[NFCI][LoopVectorize] Add MemoryDependenceAnalysis infrastructure

[peterwaller-arm]

Summary

This patch adds the memory dependence analysis pass to LoopVectorize.

The intent is to introduce patches on top of this one which use it.

I'm not certain at this stage if this is the right thing to use or if
there may be infrastructure available within LoopVectorize that it may
be possible to use without the need to introduce MemoryDependenceAnalysis.

[peterwaller-arm]

As @fhahn mentioned in D137159, the MemoryDependenceAnalysis infrastructure is considered deprecated, so this is not viable.

llvm/include/llvm/Analysis/IVDescriptors.h

 
 namespace llvm {
 
 class AssumptionCache;
 class DemandedBits;
 class DominatorTree;
 class Instruction;
 class Loop;
+class MemoryDependenceResults;
 class PredicatedScalarEvolution;
 class ScalarEvolution;
 class SCEV;
 class StoreInst;
 
 /// These are the kinds of recurrences that we support.
 enum class RecurKind {
   None,       ///< Not a recurrence.
public:
   /// the iteration before the previous, we refer to it as second-order
   /// recurrence and so on). \p SinkAfter includes pairs of instructions where
   /// the first will be rescheduled to appear after the second if/when the loop
   /// is vectorized. It may be augmented with additional pairs if needed in
   /// order to handle Phi as a first-order recurrence.
   static bool
   isFixedOrderRecurrence(PHINode *Phi, Loop *TheLoop,
                          MapVector<Instruction *, Instruction *> &SinkAfter,
-                         DominatorTree *DT);
+                         DominatorTree *DT,
+                         MemoryDependenceResults *MDR);
 
   RecurKind getRecurrenceKind() const { return Kind; }
 
   unsigned getOpcode() const { return getOpcode(getRecurrenceKind()); }
 
   FastMathFlags getFastMathFlags() const { return FMF; }
 
   TrackingVH<Value> getRecurrenceStartValue() const { return StartValue; }

llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h

 class AssumptionCache;
 class BasicBlock;
 class BlockFrequencyInfo;
 class DemandedBits;
 class DominatorTree;
 class Function;
 class Loop;
 class LoopInfo;
+class MemoryDependenceResults;
 class Metadata;
 class OptimizationRemarkEmitter;
 class PredicatedScalarEvolution;
 class ProfileSummaryInfo;
 class TargetLibraryInfo;
 class TargetTransformInfo;
 class Type;
 

 public:
   LoopVectorizationLegality(Loop *L, PredicatedScalarEvolution &PSE,
                             DominatorTree *DT, TargetTransformInfo *TTI,
                             TargetLibraryInfo *TLI, AAResults *AA, Function *F,
                             LoopAccessInfoManager &LAIs, LoopInfo *LI,
                             OptimizationRemarkEmitter *ORE,
                             LoopVectorizationRequirements *R,
                             LoopVectorizeHints *H, DemandedBits *DB,
-                            AssumptionCache *AC, BlockFrequencyInfo *BFI,
+                            AssumptionCache *AC, MemoryDependenceResults *MDR,
+                            BlockFrequencyInfo *BFI,
                             ProfileSummaryInfo *PSI)
       : TheLoop(L), LI(LI), PSE(PSE), TTI(TTI), TLI(TLI), DT(DT), LAIs(LAIs),
-        ORE(ORE), Requirements(R), Hints(H), DB(DB), AC(AC), BFI(BFI),
+        ORE(ORE), Requirements(R), Hints(H), DB(DB), AC(AC), MDR(MDR), BFI(BFI),
         PSI(PSI) {}
 
   /// ReductionList contains the reduction descriptors for all
   /// of the reductions that were found in the loop.
   using ReductionList = MapVector<PHINode *, RecurrenceDescriptor>;
 
   /// InductionList saves induction variables and maps them to the
   /// induction descriptor.
private:
   /// The demanded bits analysis is used to compute the minimum type size in
   /// which a reduction can be computed.
   DemandedBits *DB;
 
