-derive it here.
   OptimizePM.addPass(AlignmentFromAssumptionsPass());
 
   // Split out cold code. Splitting is done late to avoid hiding context from
   // other optimizations and inadvertently regressing performance. The tradeoff
   // is that this has a higher code size cost than splitting early.

llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp

 #include "llvm/Transforms/IPO/ForceFunctionAttrs.h"
 #include "llvm/Transforms/IPO/FunctionAttrs.h"
 #include "llvm/Transforms/IPO/InferFunctionAttrs.h"
 #include "llvm/Transforms/InstCombine/InstCombine.h"
 #include "llvm/Transforms/Instrumentation.h"
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Scalar/GVN.h"
 #include "llvm/Transforms/Scalar/InstSimplifyPass.h"
+#include "llvm/Transforms/Scalar/LICM.h"
 #include "llvm/Transforms/Scalar/SimpleLoopUnswitch.h"
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Vectorize.h"
 #include "llvm/Transforms/Vectorize/LoopVectorize.h"
 
 using namespace llvm;
 
 static cl::opt<bool>
PassManagerBuilder::PassManagerBuilder() {
     DisableUnrollLoops = false;
     SLPVectorize = RunSLPVectorization;
     LoopVectorize = EnableLoopVectorization;
     // FIXME: Add: LoopsInterleaved = EnableLoopInterleaving;
     // Replace usage of DisableUnrollLoops with LoopsInterleaved when creating
     // the LoopVectorize pass, to be consistent with the new pass manager.
     RerollLoops = RunLoopRerolling;
     NewGVN = RunNewGVN;
+    LicmMssaOptCap = SetLicmMssaOptCap;
+    LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
     DisableGVNLoadPRE = false;
     ForgetAllSCEVInLoopUnroll = ForgetSCEVInLoopUnroll;
     VerifyInput = false;
     VerifyOutput = false;
     MergeFunctions = false;
     PrepareForLTO = false;
     EnablePGOInstrGen = false;
     EnablePGOCSInstrGen = false;
if (EnableSimpleLoopUnswitch) {
     // The simple loop unswitch pass relies on separate cleanup passes. Schedule
     // them first so when we re-process a loop they run before other loop
     // passes.
     MPM.add(createLoopInstSimplifyPass());
     MPM.add(createLoopSimplifyCFGPass());
   }
   // Rotate Loop - disable header duplication at -Oz
   MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
-  MPM.add(createLICMPass());                  // Hoist loop invariants
+  MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
   if (EnableSimpleLoopUnswitch)
     MPM.add(createSimpleLoopUnswitchLegacyPass());
   else
     MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
   // FIXME: We break the loop pass pipeline here in order to do full
   // simplify-cfg. Eventually loop-simplifycfg should be enhanced to replace the
   // need for this.
   MPM.add(createCFGSimplificationPass());
void PassManagerBuilder::addFunctionSimplificationPasses(
 
   // Run instcombine after redundancy elimination to exploit opportunities
   // opened up by them.
   addInstructionCombiningPass(MPM);
   addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createJumpThreadingPass());         // Thread jumps
   MPM.add(createCorrelatedValuePropagationPass());
   MPM.add(createDeadStoreEliminationPass());  // Delete dead stores
-  MPM.add(createLICMPass());
+  MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
 
   addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
 
   if (RerollLoops)
     MPM.add(createLoopRerollPass());
 
   MPM.add(createAggressiveDCEPass());         // Delete dead instructions
   MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
void PassManagerBuilder::populateModulePassManager(
 
   // Scheduling LoopVersioningLICM when inlining is over, because after that
   // we may see more accurate aliasing. Reason to run this late is that too
   // early versioning may prevent further inlining due to increase of code
   // size. By placing it just after inlining other optimizations which runs
   // later might get benefit of no-alias assumption in clone loop.
   if (UseLoopVersioningLICM) {
     MPM.add(createLoopVersioningLICMPass());    // Do LoopVersioningLICM
-    MPM.add(createLICMPass());                  // Hoist loop invariants
+    MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
   }
 
