Enhance synchscope representation

OpenCL 2.0 introduces the notion of memory scopes in atomic operations to
  global and local memory. These scopes restrict how synchronization is
  achieved, which can result in improved performance.

  This change extends existing notion of synchronization scopes in LLVM to
  support arbitrary scopes expressed as target-specific strings, in addition to
  the already defined scopes (single thread, system).

  The LLVM IR and MIR syntax for expressing synchronization scopes has changed
  to use *syncscope("<scope>")*, where <scope> can be "singlethread" (this
  replaces *singlethread* keyword), or a target-specific name. As before, if
  the scope is not specified, it defaults to CrossThread/System scope.

  Implementation details:
    - Mapping from synchronization scope name/string to synchronization scope id
      is stored in LLVM context;
    - CrossThread/System and SingleThread scopes are pre-defined to efficiently
      check for known scopes without comparing strings;
    - Synchronization scope names are stored in SYNC_SCOPE_NAMES_BLOCK in
      the bitcode.

Differential Revision: https://reviews.llvm.org/D21723

llvm-svn: 307722

llvm/lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -266,6 +266,7 @@ private:
                                     const GlobalObject &GO);
   void writeModuleMetadataKinds();
   void writeOperandBundleTags();
+  void writeSyncScopeNames();
   void writeConstants(unsigned FirstVal, unsigned LastVal, bool isGlobal);
   void writeModuleConstants();
   bool pushValueAndType(const Value *V, unsigned InstID,
@@ -316,6 +317,10 @@ private:
     return VE.getValueID(VI.getValue());
   }
   std::map<GlobalValue::GUID, unsigned> &valueIds() { return GUIDToValueIdMap; }
+
+  unsigned getEncodedSyncScopeID(SyncScope::ID SSID) {
+    return unsigned(SSID);
+  }
 };
 
 /// Class to manage the bitcode writing for a combined index.
@@ -485,14 +490,6 @@ static unsigned getEncodedOrdering(AtomicOrdering Ordering) {
   llvm_unreachable("Invalid ordering");
 }
 
-static unsigned getEncodedSynchScope(SynchronizationScope SynchScope) {
-  switch (SynchScope) {
-  case SingleThread: return bitc::SYNCHSCOPE_SINGLETHREAD;
-  case CrossThread: return bitc::SYNCHSCOPE_CROSSTHREAD;
-  }
-  llvm_unreachable("Invalid synch scope");
-}
-
 static void writeStringRecord(BitstreamWriter &Stream, unsigned Code,
                               StringRef Str, unsigned AbbrevToUse) {
   SmallVector<unsigned, 64> Vals;
@@ -2042,6 +2039,24 @@ void ModuleBitcodeWriter::writeOperandBundleTags() {
   Stream.ExitBlock();
 }
 
+void ModuleBitcodeWriter::writeSyncScopeNames() {
+  SmallVector<StringRef, 8> SSNs;
+  M.getContext().getSyncScopeNames(SSNs);
+  if (SSNs.empty())
+    return;
+
+  Stream.EnterSubblock(bitc::SYNC_SCOPE_NAMES_BLOCK_ID, 2);
+
+  SmallVector<uint64_t, 64> Record;
+  for (auto SSN : SSNs) {
+    Record.append(SSN.begin(), SSN.end());
+    Stream.EmitRecord(bitc::SYNC_SCOPE_NAME, Record, 0);
+    Record.clear();
+  }
+
+  Stream.ExitBlock();
+}
+
 static void emitSignedInt64(SmallVectorImpl<uint64_t> &Vals, uint64_t V) {
   if ((int64_t)V >= 0)
     Vals.push_back(V << 1);
@@ -2658,7 +2673,7 @@ void ModuleBitcodeWriter::writeInstruction(const Instruction &I,
     Vals.push_back(cast<LoadInst>(I).isVolatile());
     if (cast<LoadInst>(I).isAtomic()) {
       Vals.push_back(getEncodedOrdering(cast<LoadInst>(I).getOrdering()));
-      Vals.push_back(getEncodedSynchScope(cast<LoadInst>(I).getSynchScope()));
+      Vals.push_back(getEncodedSyncScopeID(cast<LoadInst>(I).getSyncScopeID()));
     }
     break;
   case Instruction::Store:
@@ -2672,7 +2687,8 @@ void ModuleBitcodeWriter::writeInstruction(const Instruction &I,
     Vals.push_back(cast<StoreInst>(I).isVolatile());
     if (cast<StoreInst>(I).isAtomic()) {
       Vals.push_back(getEncodedOrdering(cast<StoreInst>(I).getOrdering()));
-      Vals.push_back(getEncodedSynchScope(cast<StoreInst>(I).getSynchScope()));
+      Vals.push_back(
+          getEncodedSyncScopeID(cast<StoreInst>(I).getSyncScopeID()));
     }
     break;
   case Instruction::AtomicCmpXchg:
@@ -2684,7 +2700,7 @@ void ModuleBitcodeWriter::writeInstruction(const Instruction &I,
     Vals.push_back(
         getEncodedOrdering(cast<AtomicCmpXchgInst>(I).getSuccessOrdering()));
     Vals.push_back(
-        getEncodedSynchScope(cast<AtomicCmpXchgInst>(I).getSynchScope()));
+        getEncodedSyncScopeID(cast<AtomicCmpXchgInst>(I).getSyncScopeID()));
     Vals.push_back(
         getEncodedOrdering(cast<AtomicCmpXchgInst>(I).getFailureOrdering()));
     Vals.push_back(cast<AtomicCmpXchgInst>(I).isWeak());
@@ -2698,12 +2714,12 @@ void ModuleBitcodeWriter::writeInstruction(const Instruction &I,
     Vals.push_back(cast<AtomicRMWInst>(I).isVolatile());
     Vals.push_back(getEncodedOrdering(cast<AtomicRMWInst>(I).getOrdering()));
     Vals.push_back(
-        getEncodedSynchScope(cast<AtomicRMWInst>(I).getSynchScope()));
+        getEncodedSyncScopeID(cast<AtomicRMWInst>(I).getSyncScopeID()));
     break;
   case Instruction::Fence:
     Code = bitc::FUNC_CODE_INST_FENCE;
     Vals.push_back(getEncodedOrdering(cast<FenceInst>(I).getOrdering()));
-    Vals.push_back(getEncodedSynchScope(cast<FenceInst>(I).getSynchScope()));
+    Vals.push_back(getEncodedSyncScopeID(cast<FenceInst>(I).getSyncScopeID()));
     break;
   case Instruction::Call: {
     const CallInst &CI = cast<CallInst>(I);
@@ -3716,6 +3732,7 @@ void ModuleBitcodeWriter::write() {
     writeUseListBlock(nullptr);
 
   writeOperandBundleTags();
+  writeSyncScopeNames();
 
   // Emit function bodies.
   DenseMap<const Function *, uint64_t> FunctionToBitcodeIndex;