   /// The assumption cache analysis is used to compute the minimum type size in
   /// which a reduction can be computed.
   AssumptionCache *AC;
 
+  // The memory dependence analysis is used to determine if stores can be
+  // reordered past loads for fixed order reductions.
+  MemoryDependenceResults *MDR;
+
   /// While vectorizing these instructions we have to generate a
   /// call to the appropriate masked intrinsic
   SmallPtrSet<const Instruction *, 8> MaskedOp;
 
   /// Assume instructions in predicated blocks must be dropped if the CFG gets
   /// flattened.
   SmallPtrSet<Instruction *, 8> ConditionalAssumes;
 
   /// BFI and PSI are used to check for profile guided size optimizations.
   BlockFrequencyInfo *BFI;
   ProfileSummaryInfo *PSI;
 };
 
 } // namespace llvm
 
 #endif // LLVM_TRANSFORMS_VECTORIZE_LOOPVECTORIZATIONLEGALITY_H

llvm/include/llvm/Transforms/Vectorize/LoopVectorize.h

 class AssumptionCache;
 class BlockFrequencyInfo;
 class DemandedBits;
 class DominatorTree;
 class Function;
 class Loop;
 class LoopAccessInfoManager;
 class LoopInfo;
+class MemoryDependenceResults;
 class OptimizationRemarkEmitter;
 class ProfileSummaryInfo;
 class ScalarEvolution;
 class TargetLibraryInfo;
 class TargetTransformInfo;
 
 extern cl::opt<bool> EnableLoopInterleaving;
 extern cl::opt<bool> EnableLoopVectorization;
public:
   ScalarEvolution *SE;
   LoopInfo *LI;
   TargetTransformInfo *TTI;
   DominatorTree *DT;
   BlockFrequencyInfo *BFI;
   TargetLibraryInfo *TLI;
   DemandedBits *DB;
   AAResults *AA;
+  MemoryDependenceResults *MDR;
   AssumptionCache *AC;
   LoopAccessInfoManager *LAIs;
   OptimizationRemarkEmitter *ORE;
   ProfileSummaryInfo *PSI;
 
   PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
   void printPipeline(raw_ostream &OS,
                      function_ref<StringRef(StringRef)> MapClassName2PassName);
 
   // Shim for old PM.
   LoopVectorizeResult
   runImpl(Function &F, ScalarEvolution &SE_, LoopInfo &LI_,
           TargetTransformInfo &TTI_, DominatorTree &DT_,
           BlockFrequencyInfo &BFI_, TargetLibraryInfo *TLI_, DemandedBits &DB_,
-          AAResults &AA_, AssumptionCache &AC_, LoopAccessInfoManager &LAIs_,
-          OptimizationRemarkEmitter &ORE_, ProfileSummaryInfo *PSI_);
+          AAResults &AA_, AssumptionCache &AC_, MemoryDependenceResults &MDR_,
+          LoopAccessInfoManager &LAIs_, OptimizationRemarkEmitter &ORE_,
+          ProfileSummaryInfo *PSI_);
 
   bool processLoop(Loop *L);
 };
 
 /// Reports a vectorization failure: print \p DebugMsg for debugging
 /// purposes along with the corresponding optimization remark \p RemarkName.
 /// If \p I is passed, it is an instruction that prevents vectorization.
 /// Otherwise, the loop \p TheLoop is used for the location of the remark.

llvm/lib/Analysis/IVDescriptors.cpp

 //===- llvm/Analysis/IVDescriptors.cpp - IndVar Descriptors -----*- C++ -*-===//
 //
 // 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
 //
 //===----------------------------------------------------------------------===//
 //
 // This file "describes" induction and recurrence variables.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Analysis/IVDescriptors.h"
 #include "llvm/Analysis/DemandedBits.h"
 #include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/MemoryDependenceAnalysis.h"
 #include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/ScalarEvolutionExpressions.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/IR/ValueHandle.h"
if (AddReductionVar(Phi, RecurKind::FMulAdd, TheLoop, FMF, RedDes, DB, AC, DT,
     return true;
   }
   // Not a reduction of known type.
   return false;
 }
 
 bool RecurrenceDescriptor::isFixedOrderRecurrence(
     PHINode *Phi, Loop *TheLoop,
-    MapVector<Instruction *, Instruction *> &SinkAfter, DominatorTree *DT) {
+    MapVector<Instruction *, Instruction *> &SinkAfter, DominatorTree *DT,
+    MemoryDependenceResults *MDR) {
 