   // We add a fresh GlobalsModRef run at this point. This is particularly
   // useful as the above will have inlined, DCE'ed, and function-attr
   // propagated everything. We should at this point have a reasonably minimal
   // and richly annotated call graph. By computing aliasing and mod/ref
   // information for all local globals here, the late loop passes and notably
   // the vectorizer will be able to use them to help recognize vectorizable
if (OptLevel > 1 && ExtraVectorizerPasses) {
     // alignment checks inserted by the vectorizer. We want to track correllated
     // runtime checks for two inner loops in the same outer loop, fold any
     // common computations, hoist loop-invariant aspects out of any outer loop,
     // and unswitch the runtime checks if possible. Once hoisted, we may have
     // dead (or speculatable) control flows or more combining opportunities.
     MPM.add(createEarlyCSEPass());
     MPM.add(createCorrelatedValuePropagationPass());
     addInstructionCombiningPass(MPM);
-    MPM.add(createLICMPass());
+    MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
     MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
     MPM.add(createCFGSimplificationPass());
     addInstructionCombiningPass(MPM);
   }
 
   // Cleanup after loop vectorization, etc. Simplification passes like CVP and
   // GVN, loop transforms, and others have already run, so it's now better to
   // convert to more optimized IR using more aggressive simplify CFG options.
void PassManagerBuilder::populateModulePassManager(
   if (!DisableUnrollLoops) {
     // LoopUnroll may generate some redundency to cleanup.
     addInstructionCombiningPass(MPM);
 
     // Runtime unrolling will introduce runtime check in loop prologue. If the
     // unrolled loop is a inner loop, then the prologue will be inside the
     // outer loop. LICM pass can help to promote the runtime check out if the
     // checked value is loop invariant.
-    MPM.add(createLICMPass());
+    MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
   }
 
   MPM.add(createWarnMissedTransformationsPass());
 
   // After vectorization and unrolling, assume intrinsics may tell us more
   // about pointer alignments.
   MPM.add(createAlignmentFromAssumptionsPass());
 
void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
   // LTO provides additional opportunities for tailcall elimination due to
   // link-time inlining, and visibility of nocapture attribute.
   PM.add(createTailCallEliminationPass());
 
   // Run a few AA driven optimizations here and now, to cleanup the code.
   PM.add(createPostOrderFunctionAttrsLegacyPass()); // Add nocapture.
   PM.add(createGlobalsAAWrapperPass()); // IP alias analysis.
 
-  PM.add(createLICMPass());                 // Hoist loop invariants.
+  PM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
   PM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds.
   PM.add(NewGVN ? createNewGVNPass()
                 : createGVNPass(DisableGVNLoadPRE)); // Remove redundancies.
   PM.add(createMemCpyOptPass());            // Remove dead memcpys.
 
   // Nuke dead stores.
   PM.add(createDeadStoreEliminationPass());
 

llvm/trunk/lib/Transforms/Scalar/LICM.cpp

 // exchange for faster compile. This is to be removed if MemorySSA starts to
 // address the same issue. This flag applies only when LICM uses MemorySSA
 // instead on AliasSetTracker. LICM calls MemorySSAWalker's
 // getClobberingMemoryAccess, up to the value of the Cap, getting perfect
 // accuracy. Afterwards, LICM will call into MemorySSA's getDefiningAccess,
 // which may not be precise, since optimizeUses is capped. The result is
 // correct, but we may not get as "far up" as possible to get which access is
 // clobbering the one queried.
-static cl::opt<int> LicmMssaOptCap(
+cl::opt<unsigned> llvm::SetLicmMssaOptCap(
     "licm-mssa-optimization-cap", cl::init(100), cl::Hidden,
     cl::desc("Enable imprecision in LICM in pathological cases, in exchange "
              "for faster compile. Caps the MemorySSA clobbering calls."));
 
 // Experimentally, memory promotion carries less importance than sinking and
 // hoisting. Limit when we do promotion when using MemorySSA, in order to save
 // compile time.
-static cl::opt<unsigned> AccessCapForMSSAPromotion(
-    "max-acc-licm-promotion", cl::init(250), cl::Hidden,
+cl::opt<unsigned> llvm::SetLicmMssaNoAccForPromotionCap(
+    "licm-mssa-max-acc-promotion", cl::init(250), cl::Hidden,
     cl::desc("[LICM & MemorySSA] When MSSA in LICM is disabled, this has no "
              "effect. When MSSA in LICM is enabled, then this is the maximum "
              "number of accesses allowed to be present in a loop in order to "
              "enable memory promotion."));
 
