[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)

[Amir Ayupov via llvm-branch-commits]

================
@@ -415,6 +422,75 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
     if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
       matchProfileToFunction(YamlBF, *BF);
 
+  // Uses name similarity to match functions that were not matched by name.
+  uint64_t MatchedWithDemangledName = 0;
+
+  if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+    auto DemangleName = [&](const char* String) {
+      int Status = 0;
+      char *DemangledName = abi::__cxa_demangle(String,
+                                                nullptr, nullptr, &Status);
+      return Status == 0 ? new std::string(DemangledName) : nullptr;
+    };
+
+    auto DeriveNameSpace = [&](std::string DemangledName) {
+      size_t LParen = std::string(DemangledName).find("(");
+      std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+      size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+      return ScopeResolutionOperator == std::string::npos ? std::string("") : std::string(DemangledName).substr(0, ScopeResolutionOperator);
+    };
+
+    std::unordered_map<std::string, std::vector<BinaryFunction *>> NamespaceToBFs;
+    NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+    for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+      std::string* DemangledName = DemangleName(BF->getOneName().str().c_str());
+      if (!DemangledName)
+        continue;
+      std::string Namespace = DeriveNameSpace(*DemangledName);
+      auto It = NamespaceToBFs.find(Namespace);
+      if (It == NamespaceToBFs.end())
+        NamespaceToBFs[Namespace] = {BF};
+      else
+        It->second.push_back(BF);
+    }
+
+    for (auto YamlBF : YamlBP.Functions) {
+      if (YamlBF.Used)
+        continue;
+      std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+      if (!YamlBFDemangledName)
+        continue;
+      std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+      auto It = NamespaceToBFs.find(Namespace);
+      if (It == NamespaceToBFs.end())
+        continue;
+      std::vector<BinaryFunction *> BFs = It->second;
+
+      unsigned MinEditDistance = UINT_MAX;
+      BinaryFunction *ClosestNameBF = nullptr;
+
+      for (BinaryFunction *BF : BFs) {
+        if (ProfiledFunctions.count(BF))
+          continue;
+        std::string *BFDemangledName = DemangleName(BF->getOneName().str().c_str());
----------------
aaupov wrote:

```suggestion
        std::string *BFDemangledName = BF->getDemangledName();
```

https://github.com/llvm/llvm-project/pull/95884