5 files changed, 47 insertions, 31 deletions

diff --git a/llvm/include/llvm/IR/Function.h b/llvm/include/llvm/IR/Function.h
index e79c891149d..1ed200f0e18 100644
--- a/llvm/include/llvm/IR/Function.h
+++ b/llvm/include/llvm/IR/Function.h
@@ -639,6 +639,14 @@ public:
   /// to \a DISubprogram.
   DISubprogram *getSubprogram() const;
 
+  /// Return the modified name for a function suitable to be
+  /// used as the key for a global lookup (e.g. profile or ThinLTO).
+  /// The function's original name is \c FuncName and has linkage of type
+  /// \c Linkage. The function is defined in module \c FileName.
+  static std::string getGlobalIdentifier(StringRef FuncName,
+                                         GlobalValue::LinkageTypes Linkage,
+                                         StringRef FileName);
+
 private:
   void allocHungoffUselist();
   template<int Idx> void setHungoffOperand(Constant *C);
diff --git a/llvm/include/llvm/ProfileData/InstrProf.h b/llvm/include/llvm/ProfileData/InstrProf.h
index 927ed1e599a..c1db9b63404 100644
--- a/llvm/include/llvm/ProfileData/InstrProf.h
+++ b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -626,21 +626,10 @@ enum class HashT : uint32_t {
   Last = MD5
 };
 
-static inline uint64_t MD5Hash(StringRef Str) {
-  MD5 Hash;
-  Hash.update(Str);
-  llvm::MD5::MD5Result Result;
-  Hash.final(Result);
-  // Return the least significant 8 bytes. Our MD5 implementation returns the
-  // result in little endian, so we may need to swap bytes.
-  using namespace llvm::support;
-  return endian::read<uint64_t, little, unaligned>(Result);
-}
-
 inline uint64_t ComputeHash(HashT Type, StringRef K) {
   switch (Type) {
   case HashT::MD5:
-    return IndexedInstrProf::MD5Hash(K);
+    return MD5Hash(K);
   }
   llvm_unreachable("Unhandled hash type");
 }
diff --git a/llvm/include/llvm/Support/MD5.h b/llvm/include/llvm/Support/MD5.h
index f6e1e92c9fa..0ce0b438fe4 100644
--- a/llvm/include/llvm/Support/MD5.h
+++ b/llvm/include/llvm/Support/MD5.h
@@ -31,6 +31,7 @@
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/Support/DataTypes.h"
+#include "llvm/Support/Endian.h"
 
 namespace llvm {
 
@@ -65,6 +66,18 @@ private:
   const uint8_t *body(ArrayRef<uint8_t> Data);
 };
 
+/// Helper to compute and return a 64-bit MD5 Hash of a given string.
+inline uint64_t MD5Hash(StringRef Str) {
+  MD5 Hash;
+  Hash.update(Str);
+  llvm::MD5::MD5Result Result;
+  Hash.final(Result);
+  // Return the least significant 8 bytes. Our MD5 implementation returns the
+  // result in little endian, so we may need to swap bytes.
+  using namespace llvm::support;
+  return endian::read<uint64_t, little, unaligned>(Result);
+}
+
 }
 
 #endif
diff --git a/llvm/lib/IR/Function.cpp b/llvm/lib/IR/Function.cpp
index 40a8ec61ca2..da1ddedc3dd 100644
--- a/llvm/lib/IR/Function.cpp
+++ b/llvm/lib/IR/Function.cpp
@@ -997,3 +997,27 @@ Optional<uint64_t> Function::getEntryCount() const {
       }
   return None;
 }
+
+std::string Function::getGlobalIdentifier(StringRef FuncName,
+                                          GlobalValue::LinkageTypes Linkage,
+                                          StringRef FileName) {
+
+  // Function names may be prefixed with a binary '1' to indicate
+  // that the backend should not modify the symbols due to any platform
+  // naming convention. Do not include that '1' in the PGO profile name.
+  if (FuncName[0] == '\1')
+    FuncName = FuncName.substr(1);
+
+  std::string NewFuncName = FuncName;
+  if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
+    // For local symbols, prepend the main file name to distinguish them.
+    // Do not include the full path in the file name since there's no guarantee
+    // that it will stay the same, e.g., if the files are checked out from
+    // version control in different locations.
+    if (FileName.empty())
+      NewFuncName = NewFuncName.insert(0, "<unknown>:");
+    else
+      NewFuncName = NewFuncName.insert(0, FileName.str() + ":");
+  }
+  return NewFuncName;
+}
diff --git a/llvm/lib/ProfileData/InstrProf.cpp b/llvm/lib/ProfileData/InstrProf.cpp
index 1cfc21e493a..551c414cff6 100644
--- a/llvm/lib/ProfileData/InstrProf.cpp
+++ b/llvm/lib/ProfileData/InstrProf.cpp
@@ -80,25 +80,7 @@ std::string getPGOFuncName(StringRef RawFuncName,
                            GlobalValue::LinkageTypes Linkage,
                            StringRef FileName,
                            uint64_t Version LLVM_ATTRIBUTE_UNUSED) {
-
-  // Function names may be prefixed with a binary '1' to indicate
-  // that the backend should not modify the symbols due to any platform
-  // naming convention. Do not include that '1' in the PGO profile name.
-  if (RawFuncName[0] == '\1')
-    RawFuncName = RawFuncName.substr(1);
-
-  std::string FuncName = RawFuncName;
-  if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
-    // For local symbols, prepend the main file name to distinguish them.
-    // Do not include the full path in the file name since there's no guarantee
-    // that it will stay the same, e.g., if the files are checked out from
-    // version control in different locations.
-    if (FileName.empty())
-      FuncName = FuncName.insert(0, "<unknown>:");
-    else
-      FuncName = FuncName.insert(0, FileName.str() + ":");
-  }
-  return FuncName;
+  return Function::getGlobalIdentifier(RawFuncName, Linkage, FileName);
 }
 
 std::string getPGOFuncName(const Function &F, uint64_t Version) {