 static bool inSubLoop(BasicBlock *BB, Loop *CurLoop, LoopInfo *LI);
 static bool isNotUsedOrFreeInLoop(const Instruction &I, const Loop *CurLoop,
                                   const LoopSafetyInfo *SafetyInfo,
static bool isSafeToExecuteUnconditionally(Instruction &Inst,
                                            const LoopSafetyInfo *SafetyInfo,
                                            OptimizationRemarkEmitter *ORE,
                                            const Instruction *CtxI = nullptr);
 static bool pointerInvalidatedByLoop(MemoryLocation MemLoc,
                                      AliasSetTracker *CurAST, Loop *CurLoop,
                                      AliasAnalysis *AA);
 static bool pointerInvalidatedByLoopWithMSSA(MemorySSA *MSSA, MemoryUse *MU,
                                              Loop *CurLoop,
-                                             int &LicmMssaOptCounter);
+                                             SinkAndHoistLICMFlags &Flags);
 static Instruction *CloneInstructionInExitBlock(
     Instruction &I, BasicBlock &ExitBlock, PHINode &PN, const LoopInfo *LI,
     const LoopSafetyInfo *SafetyInfo, MemorySSAUpdater *MSSAU);
 
 static void eraseInstruction(Instruction &I, ICFLoopSafetyInfo &SafetyInfo,
                              AliasSetTracker *AST, MemorySSAUpdater *MSSAU);
 
 static void moveInstructionBefore(Instruction &I, Instruction &Dest,
                                   ICFLoopSafetyInfo &SafetyInfo,
                                   MemorySSAUpdater *MSSAU);
 
 namespace {
 struct LoopInvariantCodeMotion {
   using ASTrackerMapTy = DenseMap<Loop *, std::unique_ptr<AliasSetTracker>>;
   bool runOnLoop(Loop *L, AliasAnalysis *AA, LoopInfo *LI, DominatorTree *DT,
                  TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
                  ScalarEvolution *SE, MemorySSA *MSSA,
                  OptimizationRemarkEmitter *ORE, bool DeleteAST);
 
   ASTrackerMapTy &getLoopToAliasSetMap() { return LoopToAliasSetMap; }
+  LoopInvariantCodeMotion(unsigned LicmMssaOptCap,
+                          unsigned LicmMssaNoAccForPromotionCap)
+      : LicmMssaOptCap(LicmMssaOptCap),
+        LicmMssaNoAccForPromotionCap(LicmMssaNoAccForPromotionCap) {}
 
 private:
   ASTrackerMapTy LoopToAliasSetMap;
+  unsigned LicmMssaOptCap;
+  unsigned LicmMssaNoAccForPromotionCap;
 
   std::unique_ptr<AliasSetTracker>
   collectAliasInfoForLoop(Loop *L, LoopInfo *LI, AliasAnalysis *AA);
   std::unique_ptr<AliasSetTracker>
   collectAliasInfoForLoopWithMSSA(Loop *L, AliasAnalysis *AA,
                                   MemorySSAUpdater *MSSAU);
 };
 
 struct LegacyLICMPass : public LoopPass {
   static char ID; // Pass identification, replacement for typeid
-  LegacyLICMPass() : LoopPass(ID) {
+  LegacyLICMPass(
+      unsigned LicmMssaOptCap = SetLicmMssaOptCap,
+      unsigned LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap)
+      : LoopPass(ID), LICM(LicmMssaOptCap, LicmMssaNoAccForPromotionCap) {
     initializeLegacyLICMPassPass(*PassRegistry::getPassRegistry());
   }
 
   bool runOnLoop(Loop *L, LPPassManager &LPM) override {
     if (skipLoop(L)) {
       // If we have run LICM on a previous loop but now we are skipping
       // (because we've hit the opt-bisect limit), we need to clear the
       // loop alias information.
PreservedAnalyses LICMPass::run(Loop &L, LoopAnalysisManager &AM,
   Function *F = L.getHeader()->getParent();
 
   auto *ORE = FAM.getCachedResult<OptimizationRemarkEmitterAnalysis>(*F);
   // FIXME: This should probably be optional rather than required.
   if (!ORE)
     report_fatal_error("LICM: OptimizationRemarkEmitterAnalysis not "
                        "cached at a higher level");
 
