[LoopVectorize] Only fetch BFI if profile summary available

[nikic]

Summary

BlockFrequencyInfo should generally only be fetched in PGO builds where a PSI profile summary is available. However, LoopVectorize was fetching it unconditionally.

This results in a compile-time improvement: http://llvm-compile-time-tracker.com/compare.php?from=f332498f9880d276890562fb861a375a13bfd9d9&to=7b224f4a8ef2355298051f8f326eccda4cb07b41&stat=instructions%3Au

[fhahn]

LGTM, thanks!

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

public:
 
   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_,
+                              BlockFrequencyInfo *BFI_, TargetLibraryInfo *TLI_,
                               DemandedBits &DB_, AssumptionCache &AC_,
                               LoopAccessInfoManager &LAIs_,
                               OptimizationRemarkEmitter &ORE_,
                               ProfileSummaryInfo *PSI_);
 
   bool processLoop(Loop *L);
 };
 

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

bool runOnFunction(Function &F) override {
     auto *TLI = TLIP ? &TLIP->getTLI(F) : nullptr;
     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();
 
     return Impl
-        .runImpl(F, *SE, *LI, *TTI, *DT, *BFI, TLI, *DB, *AC, LAIs, *ORE, PSI)
+        .runImpl(F, *SE, *LI, *TTI, *DT, BFI, TLI, *DB, *AC, LAIs, *ORE, PSI)
         .MadeAnyChange;
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<BlockFrequencyInfoWrapperPass>();
     AU.addRequired<DominatorTreeWrapperPass>();
     AU.addRequired<LoopInfoWrapperPass>();
#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_,
+    DominatorTree &DT_, BlockFrequencyInfo *BFI_, TargetLibraryInfo *TLI_,
     DemandedBits &DB_, AssumptionCache &AC_, LoopAccessInfoManager &LAIs_,
     OptimizationRemarkEmitter &ORE_, ProfileSummaryInfo *PSI_) {
   SE = &SE_;
   LI = &LI_;
   TTI = &TTI_;
   DT = &DT_;
-  BFI = &BFI_;
+  BFI = BFI_;
   TLI = TLI_;
   AC = &AC_;
   LAIs = &LAIs_;
   DB = &DB_;
   ORE = &ORE_;
   PSI = PSI_;
 
   // Don't attempt if
PreservedAnalyses LoopVectorizePass::run(Function &F,
     auto &LI = AM.getResult<LoopAnalysis>(F);
     // There are no loops in the function. Return before computing other expensive
     // analyses.
     if (LI.empty())
       return PreservedAnalyses::all();
     auto &SE = AM.getResult<ScalarEvolutionAnalysis>(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 &AC = AM.getResult<AssumptionAnalysis>(F);
     auto &DB = AM.getResult<DemandedBitsAnalysis>(F);
     auto &ORE = AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
 
     LoopAccessInfoManager &LAIs = AM.getResult<LoopAccessAnalysis>(F);
     auto &MAMProxy = AM.getResult<ModuleAnalysisManagerFunctionProxy>(F);
     ProfileSummaryInfo *PSI =
         MAMProxy.getCachedResult<ProfileSummaryAnalysis>(*F.getParent());
+    BlockFrequencyInfo *BFI = nullptr;
+    if (PSI && PSI->hasProfileSummary())
+      BFI = &AM.getResult<BlockFrequencyAnalysis>(F);
     LoopVectorizeResult Result =
         runImpl(F, SE, LI, TTI, DT, BFI, &TLI, DB, AC, LAIs, ORE, PSI);
     if (!Result.MadeAnyChange)
       return PreservedAnalyses::all();
     PreservedAnalyses PA;
 
     if (isAssignmentTrackingEnabled(*F.getParent())) {
       for (auto &BB : F)

llvm/test/Other/new-pm-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 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-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
 ; CHECK-O-NEXT: Running pass: LoopUnrollPass
 ; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass
 ; CHECK-O-NEXT: Running pass: SROAPass
 ; CHECK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}OptimizationRemarkEmitterAnalysis
 ; CHECK-O-NEXT: Running pass: LoopSimplifyPass
 ; CHECK-O-NEXT: Running pass: LCSSAPass
 ; CHECK-O-NEXT: Running pass: LICMPass
 ; CHECK-O-NEXT: Running pass: AlignmentFromAssumptionsPass
 ; CHECK-O-NEXT: Running pass: LoopSinkPass
+; CHECK-O-NEXT: Running analysis: BlockFrequencyAnalysis
+; CHECK-O-NEXT: Running analysis: BranchProbabilityAnalysis
 ; CHECK-O-NEXT: Running pass: InstSimplifyPass
 ; CHECK-O-NEXT: Running pass: DivRemPairsPass
 ; CHECK-O-NEXT: Running pass: TailCallElimPass
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-EP-OPTIMIZER-LAST: Running pass: NoOpModulePass
 ; CHECK-HOT-COLD-SPLIT-NEXT: Running pass: HotColdSplittingPass
 ; CHECK-IR-OUTLINER-NEXT: Running pass: IROutlinerPass
 ; CHECK-IR-OUTLINER-NEXT: Running analysis: IRSimilarityAnalysis

