Re: indirect threading for bytecode interpreter

[Tom Tromey]

>>>>> "Stefan" == Stefan Monnier <address@hidden> writes:

>> I've profiled (using oprofile) Emacs running this a few times; typical
>> results show mark_object at 10-12% of runtime.  It is probably pretty
>> easy to reproduce this with a variety of elisp programs.

Stefan> So no matter how hard we try, we won't gain more than about 10% speed-up
Stefan> trying to optimize the GC.  Doesn't sound like a great motivator.

Yeah, though it does vary by workload.

re_match_2_internal is actually the top time user in my profiles, using
17-25% of the runtime.

Tom