-  LoopInvariantCodeMotion LICM;
+  LoopInvariantCodeMotion LICM(LicmMssaOptCap, LicmMssaNoAccForPromotionCap);
   if (!LICM.runOnLoop(&L, &AR.AA, &AR.LI, &AR.DT, &AR.TLI, &AR.TTI, &AR.SE,
                       AR.MSSA, ORE, true))
     return PreservedAnalyses::all();
 
   auto PA = getLoopPassPreservedAnalyses();
 
   PA.preserve<DominatorTreeAnalysis>();
   PA.preserve<LoopAnalysis>();
 
   return PA;
 }
 
 char LegacyLICMPass::ID = 0;
 INITIALIZE_PASS_BEGIN(LegacyLICMPass, "licm", "Loop Invariant Code Motion",
                       false, false)
 INITIALIZE_PASS_DEPENDENCY(LoopPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
 INITIALIZE_PASS_END(LegacyLICMPass, "licm", "Loop Invariant Code Motion", false,
                     false)
 
 Pass *llvm::createLICMPass() { return new LegacyLICMPass(); }
+Pass *llvm::createLICMPass(unsigned LicmMssaOptCap,
+                           unsigned LicmMssaNoAccForPromotionCap) {
+  return new LegacyLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap);
+}
 
 /// Hoist expressions out of the specified loop. Note, alias info for inner
 /// loop is not preserved so it is not a good idea to run LICM multiple
 /// times on one loop.
 /// We should delete AST for inner loops in the new pass manager to avoid
 /// memory leak.
 ///
 bool LoopInvariantCodeMotion::runOnLoop(
     Loop *L, AliasAnalysis *AA, LoopInfo *LI, DominatorTree *DT,
     TargetLibraryInfo *TLI, TargetTransformInfo *TTI, ScalarEvolution *SE,
     MemorySSA *MSSA, OptimizationRemarkEmitter *ORE, bool DeleteAST) {
   bool Changed = false;
 
   assert(L->isLCSSAForm(*DT) && "Loop is not in LCSSA form.");
 
   std::unique_ptr<AliasSetTracker> CurAST;
   std::unique_ptr<MemorySSAUpdater> MSSAU;
   bool NoOfMemAccTooLarge = false;
-  int LicmMssaOptCounter = 0;
+  unsigned LicmMssaOptCounter = 0;
 
   if (!MSSA) {
     LLVM_DEBUG(dbgs() << "LICM: Using Alias Set Tracker.\n");
     CurAST = collectAliasInfoForLoop(L, LI, AA);
   } else {
     LLVM_DEBUG(dbgs() << "LICM: Using MemorySSA.\n");
     MSSAU = make_unique<MemorySSAUpdater>(MSSA);
 
     unsigned AccessCapCount = 0;
     for (auto *BB : L->getBlocks()) {
       if (auto *Accesses = MSSA->getBlockAccesses(BB)) {
         for (const auto &MA : *Accesses) {
           (void)MA;
           AccessCapCount++;
-          if (AccessCapCount > AccessCapForMSSAPromotion) {
+          if (AccessCapCount > LicmMssaNoAccForPromotionCap) {
             NoOfMemAccTooLarge = true;
             break;
           }
         }
       }
       if (NoOfMemAccTooLarge)
         break;
     }
bool LoopInvariantCodeMotion::runOnLoop(
   // of our subloops (they have already had their invariants hoisted out of
   // their loop, into this loop, so there is no need to process the BODIES of
   // the subloops).
   //
   // Traverse the body of the loop in depth first order on the dominator tree so
   // that we are guaranteed to see definitions before we see uses.  This allows
   // us to sink instructions in one pass, without iteration.  After sinking
   // instructions, we perform another pass to hoist them out of the loop.
-  //
+  SinkAndHoistLICMFlags Flags = {NoOfMemAccTooLarge, LicmMssaOptCounter,
+                                 LicmMssaOptCap, LicmMssaNoAccForPromotionCap};
   if (L->hasDedicatedExits())
     Changed |= sinkRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI, TTI, L,
-                          CurAST.get(), MSSAU.get(), &SafetyInfo,
-                          NoOfMemAccTooLarge, LicmMssaOptCounter, ORE);
+                          CurAST.get(), MSSAU.get(), &SafetyInfo, Flags, ORE);
   if (Preheader)
     Changed |= hoistRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI, L,
-                           CurAST.get(), MSSAU.get(), &SafetyInfo,
-                           NoOfMemAccTooLarge, LicmMssaOptCounter, ORE);
+                           CurAST.get(), MSSAU.get(), &SafetyInfo, Flags, ORE);
 
   // Now that all loop invariants have been removed from the loop, promote any
   // memory references to scalars that we can.
   // Don't sink stores from loops without dedicated block exits. Exits
   // containing indirect branches are not transformed by loop simplify,
   // make sure we catch that. An additional load may be generated in the
   // preheader for SSA updater, so also avoid sinking when no preheader
   // is available.

