The new bytecode format supports emitting strings a special case. This is

intended to save size (and does on small programs), but on big programs it
actually increases the size of the program slightly.  The deal is that many
functions end up using the characters that the string contained, and the
characters are no longer in the global constant table, so they have to be
emitted in function specific constant pools.

This pessimization will be fixed in subsequent patches.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@10864 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 15 insertions, 5 deletions

diff --git a/lib/Bytecode/Writer/Writer.cpp b/lib/Bytecode/Writer/Writer.cpp
index ca50b5a7bd..2020a3a2bd 100644
--- a/lib/Bytecode/Writer/Writer.cpp
+++ b/lib/Bytecode/Writer/Writer.cpp
@@ -24,9 +24,10 @@
 
 #include "WriterInternals.h"
 #include "llvm/Bytecode/WriteBytecodePass.h"
+#include "llvm/Constants.h"
+#include "llvm/DerivedTypes.h"
 #include "llvm/Module.h"
 #include "llvm/SymbolTable.h"
-#include "llvm/DerivedTypes.h"
 #include "Support/STLExtras.h"
 #include "Support/Statistic.h"
 #include "Support/Debug.h"
@@ -54,7 +55,9 @@ ModuleInfoBytes("bytecodewriter", "Bytes of module info");
 BytecodeWriter::BytecodeWriter(std::deque<unsigned char> &o, const Module *M) 
   : Out(o), Table(M, true) {
 
-  outputSignature();
+  // Emit the signature...
+  static const unsigned char *Sig =  (const unsigned char*)"llvm";
+  output_data(Sig, Sig+4, Out);
 
   // Emit the top level CLASS block.
   BytecodeBlock ModuleBlock(BytecodeFormat::Module, Out);
@@ -111,9 +114,12 @@ void BytecodeWriter::outputConstantsInPlane(const std::vector<const Value*>
                                             &Plane, unsigned StartNo) {
   unsigned ValNo = StartNo;
   
-  // Scan through and ignore function arguments/global values...
-  for (; ValNo < Plane.size() && (isa<Argument>(Plane[ValNo]) ||
-                                  isa<GlobalValue>(Plane[ValNo])); ValNo++)
+  // Scan through and ignore function arguments, global values, and constant
+  // strings.
+  for (; ValNo < Plane.size() &&
+         (isa<Argument>(Plane[ValNo]) || isa<GlobalValue>(Plane[ValNo]) ||
+          (isa<ConstantArray>(Plane[ValNo]) &&
+           cast<ConstantArray>(Plane[ValNo])->isString())); ValNo++)
     /*empty*/;
 
   unsigned NC = ValNo;              // Number of constants
@@ -171,6 +177,10 @@ void BytecodeWriter::outputConstants(bool isFunction) {
     }
   }
   
+  // Output module-level string constants before any other constants.x
+  if (!isFunction)
+    outputConstantStrings();
+
   for (unsigned pno = 0; pno != NumPlanes; pno++)
     if (pno != Type::TypeTyID) {         // Type plane handled above.
       const std::vector<const Value*> &Plane = Table.getPlane(pno);