[PGO] Add hash to name mapping in InstrProfSymtab

Creator and lookup interfaces are added to this symtab class.
The new interfaces will be used by InstrProf Readers and writer.

A unit test is also added for the new APIs.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256092 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/ProfileData/InstrProf.h b/include/llvm/ProfileData/InstrProf.h
index b0d08a5886f887f458999565ac906c19ec695fe2..ac60e8053c253cdabe2b9571049c6ef1d7c28d37 100644 (file)
--- a/include/llvm/ProfileData/InstrProf.h
+++ b/include/llvm/ProfileData/InstrProf.h
@@ -202,6 +202,11 @@ enum InstrProfValueKind : uint32_t {
 namespace object {
 class SectionRef;
 }
+
+namespace IndexedInstrProf {
+uint64_t ComputeHash(StringRef K);
+}
+
 /// A symbol table used for function PGO name look-up with keys
 /// (such as pointers, md5hash values) to the function. A function's
 /// PGO name or name's md5hash are used in retrieving the profile
@@ -211,6 +216,7 @@ class InstrProfSymtab {
 private:
   StringRef Data;
   uint64_t Address;
+  std::vector<std::pair<uint64_t, std::string>> HashNameMap;
 
 public:
   InstrProfSymtab() : Data(), Address(0) {}
@@ -223,11 +229,45 @@ public:
     Address = BaseAddr;
     return std::error_code();
   }
+  template <typename NameIterRange> void create(NameIterRange &IterRange) {
+    for (auto Name : IterRange)
+      HashNameMap.push_back(
+          std::make_pair(IndexedInstrProf::ComputeHash(Name), Name.str()));
+    finalizeSymtab();
+  }
+
+  // If the symtab is created by a series calls to \c addFuncName, \c
+  // finalizeSymtab needs to
+  // be called before function name/symbol lookup using MD5 hash. This is
+  // required because
+  // the underlying map is vector (for space efficiency) which needs to be
+  // sorted.
+  void finalizeSymtab() {
+    std::sort(HashNameMap.begin(), HashNameMap.end(), less_first());
+    HashNameMap.erase(std::unique(HashNameMap.begin(), HashNameMap.end()),
+                      HashNameMap.end());
+  }
+
+  void addFuncName(StringRef FuncName) {
+    HashNameMap.push_back(std::make_pair(
+        IndexedInstrProf::ComputeHash(FuncName), FuncName.str()));
+  }
 
   /// Return function's PGO name from the function name's symabol
   /// address in the object file. If an error occurs, Return
   /// an empty string.
   StringRef getFuncName(uint64_t FuncNameAddress, size_t NameSize);
+  /// Return function's PGO name from the name's md5 hash value.
+  /// If not found, return an empty string.
+  StringRef getFuncName(uint64_t FuncMD5Hash) {
+    auto Result =
+        std::lower_bound(HashNameMap.begin(), HashNameMap.end(), FuncMD5Hash,
+                         [](const std::pair<uint64_t, std::string> &LHS,
+                            uint64_t RHS) { return LHS.first < RHS; });
+    if (Result != HashNameMap.end())
+      return Result->second;
+    return StringRef();
+  }
 };
 
 struct InstrProfStringTable {
@@ -481,7 +521,7 @@ static inline uint64_t MD5Hash(StringRef Str) {
   return endian::read<uint64_t, little, unaligned>(Result);
 }
 
-static inline uint64_t ComputeHash(HashT Type, StringRef K) {
+inline uint64_t ComputeHash(HashT Type, StringRef K) {
   switch (Type) {
   case HashT::MD5:
     return IndexedInstrProf::MD5Hash(K);
@@ -493,9 +533,7 @@ const uint64_t Magic = 0x8169666f72706cff; // "\xfflprofi\x81"
 const uint64_t Version = INSTR_PROF_INDEX_VERSION;
 const HashT HashType = HashT::MD5;
 
-static inline uint64_t ComputeHash(StringRef K) {
-  return ComputeHash(HashType, K);
-}
+inline uint64_t ComputeHash(StringRef K) { return ComputeHash(HashType, K); }
 
 // This structure defines the file header of the LLVM profile
 // data file in indexed-format.

diff --git a/unittests/ProfileData/InstrProfTest.cpp b/unittests/ProfileData/InstrProfTest.cpp
index ee357053a17a9d0a8168e90f4d9611dde1c1c542..994f75502d9f2f5d9ebce5ea3d4dfbeaa84ac92e 100644 (file)
--- a/unittests/ProfileData/InstrProfTest.cpp
+++ b/unittests/ProfileData/InstrProfTest.cpp
@@ -524,4 +524,28 @@ TEST_F(InstrProfTest, get_weighted_function_counts) {
   ASSERT_EQ(20U, Counts[1]);
 }
 
+TEST_F(InstrProfTest, instr_prof_symtab_test) {
+  std::vector<StringRef> FuncNames;
+  FuncNames.push_back("func1");
+  FuncNames.push_back("func2");
+  FuncNames.push_back("func3");
+  FuncNames.push_back("bar1");
+  FuncNames.push_back("bar2");
+  FuncNames.push_back("bar3");
+  InstrProfSymtab Symtab;
+  Symtab.create(FuncNames);
+  StringRef R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("func1"));
+  ASSERT_EQ(StringRef("func1"), R);
+  R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("func2"));
+  ASSERT_EQ(StringRef("func2"), R);
+  R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("func3"));
+  ASSERT_EQ(StringRef("func3"), R);
+  R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("bar1"));
+  ASSERT_EQ(StringRef("bar1"), R);
+  R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("bar2"));
+  ASSERT_EQ(StringRef("bar2"), R);
+  R = Symtab.getFuncName(IndexedInstrProf::ComputeHash("bar3"));
+  ASSERT_EQ(StringRef("bar3"), R);
+}
+
 } // end anonymous namespace