 /// the specified block, and that are in the current loop) in reverse depth
 /// first order w.r.t the DominatorTree.  This allows us to visit uses before
 /// definitions, allowing us to sink a loop body in one pass without iteration.
 ///
 bool llvm::sinkRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
                       DominatorTree *DT, TargetLibraryInfo *TLI,
                       TargetTransformInfo *TTI, Loop *CurLoop,
                       AliasSetTracker *CurAST, MemorySSAUpdater *MSSAU,
-                      ICFLoopSafetyInfo *SafetyInfo, bool NoOfMemAccTooLarge,
-                      int &LicmMssaOptCounter, OptimizationRemarkEmitter *ORE) {
+                      ICFLoopSafetyInfo *SafetyInfo,
+                      SinkAndHoistLICMFlags &Flags,
+                      OptimizationRemarkEmitter *ORE) {
 
   // Verify inputs.
   assert(N != nullptr && AA != nullptr && LI != nullptr && DT != nullptr &&
          CurLoop != nullptr && SafetyInfo != nullptr &&
          "Unexpected input to sinkRegion.");
   assert(((CurAST != nullptr) ^ (MSSAU != nullptr)) &&
          "Either AliasSetTracker or MemorySSA should be initialized.");
 
for (BasicBlock::iterator II = BB->end(); II != BB->begin();) {
 
       // Check to see if we can sink this instruction to the exit blocks
       // of the loop.  We can do this if the all users of the instruction are
       // outside of the loop.  In this case, it doesn't even matter if the
       // operands of the instruction are loop invariant.
       //
       bool FreeInLoop = false;
       if (isNotUsedOrFreeInLoop(I, CurLoop, SafetyInfo, TTI, FreeInLoop) &&
-          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true,
-                             NoOfMemAccTooLarge, &LicmMssaOptCounter, ORE) &&
+          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true, &Flags,
+                             ORE) &&
           !I.mayHaveSideEffects()) {
         if (sink(I, LI, DT, CurLoop, SafetyInfo, MSSAU, ORE)) {
           if (!FreeInLoop) {
             ++II;
             eraseInstruction(I, *SafetyInfo, CurAST, MSSAU);
           }
           Changed = true;
         }

 /// Walk the specified region of the CFG (defined by all blocks dominated by
 /// the specified block, and that are in the current loop) in depth first
 /// order w.r.t the DominatorTree.  This allows us to visit definitions before
 /// uses, allowing us to hoist a loop body in one pass without iteration.
 ///
 bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
                        DominatorTree *DT, TargetLibraryInfo *TLI, Loop *CurLoop,
                        AliasSetTracker *CurAST, MemorySSAUpdater *MSSAU,
-                       ICFLoopSafetyInfo *SafetyInfo, bool NoOfMemAccTooLarge,
-                       int &LicmMssaOptCounter,
+                       ICFLoopSafetyInfo *SafetyInfo,
+                       SinkAndHoistLICMFlags &Flags,
                        OptimizationRemarkEmitter *ORE) {
   // Verify inputs.
   assert(N != nullptr && AA != nullptr && LI != nullptr && DT != nullptr &&
          CurLoop != nullptr && SafetyInfo != nullptr &&
          "Unexpected input to hoistRegion.");
   assert(((CurAST != nullptr) ^ (MSSAU != nullptr)) &&
          "Either AliasSetTracker or MemorySSA should be initialized.");
 
