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

1 files changed, 58 insertions, 9 deletions

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();