Merge from 'master' to 'sycl-web' (#2)

  CONFLICT (content): Merge conflict in clang/lib/CodeGen/BackendUtil.cpp

Author: Valery N Dmitriev

clang/include/clang/Basic/CodeGenOptions.def

@@ -254,7 +254,6 @@ CODEGENOPT(UnwindTables      , 1, 0) ///< Emit unwind tables.
 CODEGENOPT(VectorizeLoop     , 1, 0) ///< Run loop vectorizer.
 CODEGENOPT(VectorizeSLP      , 1, 0) ///< Run SLP vectorizer.
 CODEGENOPT(ProfileSampleAccurate, 1, 0) ///< Sample profile is accurate.
-CODEGENOPT(CallGraphProfile  , 1, 0) ///< Run call graph profile.
 
   /// Attempt to use register sized accesses to bit-fields in structures, when
   /// possible.

clang/lib/CodeGen/BackendUtil.cpp

@@ -657,6 +657,9 @@ void EmitAssemblyHelper::CreatePasses(legacy::PassManager &MPM,
     PMBuilder.SizeLevel = CodeGenOpts.OptimizeSize;
     PMBuilder.SLPVectorize = CodeGenOpts.VectorizeSLP;
     PMBuilder.LoopVectorize = CodeGenOpts.VectorizeLoop;
+    // Only enable CGProfilePass when using integrated assembler, since
+    // non-integrated assemblers don't recognize .cgprofile section.
+    PMBuilder.CallGraphProfile = !CodeGenOpts.DisableIntegratedAS;
 
     PMBuilder.DisableUnrollLoops = !CodeGenOpts.UnrollLoops;
     // Loop interleaving in the loop vectorizer has historically been set to be
@@ -1186,7 +1189,9 @@ void EmitAssemblyHelper::EmitAssemblyWithNewPassManager(
   PTO.LoopInterleaving = CodeGenOpts.UnrollLoops;
   PTO.LoopVectorization = CodeGenOpts.VectorizeLoop;
   PTO.SLPVectorization = CodeGenOpts.VectorizeSLP;
-  PTO.CallGraphProfile = CodeGenOpts.CallGraphProfile;
+  // Only enable CGProfilePass when using integrated assembler, since
+  // non-integrated assemblers don't recognize .cgprofile section.
+  PTO.CallGraphProfile = !CodeGenOpts.DisableIntegratedAS;
   PTO.Coroutines = LangOpts.Coroutines;
 
   PassInstrumentationCallbacks PIC;
@@ -1604,7 +1609,9 @@ static void runThinLTOBackend(
   Conf.PTO.LoopInterleaving = CGOpts.UnrollLoops;
   Conf.PTO.LoopVectorization = CGOpts.VectorizeLoop;
   Conf.PTO.SLPVectorization = CGOpts.VectorizeSLP;
-  Conf.PTO.CallGraphProfile = CGOpts.CallGraphProfile;
+  // Only enable CGProfilePass when using integrated assembler, since
+  // non-integrated assemblers don't recognize .cgprofile section.
+  Conf.PTO.CallGraphProfile = !CGOpts.DisableIntegratedAS;
 
   // Context sensitive profile.
   if (CGOpts.hasProfileCSIRInstr()) {

clang/lib/Frontend/CompilerInvocation.cpp

@@ -864,7 +864,6 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
   Opts.RerollLoops = Args.hasArg(OPT_freroll_loops);
 
   Opts.DisableIntegratedAS = Args.hasArg(OPT_fno_integrated_as);
-  Opts.CallGraphProfile = !Opts.DisableIntegratedAS;
   Opts.Autolink = !Args.hasArg(OPT_fno_autolink);
   Opts.SampleProfileFile =
       std::string(Args.getLastArgValue(OPT_fprofile_sample_use_EQ));

llvm/include/llvm/InitializePasses.h

@@ -103,6 +103,7 @@ void initializeCFGViewerLegacyPassPass(PassRegistry&);
 void initializeCFIInstrInserterPass(PassRegistry&);
 void initializeCFLAndersAAWrapperPassPass(PassRegistry&);
 void initializeCFLSteensAAWrapperPassPass(PassRegistry&);
+void initializeCGProfileLegacyPassPass(PassRegistry &);
 void initializeCallGraphDOTPrinterPass(PassRegistry&);
 void initializeCallGraphPrinterLegacyPassPass(PassRegistry&);
 void initializeCallGraphViewerPass(PassRegistry&);

llvm/include/llvm/Transforms/IPO.h

@@ -282,6 +282,8 @@ ModulePass *createSampleProfileLoaderPass(StringRef Name);
 ModulePass *createWriteThinLTOBitcodePass(raw_ostream &Str,
                                           raw_ostream *ThinLinkOS = nullptr);
 
+ModulePass *createCGProfileLegacyPass();
+
 } // End llvm namespace
 
 #endif

llvm/include/llvm/Transforms/IPO/Attributor.h

@@ -1036,14 +1036,6 @@ struct Attributor {
     identifyDefaultAbstractAttributes(const_cast<Function &>(F));
   }
 
-  /// Helper function to remove callsite.
-  void removeCallSite(CallInst *CI) {
-    if (!CI)
-      return;
-
-    CGUpdater.removeCallSite(*CI);
-  }
-
   /// Record that \p U is to be replaces with \p NV after information was
   /// manifested. This also triggers deletion of trivially dead istructions.
   bool changeUseAfterManifest(Use &U, Value &NV) {

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

@@ -156,6 +156,7 @@ class PassManagerBuilder {
 
   bool DisableTailCalls;
   bool DisableUnrollLoops;
+  bool CallGraphProfile;
   bool SLPVectorize;
   bool LoopVectorize;
   bool LoopsInterleaved;

llvm/include/llvm/Transforms/Instrumentation/CGProfile.h

@@ -19,11 +19,6 @@ namespace llvm {
 class CGProfilePass : public PassInfoMixin<CGProfilePass> {
 public:
   PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
-
-private:
-  void addModuleFlags(
-      Module &M,
-      MapVector<std::pair<Function *, Function *>, uint64_t> &Counts) const;
 };
 } // end namespace llvm
 

llvm/lib/Passes/PassBuilder.cpp

@@ -248,10 +248,6 @@ static cl::opt<bool>
     EnableCHR("enable-chr-npm", cl::init(true), cl::Hidden,
               cl::desc("Enable control height reduction optimization (CHR)"));
 
-static cl::opt<bool> EnableCallGraphProfile(
-    "enable-npm-call-graph-profile", cl::init(true), cl::Hidden,
-    cl::desc("Enable call graph profile pass for the new PM (default = on)"));
-
 /// Flag to enable inline deferral during PGO.
 static cl::opt<bool>
     EnablePGOInlineDeferral("enable-npm-pgo-inline-deferral", cl::init(true),
@@ -267,7 +263,7 @@ PipelineTuningOptions::PipelineTuningOptions() {
   Coroutines = false;
   LicmMssaOptCap = SetLicmMssaOptCap;
   LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
-  CallGraphProfile = EnableCallGraphProfile;
+  CallGraphProfile = true;
 }
 
 extern cl::opt<bool> EnableHotColdSplit;