Commit Graph

6 Commits

Author SHA1 Message Date
Julian Seward
87e9f78e0c - Track vex r1494 (x86/amd64 change of conventions for getting
to translations and back to dispatcher, and also different arg
  passing conventions to LibVEX_Translate).

- Rewrite x86 dispatcher to not increment the profiling counters
  unless requested by the user.  This dramatically reduces the
  D1 miss rate and gives considerable performance improvement
  on x86.  Also, restructure and add comments to dispatch-x86-linux.S
  to make it much easier to follow (imo).

amd64/ppc32/ppc64 fixes to follow.



git-svn-id: svn://svn.valgrind.org/valgrind/trunk@5345
2005-12-15 14:07:07 +00:00
Nicholas Nethercote
8a17ca2276 add comment from log message.
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@5281
2005-12-04 19:33:03 +00:00
Julian Seward
f6c90df51e Avoid potential partial-flags stall on P4.
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@5275
2005-12-03 14:27:41 +00:00
Julian Seward
18afc93af3 wibble
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@5118
2005-11-13 18:50:39 +00:00
Julian Seward
10ee793424 Tidy up the machinery for detecting the CPU type and capabilities.
Move it from m_translate to m_machine, which is a more appropriate
place for it.


git-svn-id: svn://svn.valgrind.org/valgrind/trunk@5104
2005-11-12 23:10:48 +00:00
Nicholas Nethercote
4ef4aabbd0 Make the dispatch files platform-specific, not just arch-specific,
as requested by Greg Parker.  (The ppc32/Darwin dispatch loop is
different to the ppc32/Linux one, for example.)



git-svn-id: svn://svn.valgrind.org/valgrind/trunk@4843
2005-10-02 14:48:09 +00:00