Infrastructure for more compact bytecode files and REAL support for versioning

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@5716 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 47 insertions, 9 deletions

diff --git a/lib/Bytecode/Reader/Reader.cpp b/lib/Bytecode/Reader/Reader.cpp
index b1d3ae0..48e14dd 100644
--- a/lib/Bytecode/Reader/Reader.cpp
+++ b/lib/Bytecode/Reader/Reader.cpp
@@ -60,8 +60,12 @@ int BytecodeParser::insertValue(Value *Val, std::vector<ValueList> &ValueTab) {
   if (getTypeSlot(Val->getType(), type)) return -1;
   assert(type != Type::TypeTyID && "Types should never be insertValue'd!");
  
-  if (ValueTab.size() <= type)
-    ValueTab.resize(type+1, ValueList());
+  while (ValueTab.size() <= type) {
+    ValueTab.push_back(ValueList());
+    if (HasImplicitZeroInitializer)   // add a zero initializer if appropriate
+      ValueTab.back().push_back(
+                 Constant::getNullValue(getType(ValueTab.size()-1)));
+  }
 
   //cerr << "insertValue Values[" << type << "][" << ValueTab[type].size() 
   //     << "] = " << Val << "\n";
@@ -194,8 +198,7 @@ bool BytecodeParser::ParseBasicBlock(const uchar *&Buf, const uchar *EndBuf,
 
   while (Buf < EndBuf) {
     Instruction *Inst;
-    if (ParseInstruction(Buf, EndBuf, Inst,
-                         /*HACK*/BB)) {
+    if (ParseInstruction(Buf, EndBuf, Inst, /*HACK*/BB)) {
       delete BB;
       return true;
     }
@@ -490,6 +493,38 @@ bool BytecodeParser::ParseModuleGlobalInfo(const uchar *&Buf, const uchar *End){
   return false;
 }
 
+bool BytecodeParser::ParseVersionInfo(const uchar *&Buf, const uchar *EndBuf) {
+  unsigned Version;
+  if (read_vbr(Buf, EndBuf, Version)) return true;
+
+  // Unpack version number: low four bits are for flags, top bits = version
+  isBigEndian     = Version & 1;
+  hasLongPointers = Version & 2;
+  RevisionNum     = Version >> 4;
+  HasImplicitZeroInitializer = true;
+
+  switch (RevisionNum) {
+  case 0:                  // Initial revision
+    if (Version != 14) return true;  // Unknown revision 0 flags?
+    FirstDerivedTyID = 14;
+    HasImplicitZeroInitializer = false;
+    isBigEndian = hasLongPointers = true;
+    break;
+  case 1:
+    FirstDerivedTyID = 14;
+    break;
+  default:
+    Error = "Unknown bytecode version number!";
+    return true;
+  }
+
+  BCR_TRACE(1, "Bytecode Rev = " << (unsigned)RevisionNum << "\n");
+  BCR_TRACE(1, "BigEndian/LongPointers = " << isBigEndian << ","
+               << hasLongPointers << "\n");
+  BCR_TRACE(1, "HasImplicitZeroInit = " << HasImplicitZeroInitializer << "\n");
+  return false;
+}
+
 bool BytecodeParser::ParseModule(const uchar *Buf, const uchar *EndBuf) {
   unsigned Type, Size;
   if (readBlock(Buf, EndBuf, Type, Size)) return true;
@@ -502,9 +537,8 @@ bool BytecodeParser::ParseModule(const uchar *Buf, const uchar *EndBuf) {
   FunctionSignatureList.clear();                 // Just in case...
 
   // Read into instance variables...
-  if (read_vbr(Buf, EndBuf, FirstDerivedTyID)) return true;
+  if (ParseVersionInfo(Buf, EndBuf)) return true;
   if (align32(Buf, EndBuf)) return true;
-  BCR_TRACE(1, "FirstDerivedTyID = " << FirstDerivedTyID << "\n");
 
   while (Buf < EndBuf) {
     const unsigned char *OldBuf = Buf;
diff --git a/lib/Bytecode/Reader/ReaderInternals.h b/lib/Bytecode/Reader/ReaderInternals.h
index 9ed7e29..09a21d7 100644
--- a/lib/Bytecode/Reader/ReaderInternals.h
+++ b/lib/Bytecode/Reader/ReaderInternals.h
@@ -57,6 +57,12 @@ public:
 private:          // All of this data is transient across calls to ParseBytecode
   Module *TheModule;   // Current Module being read into...
   
+  // Information about the module, extracted from the bytecode revision number.
+  unsigned char RevisionNum;        // The rev # itself
+  unsigned char FirstDerivedTyID;   // First variable index to use for type
+  bool HasImplicitZeroInitializer;  // Is entry 0 of every slot implicity zeros?
+  bool isBigEndian, hasLongPointers;// Information about the target compiled for
+
   typedef std::vector<Value *> ValueList;
   typedef std::vector<ValueList> ValueTable;
   ValueTable Values, LateResolveValues;
@@ -78,9 +84,6 @@ private:          // All of this data is transient across calls to ParseBytecode
   TypeValuesListTy ModuleTypeValues;
   TypeValuesListTy FunctionTypeValues;
 
-  // Information read from the ModuleGlobalInfo section of the file...
-  unsigned FirstDerivedTyID;
-
   // When the ModuleGlobalInfo section is read, we load the type of each
   // function and the 'ModuleValues' slot that it lands in.  We then load a
   // placeholder into its slot to reserve it.  When the function is loaded, this
@@ -90,6 +93,7 @@ private:          // All of this data is transient across calls to ParseBytecode
 
 private:
   bool ParseModule          (const uchar * Buf, const uchar *End);
+  bool ParseVersionInfo     (const uchar *&Buf, const uchar *End);
   bool ParseModuleGlobalInfo(const uchar *&Buf, const uchar *End);
   bool ParseSymbolTable   (const uchar *&Buf, const uchar *End, SymbolTable *);
   bool ParseFunction      (const uchar *&Buf, const uchar *End);