for (BasicBlock::iterator II = BB->begin(), E = BB->end(); II != E;) {
 
       // Try hoisting the instruction out to the preheader.  We can only do
       // this if all of the operands of the instruction are loop invariant and
       // if it is safe to hoist the instruction.
       // TODO: It may be safe to hoist if we are hoisting to a conditional block
       // and we have accurately duplicated the control flow from the loop header
       // to that block.
       if (CurLoop->hasLoopInvariantOperands(&I) &&
-          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true,
-                             NoOfMemAccTooLarge, &LicmMssaOptCounter, ORE) &&
+          canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true, &Flags,
+                             ORE) &&
           isSafeToExecuteUnconditionally(
               I, DT, CurLoop, SafetyInfo, ORE,
               CurLoop->getLoopPreheader()->getTerminator())) {
         hoist(I, DT, CurLoop, CFH.getOrCreateHoistedBlock(BB), SafetyInfo,
               MSSAU, ORE);
         HoistedInstructions.push_back(&I);
         Changed = true;
         continue;
bool isOnlyMemoryAccess(const Instruction *I, const Loop *L,
   return true;
 }
 }
 
 bool llvm::canSinkOrHoistInst(Instruction &I, AAResults *AA, DominatorTree *DT,
                               Loop *CurLoop, AliasSetTracker *CurAST,
                               MemorySSAUpdater *MSSAU,
                               bool TargetExecutesOncePerLoop,
-                              bool NoOfMemAccTooLarge, int *LicmMssaOptCounter,
+                              SinkAndHoistLICMFlags *Flags,
                               OptimizationRemarkEmitter *ORE) {
   // If we don't understand the instruction, bail early.
   if (!isHoistableAndSinkableInst(I))
     return false;
 
   MemorySSA *MSSA = MSSAU ? MSSAU->getMemorySSA() : nullptr;
   if (MSSA)
-    assert(LicmMssaOptCounter != nullptr && "Counter cannot be null.");
+    assert(Flags != nullptr && "Flags cannot be null.");
 
   // Loads have extra constraints we have to verify before we can hoist them.
   if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
     if (!LI->isUnordered())
       return false; // Don't sink/hoist volatile or ordered atomic loads!
 
     // Loads from constant memory are always safe to move, even if they end up
     // in the same alias set as something that ends up being modified.
if (isLoadInvariantInLoop(LI, DT, CurLoop))
       return true;
 
     bool Invalidated;
     if (CurAST)
       Invalidated = pointerInvalidatedByLoop(MemoryLocation::get(LI), CurAST,
                                              CurLoop, AA);
     else
       Invalidated = pointerInvalidatedByLoopWithMSSA(
-          MSSA, cast<MemoryUse>(MSSA->getMemoryAccess(LI)), CurLoop,
-          *LicmMssaOptCounter);
+          MSSA, cast<MemoryUse>(MSSA->getMemoryAccess(LI)), CurLoop, *Flags);
     // Check loop-invariant address because this may also be a sinkable load
     // whose address is not necessarily loop-invariant.
     if (ORE && Invalidated && CurLoop->isLoopInvariant(LI->getPointerOperand()))
       ORE->emit([&]() {
         return OptimizationRemarkMissed(
                    DEBUG_TYPE, "LoadWithLoopInvariantAddressInvalidated", LI)
                << "failed to move load with loop-invariant address "
                   "because the loop may invalidate its value";
if (AliasAnalysis::onlyReadsMemory(Behavior)) {
             bool Invalidated;
             if (CurAST)
               Invalidated = pointerInvalidatedByLoop(
                   MemoryLocation(Op, LocationSize::unknown(), AAMDNodes()),
                   CurAST, CurLoop, AA);
             else
               Invalidated = pointerInvalidatedByLoopWithMSSA(
                   MSSA, cast<MemoryUse>(MSSA->getMemoryAccess(CI)), CurLoop,
-                  *LicmMssaOptCounter);
+                  *Flags);
             if (Invalidated)
               return false;
           }
         return true;
       }
 