   // Ensure the phi node is in the loop header and has two incoming values.
   if (Phi->getParent() != TheLoop->getHeader() ||
       Phi->getNumIncomingValues() != 2)
     return false;
 
   // Ensure the loop has a preheader and a single latch block. The loop
   // vectorizer will need the latch to set up the next iteration of the loop.

llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp

for (Instruction &I : *BB) {
         InductionDescriptor ID;
         if (InductionDescriptor::isInductionPHI(Phi, TheLoop, PSE, ID)) {
           addInductionPhi(Phi, ID, AllowedExit);
           Requirements->addExactFPMathInst(ID.getExactFPMathInst());
           continue;
         }
 
         if (RecurrenceDescriptor::isFixedOrderRecurrence(Phi, TheLoop,
-                                                         SinkAfter, DT)) {
+                                                         SinkAfter, DT, MDR)) {
           AllowedExit.insert(Phi);
           FixedOrderRecurrences.insert(Phi);
           continue;
         }
 
         // As a last resort, coerce the PHI to a AddRec expression
         // and re-try classifying it a an induction PHI.
         if (InductionDescriptor::isInductionPHI(Phi, TheLoop, PSE, ID, true)) {

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/CodeMetrics.h"
 #include "llvm/Analysis/DemandedBits.h"
 #include "llvm/Analysis/GlobalsModRef.h"
 #include "llvm/Analysis/LoopAccessAnalysis.h"
 #include "llvm/Analysis/LoopAnalysisManager.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/LoopIterator.h"
+#include "llvm/Analysis/MemoryDependenceAnalysis.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/ScalarEvolutionExpressions.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/Analysis/VectorUtils.h"
bool runOnFunction(Function &F) override {
     auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
     auto *TLI = TLIP ? &TLIP->getTLI(F) : nullptr;
     auto *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
     auto *AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
     auto &LAIs = getAnalysis<LoopAccessLegacyAnalysis>().getLAIs();
     auto *DB = &getAnalysis<DemandedBitsWrapperPass>().getDemandedBits();
     auto *ORE = &getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();
     auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+    auto *MDR = &getAnalysis<MemoryDependenceWrapperPass>().getMemDep();
 
     return Impl
-        .runImpl(F, *SE, *LI, *TTI, *DT, *BFI, TLI, *DB, *AA, *AC, LAIs, *ORE,
+        .runImpl(F, *SE, *LI, *TTI, *DT, *BFI, TLI, *DB, *AA, *AC, *MDR, LAIs, *ORE,
                  PSI)
         .MadeAnyChange;
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<BlockFrequencyInfoWrapperPass>();
     AU.addRequired<DominatorTreeWrapperPass>();
     AU.addRequired<LoopInfoWrapperPass>();
     AU.addRequired<ScalarEvolutionWrapperPass>();
     AU.addRequired<TargetTransformInfoWrapperPass>();
     AU.addRequired<AAResultsWrapperPass>();
     AU.addRequired<LoopAccessLegacyAnalysis>();
     AU.addRequired<DemandedBitsWrapperPass>();
     AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
     AU.addRequired<InjectTLIMappingsLegacy>();
+    AU.addRequired<MemoryDependenceWrapperPass>();
 
     // We currently do not preserve loopinfo/dominator analyses with outer loop
     // vectorization. Until this is addressed, mark these analyses as preserved
     // only for non-VPlan-native path.
     // TODO: Preserve Loop and Dominator analyses for VPlan-native path.
     if (!EnableVPlanNativePath) {
       AU.addPreserved<LoopInfoWrapperPass>();
       AU.addPreserved<DominatorTreeWrapperPass>();
if (!Hints.allowVectorization(F, L, VectorizeOnlyWhenForced)) {
     return false;
   }
 
