Make abbreviations explicit in pnacl-freeze/thaw.

include/llvm/Bitcode/NaCl/NaClBitCodes.h

 //===- NaClBitCodes.h - Enum values for the bitcode format ------*- C++ -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This header Bitcode enum values.
 //
 // The enum values defined in this file should be considered permanent.  If
 // new features are added, they should have values added at the end of the
 // respective lists.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_BITCODE_NACL_NACLBITCODES_H
 #define LLVM_BITCODE_NACL_NACLBITCODES_H
 
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Support/DataTypes.h"
 #include "llvm/Support/ErrorHandling.h"

[Karl, 2013/05/17 20:52:18]

Added '#include "llvm/Support/MathExtras.h" so that we can use Log2_32_Ceil.

 #include <cassert>
 
 namespace llvm {
 namespace naclbitc {
   enum StandardWidths {
     BlockIDWidth   = 8,  // We use VBR-8 for block IDs.
     CodeLenWidth   = 4,  // Codelen are VBR-4.
     BlockSizeWidth = 32  // BlockSize up to 2^32 32-bit words = 16GB per block.
   };
 
   // The standard abbrev namespace always has a way to exit a block, enter a
   // nested block, define abbrevs, and define an unabbreviated record.
   enum FixedAbbrevIDs {
     END_BLOCK = 0,  // Must be zero to guarantee termination for broken bitcode.
     ENTER_SUBBLOCK = 1,
 
     /// DEFINE_ABBREV - Defines an abbrev for the current block.  It consists
     /// of a vbr5 for # operand infos.  Each operand info is emitted with a
     /// single bit to indicate if it is a literal encoding.  If so, the value is
     /// emitted with a vbr8.  If not, the encoding is emitted as 3 bits followed
     /// by the info value as a vbr5 if needed.
     DEFINE_ABBREV = 2,
 
     // UNABBREV_RECORDs are emitted with a vbr6 for the record code, followed by
     // a vbr6 for the # operands, followed by vbr6's for each operand.
     UNABBREV_RECORD = 3,
 
     // This is not a code, this is a marker for the first abbrev assignment.
-    FIRST_APPLICATION_ABBREV = 4
+    // In Addition, we assume up to two additional enumerated constants are

[jvoung (off chromium), 2013/05/14 23:47:14]

In addition, ...

[Karl, 2013/05/17 20:52:18]

Done.

+    // added for each extension. These constants are:
+    //
+    //   PREFIX_MAX_FIXED_ABBREV
+    //   PREFIX_MAX_ABBREV
+    //
+    // PREFIX_MAX_ABBREV defines the maximal enumeration value used for
+    // the code selector of a block. If Both PREFIX_MAX_FIXED_ABBREV
+    // and PREFIX_MAX_ABBREV is defined, then PREFIX_MAX_FIXED_ABBREV
+    // defines the last code selector of the block that must be read using
+    // a single read (i.e. a FIXED read, or the first chunk of a VBR read.
+    FIRST_APPLICATION_ABBREV = 4,
+    // Defines default values for code length, if no additional selectors
+    // are added.
+    DEFAULT_MAX_ABBREV = FIRST_APPLICATION_ABBREV-1
   };
 
   /// StandardBlockIDs - All bitcode files can optionally include a BLOCKINFO
   /// block, which contains metadata about other blocks in the file.
   enum StandardBlockIDs {
     /// BLOCKINFO_BLOCK is used to define metadata about blocks, for example,
     /// standard abbrevs that should be available to all blocks of a specified
     /// ID.
     BLOCKINFO_BLOCK_ID = 0,
 
@@ skipping 114 matching lines @@
     return static_cast<unsigned>(OperandList.size());
   }
   const NaClBitCodeAbbrevOp &getOperandInfo(unsigned N) const {
     return OperandList[N];
   }
 
   void Add(const NaClBitCodeAbbrevOp &OpInfo) {
     OperandList.push_back(OpInfo);
   }
 };
+
+// NaClBitcodeSelectorAbbrev - This class determines whether a FIXED or VBR
+// abbreviation should be used for the selector, and the number of bits
+// needed to capture such selectors.
+class NaClBitcodeSelectorAbbrev {
+  // Number of bits needed for selector.
+  unsigned NumBits;

[Karl, 2013/05/17 20:52:18]

Made publicly visible so that it can be set by the reader.

+  // If true, use a FIXED abbreviation. Otherwise, use a VBR abbreviation.
+  bool UseFixedAbbrev;

[Karl, 2013/05/17 20:52:18]

Renamed to IsFixed, and made publicly visible (so that it can be set by the
reader).

+
+public:
+
+  // Computes the minimum number of bits needed to encode value.
+  static unsigned BitsNeededForValue(unsigned Value) {

[Karl, 2013/05/17 20:52:18]

Moved this out (above) to be an inline. Also added inline routines
   NaClEncodeSignRotatedValue
   NaClDecodeSignRotatedValue
so that they can be (consistently) used.

+    unsigned NumBits = 1;

[Karl, 2013/05/17 20:52:18]

Replaced body with call to Log2_32_Ceil.

+    while (Value >= 2) {
+      ++NumBits;
+      Value >>= 1;
+    }
+    return NumBits;
+  }
+
+  // Creates a selector range when no abbreviations are defined.
+  NaClBitcodeSelectorAbbrev()
+      : NumBits(BitsNeededForValue(naclbitc::DEFAULT_MAX_ABBREV)),
+        UseFixedAbbrev(true) {}
+
+  // Creates a selector range to handle fixed abbrevations up to
+  // the specified value.
+  NaClBitcodeSelectorAbbrev(unsigned MaxAbbrev)
+      : NumBits(BitsNeededForValue(MaxAbbrev)), UseFixedAbbrev(true) {}
+
+  // Creates a selector range where the first chunk can handle all
+  // values < FirstChunkCutoff, and all range values are less than
+  // AllCutoff.

[jvoung (off chromium), 2013/05/14 23:47:14]

what is AllCutoff?

[Karl, 2013/05/17 20:52:18]

Fixed reference to use "MaxAbbrev".

+  NaClBitcodeSelectorAbbrev(unsigned FirstChunkCutoff, unsigned MaxAbbrev)
+      : NumBits(BitsNeededForValue(FirstChunkCutoff)),
+        UseFixedAbbrev(FirstChunkCutoff == MaxAbbrev) {
+    // Before returning, patch up values, based on behaviour of
+    // bitstream writer. Note that VBR requires an extra bit to
+    // define if further bit chunks are needed. Hence, add this
+    // information.
+    if (!UseFixedAbbrev) {
+      if ((1U << (NumBits+1)) < MaxAbbrev) {
+        // Fixed size on corresponding VBR will hold all values, so
+        // don't bother to use VBR.
+        UseFixedAbbrev = true;
+      } else {
+        // Add bit to handle multiple chunks.
+        ++NumBits;
+      }
+    }
+  }
+
+  // Returns true if FIXED should be used (instead of VBR).
+  bool UseFixed() const {

[Karl, 2013/05/17 20:52:18]

Removed UseFixed and UseNumBits, since the fields are now public and can be
changed.

+    return UseFixedAbbrev;
+  }
+
+  // Returns the number of bits to use.
+  int UseNumBits() const {
+    return NumBits;
+  }
+};
 } // End llvm namespace
 
 #endif