From: Archie Cobbs (archie@whistle.com)
Date: Thu Dec 03 1998 - 01:45:33 EST
Alexandre Oliva writes:
> On Dec 2, 1998, Archie Cobbs <archie@whistle.com> wrote:
> > Interesting paper "Mostly parallel garbage collection":
>
> > The idea is to use page faults to detect changed pointers,
> > so you can run the GC (mostly) in parallel.
>
> Do they present any performance figures about this mechanism? I think
> page faults are too expensive a way to detect changed pointers, unless
> you have page faults very rarely.
They do present performance figures, but I haven't gotten that far yet :-)
The claim is that performance is no worse than normal "stop-the-world"
GC..
-Archie
___________________________________________________________________________
Archie Cobbs * Whistle Communications, Inc. * http://www.whistle.com
This archive was generated by hypermail 2b29 : Sat Sep 23 2000 - 19:57:04 EDT