   PredicatedScalarEvolution PSE(*SE, *L);
 
   // Check if it is legal to vectorize the loop.
   LoopVectorizationRequirements Requirements;
   LoopVectorizationLegality LVL(L, PSE, DT, TTI, TLI, AA, F, *LAIs, LI, ORE,
-                                &Requirements, &Hints, DB, AC, BFI, PSI);
+                                &Requirements, &Hints, DB, AC, MDR, BFI, PSI);
   if (!LVL.canVectorize(EnableVPlanNativePath)) {
     LLVM_DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
     Hints.emitRemarkWithHints();
     return false;
   }
 
   // Entrance to the VPlan-native vectorization path. Outer loops are processed
   // here. They may require CFG and instruction level transformations before
#endif /* NDEBUG */
   assert(!verifyFunction(*L->getHeader()->getParent(), &dbgs()));
   return true;
 }
 
 LoopVectorizeResult LoopVectorizePass::runImpl(
     Function &F, ScalarEvolution &SE_, LoopInfo &LI_, TargetTransformInfo &TTI_,
     DominatorTree &DT_, BlockFrequencyInfo &BFI_, TargetLibraryInfo *TLI_,
     DemandedBits &DB_, AAResults &AA_, AssumptionCache &AC_,
-    LoopAccessInfoManager &LAIs_, OptimizationRemarkEmitter &ORE_,
-    ProfileSummaryInfo *PSI_) {
+    MemoryDependenceResults &MDR_, LoopAccessInfoManager &LAIs_,
+    OptimizationRemarkEmitter &ORE_, ProfileSummaryInfo *PSI_) {
   SE = &SE_;
   LI = &LI_;
   TTI = &TTI_;
   DT = &DT_;
   BFI = &BFI_;
   TLI = TLI_;
   AA = &AA_;
   AC = &AC_;
   LAIs = &LAIs_;
   DB = &DB_;
   ORE = &ORE_;
   PSI = PSI_;
+  MDR = &MDR_;
 
   // Don't attempt if
   // 1. the target claims to have no vector registers, and
   // 2. interleaving won't help ILP.
   //
   // The second condition is necessary because, even if the target has no
   // vector registers, loop vectorization may still enable scalar
   // interleaving.
PreservedAnalyses LoopVectorizePass::run(Function &F,
     auto &TTI = AM.getResult<TargetIRAnalysis>(F);
     auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
     auto &BFI = AM.getResult<BlockFrequencyAnalysis>(F);
     auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
     auto &AA = AM.getResult<AAManager>(F);
     auto &AC = AM.getResult<AssumptionAnalysis>(F);
     auto &DB = AM.getResult<DemandedBitsAnalysis>(F);
     auto &ORE = AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
+    auto &MDA = AM.getResult<MemoryDependenceAnalysis>(F);
 
     LoopAccessInfoManager &LAIs = AM.getResult<LoopAccessAnalysis>(F);
     auto &MAMProxy = AM.getResult<ModuleAnalysisManagerFunctionProxy>(F);
     ProfileSummaryInfo *PSI =
         MAMProxy.getCachedResult<ProfileSummaryAnalysis>(*F.getParent());
     LoopVectorizeResult Result =
-        runImpl(F, SE, LI, TTI, DT, BFI, &TLI, DB, AA, AC, LAIs, ORE, PSI);
+        runImpl(F, SE, LI, TTI, DT, BFI, &TLI, DB, AA, AC, MDA, LAIs, ORE, PSI);
     if (!Result.MadeAnyChange)
       return PreservedAnalyses::all();
     PreservedAnalyses PA;
 
     // We currently do not preserve loopinfo/dominator analyses with outer loop
     // vectorization. Until this is addressed, mark these analyses as preserved
     // only for non-VPlan-native path.
     // TODO: Preserve Loop and Dominator analyses for VPlan-native path.

