[llvm] [SampleFDO] Stale profile renaming matching (PR #92151)

[David Li via llvm-commits]

================
@@ -590,14 +617,314 @@ void SampleProfileMatcher::computeAndReportProfileStaleness() {
   }
 }
 
-void SampleProfileMatcher::runOnModule() {
-  ProfileConverter::flattenProfile(Reader.getProfiles(), FlattenedProfiles,
-                                   FunctionSamples::ProfileIsCS);
+// Find functions that don't show in the profile or profile symbol list, which
+// are supposed to be new functions. We use them as the targets for renaming
+// matching.
+void SampleProfileMatcher::findNewIRFunctions(
+    StringMap<Function *> &newIRFunctions) {
+  // TODO: Support MD5 profile.
+  if (FunctionSamples::UseMD5)
+    return;
+  StringSet<> NamesInProfile;
+  if (auto NameTable = Reader.getNameTable()) {
+    for (auto Name : *NameTable)
+      NamesInProfile.insert(Name.stringRef());
+  }
+
   for (auto &F : M) {
-    if (skipProfileForFunction(F))
+    // Skip declarations, as even if the function can be recognized renamed, we
+    // have nothing to do with it.
+    if (F.isDeclaration())
       continue;
-    runOnFunction(F);
+
+    StringRef CanonFName = FunctionSamples::getCanonicalFnName(F.getName());
+    const auto *FS = getFlattenedSamplesFor(F);
+    if (FS)
+      continue;
+
+    // For extended binary, functions are fully inlined may not be loaded in the
+    // top-level profile, so check the NameTable which has the all symbol names
+    // in profile.
+    if (NamesInProfile.count(CanonFName))
+      continue;
+
+    // For extended binary, non-profiled function symbols are in the profile
+    // symbol list table.
+    if (PSL && PSL->contains(CanonFName))
+      continue;
+
+    LLVM_DEBUG(dbgs() << "Function " << CanonFName
+                      << " is not in profile or symbol list table.\n");
+    newIRFunctions[CanonFName] = &F;
+  }
+}
+
+void SampleProfileMatcher::findNewIRCallees(
+    Function &Caller, const StringMap<Function *> &newIRFunctions,
+    std::vector<Function *> &NewIRCallees) {
+  for (auto &BB : Caller) {
+    for (auto &I : BB) {
+      const auto *CB = dyn_cast<CallBase>(&I);
+      if (!CB || isa<IntrinsicInst>(&I))
+        continue;
+      Function *Callee = CB->getCalledFunction();
+      if (!Callee || Callee->isDeclaration())
+        continue;
+      StringRef CalleeName =
+          FunctionSamples::getCanonicalFnName(Callee->getName());
+      if (newIRFunctions.count(CalleeName))
+        NewIRCallees.push_back(Callee);
+    }
+  }
+}
+
+// Find the function using the profile name. If the function is not found but
+// the NewIRCallees is provided, try to match the function profile with all
+// functions in NewIRCallees and return the matched function.
+// The return pair includes the function pointer and a bool value indicating
+// whether the function is new(matched).
+std::pair<Function *, bool> SampleProfileMatcher::findOrMatchNewFunction(
+    const FunctionId &ProfCallee, FunctionMap &OldProfToNewSymbolMap,
+    const std::vector<Function *> &NewIRCallees = std::vector<Function *>()) {
+  auto F = SymbolMap->find(ProfCallee);
+  if (F != SymbolMap->end())
+    return {F->second, false};
+
+  // Existing matched function is found.
+  auto NewF = OldProfToNewSymbolMap.find(ProfCallee);
+  if (NewF != OldProfToNewSymbolMap.end())
+    return {NewF->second, true};
+
+  for (auto *IRCallee : NewIRCallees)
+    if (functionMatchesProfile(*IRCallee, ProfCallee)) {
+      OldProfToNewSymbolMap[ProfCallee] = IRCallee;
+      return {IRCallee, true};
+    }
+  return {nullptr, false};
+}
+
+// Determine if the function matches profile by computing a similarity ratio
+// between two callsite anchors sequences extracted from function and profile.
+bool SampleProfileMatcher::functionMatchesProfileHelper(
+    const Function &IRFunc, const FunctionId &ProfFunc) {
+  // The value is in the range [0, 1]. The bigger the value is, the more similar
+  // two sequences are.
+  float Similarity = 0.0;
+
+  const auto *FSFlattened = getFlattenedSamplesFor(ProfFunc);
+  assert(FSFlattened && "Flattened profile sample is null");
+  // Similarity check may not be reiable if the function is tiny, we use the
----------------
david-xl wrote:

s/reiable/reliable/

https://github.com/llvm/llvm-project/pull/92151