Change encoding of instruction operands in bitcode binaries to be relative

to the instruction position.  The old encoding would give an absolute
ID which counts up within a function, and only resets at the next function.

I.e., Instead of having:

... = icmp eq i32 n-1, n-2
br i1 ..., label %bb1, label %bb2

it will now be roughly:

... = icmp eq i32 1, 2
br i1 1, label %bb1, label %bb2

This makes it so that ids remain relatively small and can be encoded
in fewer bits.

With this encoding, forward reference operands will be given
negative-valued IDs.  Use signed VBRs for the most common case
of forward references, which is phi instructions.

To retain backward compatibility we bump the bitcode version
from 0 to 1 to distinguish between the different encodings.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165739 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 107 insertions, 46 deletions

diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp
index 8860ef065c..1a3a7b0f3f 100644
--- a/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -891,9 +891,9 @@ bool BitcodeReader::ParseMetadata() {
   }
 }
 
-/// DecodeSignRotatedValue - Decode a signed value stored with the sign bit in
+/// decodeSignRotatedValue - Decode a signed value stored with the sign bit in
 /// the LSB for dense VBR encoding.
-static uint64_t DecodeSignRotatedValue(uint64_t V) {
+uint64_t BitcodeReader::decodeSignRotatedValue(uint64_t V) {
   if ((V & 1) == 0)
     return V >> 1;
   if (V != 1)
@@ -943,7 +943,7 @@ bool BitcodeReader::ResolveGlobalAndAliasInits() {
 static APInt ReadWideAPInt(ArrayRef<uint64_t> Vals, unsigned TypeBits) {
   SmallVector<uint64_t, 8> Words(Vals.size());
   std::transform(Vals.begin(), Vals.end(), Words.begin(),
-                 DecodeSignRotatedValue);
+                 BitcodeReader::decodeSignRotatedValue);
 
   return APInt(TypeBits, Words);
 }
@@ -997,7 +997,7 @@ bool BitcodeReader::ParseConstants() {
     case bitc::CST_CODE_INTEGER:   // INTEGER: [intval]
       if (!CurTy->isIntegerTy() || Record.empty())
         return Error("Invalid CST_INTEGER record");
-      V = ConstantInt::get(CurTy, DecodeSignRotatedValue(Record[0]));
+      V = ConstantInt::get(CurTy, decodeSignRotatedValue(Record[0]));
       break;
     case bitc::CST_CODE_WIDE_INTEGER: {// WIDE_INTEGER: [n x intval]
       if (!CurTy->isIntegerTy() || Record.empty())
@@ -1524,13 +1524,22 @@ bool BitcodeReader::ParseModule(bool Resume) {
     // Read a record.
     switch (Stream.ReadRecord(Code, Record)) {
     default: break;  // Default behavior, ignore unknown content.
-    case bitc::MODULE_CODE_VERSION:  // VERSION: [version#]
+    case bitc::MODULE_CODE_VERSION: {  // VERSION: [version#]
       if (Record.size() < 1)
         return Error("Malformed MODULE_CODE_VERSION");
-      // Only version #0 is supported so far.
-      if (Record[0] != 0)
-        return Error("Unknown bitstream version!");
+      // Only version #0 and #1 are supported so far.
+      unsigned module_version = Record[0];
+      switch (module_version) {
+        default: return Error("Unknown bitstream version!");
+        case 0:
+          UseRelativeIDs = false;
+          break;
+        case 1:
+          UseRelativeIDs = true;
+          break;
+      }
       break;
+    }
     case bitc::MODULE_CODE_TRIPLE: {  // TRIPLE: [strchr x N]
       std::string S;
       if (ConvertToString(Record, 0, S))
@@ -1797,13 +1806,6 @@ bool BitcodeReader::ParseModuleTriple(std::string &Triple) {
     // Read a record.
     switch (Stream.ReadRecord(Code, Record)) {
     default: break;  // Default behavior, ignore unknown content.
-    case bitc::MODULE_CODE_VERSION:  // VERSION: [version#]
-      if (Record.size() < 1)
-        return Error("Malformed MODULE_CODE_VERSION");
-      // Only version #0 is supported so far.
-      if (Record[0] != 0)
-        return Error("Unknown bitstream version!");
-      break;
     case bitc::MODULE_CODE_TRIPLE: {  // TRIPLE: [strchr x N]
       std::string S;
       if (ConvertToString(Record, 0, S))
@@ -2016,7 +2018,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *LHS, *RHS;
       if (getValueTypePair(Record, OpNum, NextValueNo, LHS) ||
-          getValue(Record, OpNum, LHS->getType(), RHS) ||
+          popValue(Record, OpNum, NextValueNo, LHS->getType(), RHS) ||
           OpNum+1 > Record.size())
         return Error("Invalid BINOP record");
 