llvm/test/Other/new-pm-defaults.ll

 ; CHECK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-O-NEXT: Running pass: LoopDistributePass
 ; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis on foo
 ; CHECK-O-NEXT: Running pass: InjectTLIMappings
 ; CHECK-O-NEXT: Running pass: LoopVectorizePass
 ; CHECK-O-NEXT: Running analysis: BlockFrequencyAnalysis
 ; CHECK-O-NEXT: Running analysis: BranchProbabilityAnalysis
+; CHECK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O2-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O-NEXT: Running pass: VectorCombinePass
 ; CHECK-O-NEXT: Running pass: InstCombinePass

llvm/test/Other/new-pm-thinlto-defaults.ll

 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-Oz,CHECK-O23SZ,CHECK-PRELINK-O,CHECK-PRELINK-O-NODIS
 ; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager -new-pm-debug-info-for-profiling \
 ; RUN:     -passes='thinlto-pre-link<O2>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-DIS,CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-PRELINK-O
 ;
 ; Postlink pipelines:
 ; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes='thinlto<O1>' -S %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O1,CHECK-POSTLINK-O,%llvmcheckext
+; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O1,CHECK-POSTLINK-O,CHECK-POSTLINK-O1,%llvmcheckext
 ; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager \
 ; RUN:     -passes='thinlto<O2>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O2,CHECK-O23SZ,CHECK-POSTLINK-O,%llvmcheckext,CHECK-POSTLINK-O2
 ; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager -passes-ep-pipeline-start='no-op-module' \
 ; RUN:     -passes='thinlto<O3>' -S  %s 2>&1 \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK-O,CHECK-O3,CHECK-O23SZ,CHECK-POSTLINK-O,%llvmcheckext,CHECK-POSTLINK-O3
 ; RUN: opt -disable-verify -verify-cfg-preserved=0 -eagerly-invalidate-analyses=0 -debug-pass-manager -passes-ep-optimizer-early='no-op-module' \
 ; RUN:     -passes='thinlto<O3>' -S  %s 2>&1 \

 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopDistributePass
 ; CHECK-POSTLINK-O-NEXT: Running analysis: LoopAccessAnalysis on foo
 ; CHECK-POSTLINK-O-NEXT: Running pass: InjectTLIMappings
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopVectorizePass
 ; CHECK-POSTLINK-O-NEXT: Running analysis: BlockFrequencyAnalysis
 ; CHECK-POSTLINK-O-NEXT: Running analysis: BranchProbabilityAnalysis
+; CHECK-POSTLINK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-POSTLINK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-POSTLINK-O2-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-POSTLINK-O3-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-POSTLINK-Os-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: VectorCombinePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass

llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll

 ; CHECK-O-NEXT: Running pass: LoopSimplifyPass on foo
 ; CHECK-O-NEXT: Running pass: LCSSAPass on foo
 ; CHECK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-O-NEXT: Running pass: LoopDistributePass
 ; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis on foo
 ; CHECK-O-NEXT: Running pass: InjectTLIMappings
 ; CHECK-O-NEXT: Running pass: LoopVectorizePass
+; CHECK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O2-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O-NEXT: Running pass: VectorCombinePass
 ; CHECK-O-NEXT: Running pass: InstCombinePass

llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll

 ; CHECK-O-NEXT: Running pass: LoopSimplifyPass
 ; CHECK-O-NEXT: Running pass: LCSSAPass
 ; CHECK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-O-NEXT: Running pass: LoopDeletionPass
 ; CHECK-O-NEXT: Running pass: LoopDistributePass
 ; CHECK-O-NEXT: Running analysis: LoopAccessAnalysis
 ; CHECK-O-NEXT: Running pass: InjectTLIMappings
 ; CHECK-O-NEXT: Running pass: LoopVectorizePass
+; CHECK-O1-NEXT: Running analysis: MemoryDependenceAnalysis
+; CHECK-O1-NEXT: Running analysis: PhiValuesAnalysis
 ; CHECK-O-NEXT: Running pass: LoopLoadEliminationPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O2-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
 ; CHECK-O-NEXT: Running pass: VectorCombinePass
 ; CHECK-O-NEXT: Running pass: InstCombinePass