Correction to last message, GC status

Tue Jun 26 09:32:00 GMT 2001

I suspect that we'll also see a measurable performance increase from linking
statically linking the GC library against libgcj. Allocation calls from
inside libgcj (e.g. for strings) will no longer cross a dynamic library
boundary. So long as gcc doesn't generate direct GC_ calls, we'll reduce
the number of boundary crossings for allocation from 2 to 1.
Hans
> -----Original Message-----
> From: Tom Tromey [ mailto:tromey@redhat.com ]
> Sent: Monday, June 25, 2001 8:10 PM
> To: Jeff Sturm
> Cc: Boehm, Hans; java@gcc.gnu.org
> Subject: Re: Correction to last message, GC status
>>> >>>>> "Jeff" == Jeff Sturm <jsturm@one-point.com> writes:
>> Jeff> What is the advantage of building libgcjgc as a shared lib? Or
> Jeff> libzgcj for that matter? We don't have pluggable GC, and
> Jeff> libzgcj isn't any different from libz.so (or is it?).
>> There probably isn't a benefit.
>...