From 6565a0d4b2c98722eb8fee9093cdde4f37928986 Mon Sep 17 00:00:00 2001
From: "Duncan P. N. Exon Smith" <dexonsmith@apple.com>
Date: Sun, 27 Mar 2016 23:17:54 +0000
Subject: Reapply ~"Bitcode: Collect all MDString records into a single blob"

Spiritually reapply commit r264409 (reverted in r264410), albeit with a
bit of a redesign.

Firstly, avoid splitting the big blob into multiple chunks of strings.

r264409 imposed an arbitrary limit to avoid a massive allocation on the
shared 'Record' SmallVector.  The bug with that commit only reproduced
when there were more than "chunk-size" strings.  A test for this would
have been useless long-term, since we're liable to adjust the chunk-size
in the future.

Thus, eliminate the motivation for chunk-ing by storing the string sizes
in the blob.  Here's the layout:

    vbr6: # of strings
    vbr6: offset-to-blob
    blob:
       [vbr6]: string lengths
       [char]: concatenated strings

Secondly, make the output of llvm-bcanalyzer readable.

I noticed when debugging r264409 that llvm-bcanalyzer was outputting a
massive blob all in one line.  Past a small number, the strings were
impossible to split in my head, and the lines were way too long.  This
version adds support in llvm-bcanalyzer for pretty-printing.

    <STRINGS abbrevid=4 op0=3 op1=9/> num-strings = 3 {
      'abc'
      'def'
      'ghi'
    }

From the original commit:

Inspired by Mehdi's similar patch, http://reviews.llvm.org/D18342, this
should (a) slightly reduce bitcode size, since there is less record
overhead, and (b) greatly improve reading speed, since blobs are super
cheap to deserialize.

llvm-svn: 264551
---
 llvm/lib/Bitcode/Writer/ValueEnumerator.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'llvm/lib/Bitcode/Writer/ValueEnumerator.h')

diff --git a/llvm/lib/Bitcode/Writer/ValueEnumerator.h b/llvm/lib/Bitcode/Writer/ValueEnumerator.h
index 7665210d014..fd09a695a99 100644
--- a/llvm/lib/Bitcode/Writer/ValueEnumerator.h
+++ b/llvm/lib/Bitcode/Writer/ValueEnumerator.h
@@ -66,7 +66,7 @@ private:
   SmallVector<const LocalAsMetadata *, 8> FunctionLocalMDs;
   typedef DenseMap<const Metadata *, unsigned> MetadataMapType;
   MetadataMapType MetadataMap;
-  bool HasMDString;
+  unsigned NumMDStrings = 0;
   bool ShouldPreserveUseListOrder;
 
   typedef DenseMap<AttributeSet, unsigned> AttributeGroupMapType;
@@ -121,8 +121,6 @@ public:
   }
   unsigned numMDs() const { return MDs.size(); }
 
-  bool hasMDString() const { return HasMDString; }
-
   bool shouldPreserveUseListOrder() const { return ShouldPreserveUseListOrder; }
 
   unsigned getTypeID(Type *T) const {
@@ -157,9 +155,16 @@ public:
 
   const ValueList &getValues() const { return Values; }
   const std::vector<const Metadata *> &getMDs() const { return MDs; }
+  ArrayRef<const Metadata *> getMDStrings() const {
+    return makeArrayRef(MDs).slice(0, NumMDStrings);
+  }
+  ArrayRef<const Metadata *> getNonMDStrings() const {
+    return makeArrayRef(MDs).slice(NumMDStrings);
+  }
   const SmallVectorImpl<const LocalAsMetadata *> &getFunctionLocalMDs() const {
     return FunctionLocalMDs;
   }
+
   const TypeList &getTypes() const { return Types; }
   const std::vector<const BasicBlock*> &getBasicBlocks() const {
     return BasicBlocks;
@@ -189,6 +194,10 @@ public:
 private:
   void OptimizeConstants(unsigned CstStart, unsigned CstEnd);
 
+  // Reorder the reachable metadata.  This is not just an optimization, but is
+  // mandatory for emitting MDString correctly.
+  void organizeMetadata();
+
   void EnumerateMDNodeOperands(const MDNode *N);
   void EnumerateMetadata(const Metadata *MD);
   void EnumerateFunctionLocalMetadata(const LocalAsMetadata *Local);
-- 
cgit v1.2.3