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

 ; CHECK-O23SZ-NEXT: Running pass: LoopSimplifyPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LCSSAPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: IndVarSimplifyPass on loop
 ; CHECK-O23SZ-NEXT: Running pass: LoopDeletionPass on loop
 ; CHECK-O23SZ-NEXT: Running pass: LoopFullUnrollPass on loop
 ; CHECK-O23SZ-NEXT: Running pass: LoopDistributePass on foo
 ; CHECK-O23SZ-NEXT: Running analysis: LoopAccessAnalysis on foo
 ; CHECK-O23SZ-NEXT: Running pass: LoopVectorizePass on foo
-; CHECK-O23SZ-NEXT: Running analysis: BlockFrequencyAnalysis on foo
-; CHECK-O23SZ-NEXT: Running analysis: BranchProbabilityAnalysis on foo
 ; CHECK-O23SZ-NEXT: Running analysis: DemandedBitsAnalysis on foo
 ; CHECK-O23SZ-NEXT: Running pass: LoopUnrollPass on foo
 ; CHECK-O23SZ-NEXT: WarnMissedTransformationsPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: SROAPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass on foo
 ; CHECK-O23SZ-NEXT: Running pass: SimplifyCFGPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: SCCPPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass on foo
 ; CHECK-O23SZ-NEXT: Running pass: BDCEPass on foo
 ; CHECK-O2-NEXT: Running pass: SLPVectorizerPass on foo
 ; CHECK-O3-NEXT: Running pass: SLPVectorizerPass on foo
 ; CHECK-OS-NEXT: Running pass: SLPVectorizerPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: VectorCombinePass on foo
 ; CHECK-O23SZ-NEXT: Running pass: AlignmentFromAssumptionsPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: InstCombinePass on foo
 ; CHECK-EP-Peephole-NEXT: Running pass: NoOpFunctionPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: JumpThreadingPass on foo
 ; CHECK-O23SZ-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O-NEXT: Running pass: LowerTypeTestsPass
 ; CHECK-O23SZ-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-O23SZ-NEXT: Running pass: EliminateAvailableExternallyPass
 ; CHECK-O23SZ-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O23SZ-NEXT: Running pass: CGProfilePass
+; CHECK-O23SZ-NEXT: Running analysis: BlockFrequencyAnalysis on foo
+; CHECK-O23SZ-NEXT: Running analysis: BranchProbabilityAnalysis on foo
 ; CHECK-EP-NEXT: Running pass: NoOpModulePass
 ; CHECK-O-NEXT: Running pass: AnnotationRemarksPass on foo
 ; CHECK-O-NEXT: Running pass: PrintModulePass
 
 ; Make sure we get the IR back out without changes when we print the module.
 ; CHECK-O-LABEL: define void @foo(i32 %n) local_unnamed_addr {
 ; CHECK-O-NEXT: entry:
 ; CHECK-O-NEXT:   br label %loop

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

 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopSimplifyPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LCSSAPass
 ; 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-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
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopUnrollPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: WarnMissedTransformationsPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: SROAPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}OptimizationRemarkEmitterAnalysis
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopSimplifyPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LCSSAPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LICMPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: AlignmentFromAssumptionsPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: LoopSinkPass
+; CHECK-POSTLINK-O-NEXT: Running analysis: BlockFrequencyAnalysis
+; CHECK-POSTLINK-O-NEXT: Running analysis: BranchProbabilityAnalysis
 ; CHECK-POSTLINK-O-NEXT: Running pass: InstSimplifyPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: DivRemPairsPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: TailCallElimPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: SimplifyCFGPass
 ; CHECK-POST-EP-OPT-LAST-NEXT: Running pass: NoOpModulePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: GlobalDCEPass
 ; CHECK-POSTLINK-O-NEXT: Running pass: ConstantMergePass
 ; CHECK-POSTLINK-O-NEXT: Running pass: CGProfilePass