@@ -2131,8 +2133,8 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *TrueVal, *FalseVal, *Cond;
       if (getValueTypePair(Record, OpNum, NextValueNo, TrueVal) ||
-          getValue(Record, OpNum, TrueVal->getType(), FalseVal) ||
-          getValue(Record, OpNum, Type::getInt1Ty(Context), Cond))
+          popValue(Record, OpNum, NextValueNo, TrueVal->getType(), FalseVal) ||
+          popValue(Record, OpNum, NextValueNo, Type::getInt1Ty(Context), Cond))
         return Error("Invalid SELECT record");
 
       I = SelectInst::Create(Cond, TrueVal, FalseVal);
@@ -2146,7 +2148,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *TrueVal, *FalseVal, *Cond;
       if (getValueTypePair(Record, OpNum, NextValueNo, TrueVal) ||
-          getValue(Record, OpNum, TrueVal->getType(), FalseVal) ||
+          popValue(Record, OpNum, NextValueNo, TrueVal->getType(), FalseVal) ||
           getValueTypePair(Record, OpNum, NextValueNo, Cond))
         return Error("Invalid SELECT record");
 
@@ -2171,7 +2173,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Vec, *Idx;
       if (getValueTypePair(Record, OpNum, NextValueNo, Vec) ||
-          getValue(Record, OpNum, Type::getInt32Ty(Context), Idx))
+          popValue(Record, OpNum, NextValueNo, Type::getInt32Ty(Context), Idx))
         return Error("Invalid EXTRACTELT record");
       I = ExtractElementInst::Create(Vec, Idx);
       InstructionList.push_back(I);
@@ -2182,9 +2184,9 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Vec, *Elt, *Idx;
       if (getValueTypePair(Record, OpNum, NextValueNo, Vec) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                    cast<VectorType>(Vec->getType())->getElementType(), Elt) ||
-          getValue(Record, OpNum, Type::getInt32Ty(Context), Idx))
+          popValue(Record, OpNum, NextValueNo, Type::getInt32Ty(Context), Idx))
         return Error("Invalid INSERTELT record");
       I = InsertElementInst::Create(Vec, Elt, Idx);
       InstructionList.push_back(I);
@@ -2195,7 +2197,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Vec1, *Vec2, *Mask;
       if (getValueTypePair(Record, OpNum, NextValueNo, Vec1) ||
-          getValue(Record, OpNum, Vec1->getType(), Vec2))
+          popValue(Record, OpNum, NextValueNo, Vec1->getType(), Vec2))
         return Error("Invalid SHUFFLEVEC record");
 
       if (getValueTypePair(Record, OpNum, NextValueNo, Mask))
@@ -2215,7 +2217,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *LHS, *RHS;
       if (getValueTypePair(Record, OpNum, NextValueNo, LHS) ||
-          getValue(Record, OpNum, LHS->getType(), RHS) ||
+          popValue(Record, OpNum, NextValueNo, LHS->getType(), RHS) ||
           OpNum+1 != Record.size())
         return Error("Invalid CMP record");
 
@@ -2260,7 +2262,8 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       }
       else {
         BasicBlock *FalseDest = getBasicBlock(Record[1]);
-        Value *Cond = getFnValueByID(Record[2], Type::getInt1Ty(Context));
+        Value *Cond = getValue(Record, 2, NextValueNo,
+                               Type::getInt1Ty(Context));
         if (FalseDest == 0 || Cond == 0)
           return Error("Invalid BR record");
         I = BranchInst::Create(TrueDest, FalseDest, Cond);
@@ -2276,7 +2279,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
         Type *OpTy = getTypeByID(Record[1]);
         unsigned ValueBitWidth = cast<IntegerType>(OpTy)->getBitWidth();
 
-        Value *Cond = getFnValueByID(Record[2], OpTy);
+        Value *Cond = getValue(Record, 2, NextValueNo, OpTy);
         BasicBlock *Default = getBasicBlock(Record[3]);
         if (OpTy == 0 || Cond == 0 || Default == 0)
           return Error("Invalid SWITCH record");
@@ -2331,7 +2334,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       if (Record.size() < 3 || (Record.size() & 1) == 0)
         return Error("Invalid SWITCH record");
       Type *OpTy = getTypeByID(Record[0]);
-      Value *Cond = getFnValueByID(Record[1], OpTy);
+      Value *Cond = getValue(Record, 1, NextValueNo, OpTy);
       BasicBlock *Default = getBasicBlock(Record[2]);
       if (OpTy == 0 || Cond == 0 || Default == 0)
         return Error("Invalid SWITCH record");
@@ -2355,7 +2358,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       if (Record.size() < 2)
         return Error("Invalid INDIRECTBR record");
       Type *OpTy = getTypeByID(Record[0]);
-      Value *Address = getFnValueByID(Record[1], OpTy);
+      Value *Address = getValue(Record, 1, NextValueNo, OpTy);
       if (OpTy == 0 || Address == 0)
         return Error("Invalid INDIRECTBR record");
       unsigned NumDests = Record.size()-2;
@@ -2397,7 +2400,8 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
 