       // If this call only reads from memory and there are no writes to memory
       // in the loop, we can hoist or sink the call as appropriate.
if (CurAST) {
         return false;
       assert(UniqueI == SI && "AS must contain SI");
       return true;
     } else { // MSSAU
       if (isOnlyMemoryAccess(SI, CurLoop, MSSAU))
         return true;
       // If there are more accesses than the Promotion cap, give up, we're not
       // walking a list that long.
-      if (NoOfMemAccTooLarge)
+      if (Flags->NoOfMemAccTooLarge)
         return false;
       // Check store only if there's still "quota" to check clobber.
-      if (*LicmMssaOptCounter >= LicmMssaOptCap)
+      if (Flags->LicmMssaOptCounter >= Flags->LicmMssaOptCap)
         return false;
       // If there are interfering Uses (i.e. their defining access is in the
       // loop), or ordered loads (stored as Defs!), don't move this store.
       // Could do better here, but this is conservatively correct.
       // TODO: Cache set of Uses on the first walk in runOnLoop, update when
       // moving accesses. Can also extend to dominating uses.
       for (auto *BB : CurLoop->getBlocks())
         if (auto *Accesses = MSSA->getBlockAccesses(BB)) {
           for (const auto &MA : *Accesses)
             if (const auto *MU = dyn_cast<MemoryUse>(&MA)) {
               auto *MD = MU->getDefiningAccess();
               if (!MSSA->isLiveOnEntryDef(MD) &&
                   CurLoop->contains(MD->getBlock()))
                 return false;
             } else if (const auto *MD = dyn_cast<MemoryDef>(&MA))
               if (auto *LI = dyn_cast<LoadInst>(MD->getMemoryInst())) {
                 (void)LI; // Silence warning.
                 assert(!LI->isUnordered() && "Expected unordered load");
                 return false;
               }
         }
 
       auto *Source = MSSA->getSkipSelfWalker()->getClobberingMemoryAccess(SI);
-      (*LicmMssaOptCounter)++;
+      Flags->LicmMssaOptCounter++;
       // If there are no clobbering Defs in the loop, store is safe to hoist.
       return MSSA->isLiveOnEntryDef(Source) ||
              !CurLoop->contains(Source->getBlock());
     }
   }
 
   assert(!I.mayReadOrWriteMemory() && "unhandled aliasing");
 
for (Instruction &I : *BB) {
       }
     }
   LLVM_DEBUG(dbgs() << "Aliasing okay for " << *(MemLoc.Ptr) << "\n");
   return false;
 }
 
 static bool pointerInvalidatedByLoopWithMSSA(MemorySSA *MSSA, MemoryUse *MU,
                                              Loop *CurLoop,
-                                             int &LicmMssaOptCounter) {
+                                             SinkAndHoistLICMFlags &Flags) {
   MemoryAccess *Source;
-  // See declaration of LicmMssaOptCap for usage details.
-  if (LicmMssaOptCounter >= LicmMssaOptCap)
+  // See declaration of SetLicmMssaOptCap for usage details.
+  if (Flags.LicmMssaOptCounter >= Flags.LicmMssaOptCap)
     Source = MU->getDefiningAccess();
   else {
     Source = MSSA->getSkipSelfWalker()->getClobberingMemoryAccess(MU);
-    LicmMssaOptCounter++;
+    Flags.LicmMssaOptCounter++;
   }
   return !MSSA->isLiveOnEntryDef(Source) &&
          CurLoop->contains(Source->getBlock());
 }
 
 /// Little predicate that returns true if the specified basic block is in
 /// a subloop of the current one, not the current one itself.
 ///
 static bool inSubLoop(BasicBlock *BB, Loop *CurLoop, LoopInfo *LI) {
   assert(CurLoop->contains(BB) && "Only valid if BB is IN the loop");
   return LI->getLoopFor(BB) != CurLoop;
 }

llvm/trunk/lib/Transforms/Scalar/LoopSink.cpp

static bool sinkLoopInvariantInstructions(Loop &L, AAResults &AA, LoopInfo &LI,
   // Traverse preheader's instructions in reverse order becaue if A depends
   // on B (A appears after B), A needs to be sinked first before B can be
   // sinked.
   for (auto II = Preheader->rbegin(), E = Preheader->rend(); II != E;) {
     Instruction *I = &*II++;
     // No need to check for instruction's operands are loop invariant.
     assert(L.hasLoopInvariantOperands(I) &&
            "Insts in a loop's preheader should have loop invariant operands!");
-    if (!canSinkOrHoistInst(*I, &AA, &DT, &L, &CurAST, nullptr, false, false))
+    if (!canSinkOrHoistInst(*I, &AA, &DT, &L, &CurAST, nullptr, false))
       continue;
     if (sinkInstruction(L, *I, ColdLoopBBs, LoopBlockNumber, LI, DT, BFI))
       Changed = true;
   }
 
   if (Changed && SE)
     SE->forgetLoopDispositions(&L);
   return Changed;