       SmallVector<Value*, 16> Ops;
       for (unsigned i = 0, e = FTy->getNumParams(); i != e; ++i, ++OpNum) {
-        Ops.push_back(getFnValueByID(Record[OpNum], FTy->getParamType(i)));
+        Ops.push_back(getValue(Record, OpNum, NextValueNo,
+                               FTy->getParamType(i)));
         if (Ops.back() == 0) return Error("Invalid INVOKE record");
       }
 
@@ -2444,7 +2448,14 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       InstructionList.push_back(PN);
 
       for (unsigned i = 0, e = Record.size()-1; i != e; i += 2) {
-        Value *V = getFnValueByID(Record[1+i], Ty);
+        Value *V;
+        // With the new function encoding, it is possible that operands have
+        // negative IDs (for forward references).  Use a signed VBR
+        // representation to keep the encoding small.
+        if (UseRelativeIDs)
+          V = getValueSigned(Record, 1+i, NextValueNo, Ty);
+        else
+          V = getValue(Record, 1+i, NextValueNo, Ty);
         BasicBlock *BB = getBasicBlock(Record[2+i]);
         if (!V || !BB) return Error("Invalid PHI record");
         PN->addIncoming(V, BB);
@@ -2542,7 +2553,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Val, *Ptr;
       if (getValueTypePair(Record, OpNum, NextValueNo, Ptr) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                     cast<PointerType>(Ptr->getType())->getElementType(), Val) ||
           OpNum+2 != Record.size())
         return Error("Invalid STORE record");
@@ -2556,7 +2567,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Val, *Ptr;
       if (getValueTypePair(Record, OpNum, NextValueNo, Ptr) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                     cast<PointerType>(Ptr->getType())->getElementType(), Val) ||
           OpNum+4 != Record.size())
         return Error("Invalid STOREATOMIC record");
@@ -2579,9 +2590,9 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Ptr, *Cmp, *New;
       if (getValueTypePair(Record, OpNum, NextValueNo, Ptr) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                     cast<PointerType>(Ptr->getType())->getElementType(), Cmp) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                     cast<PointerType>(Ptr->getType())->getElementType(), New) ||
           OpNum+3 != Record.size())
         return Error("Invalid CMPXCHG record");
@@ -2599,7 +2610,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       unsigned OpNum = 0;
       Value *Ptr, *Val;
       if (getValueTypePair(Record, OpNum, NextValueNo, Ptr) ||
-          getValue(Record, OpNum,
+          popValue(Record, OpNum, NextValueNo,
                     cast<PointerType>(Ptr->getType())->getElementType(), Val) ||
           OpNum+4 != Record.size())
         return Error("Invalid ATOMICRMW record");
@@ -2653,7 +2664,8 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
         if (FTy->getParamType(i)->isLabelTy())
           Args.push_back(getBasicBlock(Record[OpNum]));
         else
-          Args.push_back(getFnValueByID(Record[OpNum], FTy->getParamType(i)));
+          Args.push_back(getValue(Record, OpNum, NextValueNo,
+                                  FTy->getParamType(i)));
         if (Args.back() == 0) return Error("Invalid CALL record");
       }
 
@@ -2682,7 +2694,7 @@ bool BitcodeReader::ParseFunctionBody(Function *F) {
       if (Record.size() < 3)
         return Error("Invalid VAARG record");
       Type *OpTy = getTypeByID(Record[0]);
-      Value *Op = getFnValueByID(Record[1], OpTy);
+      Value *Op = getValue(Record, 1, NextValueNo, OpTy);
       Type *ResTy = getTypeByID(Record[2]);
       if (!OpTy || !Op || !ResTy)
         return Error("Invalid VAARG record");
diff --git a/lib/Bitcode/Reader/BitcodeReader.h b/lib/Bitcode/Reader/BitcodeReader.h
index e7c4e94f78..c5e97991b9 100644
--- a/lib/Bitcode/Reader/BitcodeReader.h
+++ b/lib/Bitcode/Reader/BitcodeReader.h
@@ -179,18 +179,27 @@ class BitcodeReader : public GVMaterializer {
   typedef std::pair<unsigned, GlobalVariable*> BlockAddrRefTy;
   DenseMap<Function*, std::vector<BlockAddrRefTy> > BlockAddrFwdRefs;
 
+  /// UseRelativeIDs - Indicates that we are using a new encoding for
+  /// instrunction operands where most operands in the current
+  /// FUNCTION_BLOCK are encoded relative to the instruction number,
+  /// for a more compact encoding.  Some instruction operands are not
+  /// relative to the instruction ID: basic block numbers, and types.
+  /// Once the old style function blocks have been phased out, we would
+  /// not need this flag.
+  bool UseRelativeIDs;
+
 public:
   explicit BitcodeReader(MemoryBuffer *buffer, LLVMContext &C)
     : Context(C), TheModule(0), Buffer(buffer), BufferOwned(false),
       LazyStreamer(0), NextUnreadBit(0), SeenValueSymbolTable(false),
       ErrorString(0), ValueList(C), MDValueList(C),
-      SeenFirstFunctionBody(false) {
+      SeenFirstFunctionBody(false), UseRelativeIDs(false) {
   }
   explicit BitcodeReader(DataStreamer *streamer, LLVMContext &C)
     : Context(C), TheModule(0), Buffer(0), BufferOwned(false),
       LazyStreamer(streamer), NextUnreadBit(0), SeenValueSymbolTable(false),
       ErrorString(0), ValueList(C), MDValueList(C),
-      SeenFirstFunctionBody(false) {
+      SeenFirstFunctionBody(false), UseRelativeIDs(false) {
   }
   ~BitcodeReader() {
     FreeState();
@@ -223,6 +232,9 @@ public:
   /// @brief Cheap mechanism to just extract module triple
   /// @returns true if an error occurred.
   bool ParseTriple(std::string &Triple);
+
+  static uint64_t decodeSignRotatedValue(uint64_t V);
+
 private:
   Type *getTypeByID(unsigned ID);
   Value *getFnValueByID(unsigned ID, Type *Ty) {
@@ -247,6 +259,9 @@ private:
                         unsigned InstNum, Value *&ResVal) {
     if (Slot == Record.size()) return true;
     unsigned ValNo = (unsigned)Record[Slot++];
+    // Adjust the ValNo, if it was encoded relative to the InstNum.
+    if (UseRelativeIDs)
+      ValNo = InstNum - ValNo;
     if (ValNo < InstNum) {
       // If this is not a forward reference, just return the value we already
       // have.
@@ -255,20 +270,54 @@ private:
     } else if (Slot == Record.size()) {
       return true;
     }
-    
+
     unsigned TypeNo = (unsigned)Record[Slot++];
     ResVal = getFnValueByID(ValNo, getTypeByID(TypeNo));
     return ResVal == 0;
   }
-  bool getValue(SmallVector<uint64_t, 64> &Record, unsigned &Slot,
-                Type *Ty, Value *&ResVal) {
-    if (Slot == Record.size()) return true;
-    unsigned ValNo = (unsigned)Record[Slot++];
-    ResVal = getFnValueByID(ValNo, Ty);
+
+  /// popValue - Read a value out of the specified record from slot 'Slot'.
+  /// Increment Slot past the number of slots used by the value in the record.
+  /// Return true if there is an error.
+  bool popValue(SmallVector<uint64_t, 64> &Record, unsigned &Slot,
+                unsigned InstNum, Type *Ty, Value *&ResVal) {
+    if (getValue(Record, Slot, InstNum, Ty, ResVal))
+      return true;
+    // All values currently take a single record slot.
+    ++Slot;
+    return false;
+  }
+
+  /// getValue -- Like popValue, but does not increment the Slot number.
+  bool getValue(SmallVector<uint64_t, 64> &Record, unsigned Slot,
+                unsigned InstNum, Type *Ty, Value *&ResVal) {
+    ResVal = getValue(Record, Slot, InstNum, Ty);
     return ResVal == 0;
   }
 
-  
+  /// getValue -- Version of getValue that returns ResVal directly,
+  /// or 0 if there is an error.
+  Value *getValue(SmallVector<uint64_t, 64> &Record, unsigned Slot,
+                  unsigned InstNum, Type *Ty) {
+    if (Slot == Record.size()) return 0;
+    unsigned ValNo = (unsigned)Record[Slot];
+    // Adjust the ValNo, if it was encoded relative to the InstNum.
+    if (UseRelativeIDs)
+      ValNo = InstNum - ValNo;
+    return getFnValueByID(ValNo, Ty);
+  }
+
+  /// getValueSigned -- Like getValue, but decodes signed VBRs.
+  Value *getValueSigned(SmallVector<uint64_t, 64> &Record, unsigned Slot,
+                        unsigned InstNum, Type *Ty) {
+    if (Slot == Record.size()) return 0;
+    unsigned ValNo = (unsigned)decodeSignRotatedValue(Record[Slot]);
+    // Adjust the ValNo, if it was encoded relative to the InstNum.
+    if (UseRelativeIDs)
+      ValNo = InstNum - ValNo;
+    return getFnValueByID(ValNo, Ty);
+  }
+
   bool ParseModule(bool Resume);
   bool ParseAttributeBlock();
   bool ParseTypeTable();