Re: Folding@Home Package
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Magnus Holmgren wrote:
> Sebastiaan Couwenberg wrote:
> Has there been any talk about moving to the BOINC infrastructure?
There used to be work on a BOINC F@H client, but this work has stopped
due to personnel turnover.
See:
http://fahwiki.net/index.php/Alternative_FAH_Platforms#BOINC
http://folding.stanford.edu/FAQ-highperformance.html
> But the only way to be sure that the individual users don't cheat would
> be to require Treacherous Computing. Instead, BOINC-powered projects
> rely on handing out several copies of each work unit and checking that
> the reported results match. Perhaps F@H does this as well.
F@H doesn't duplicate work, each WU is only assigned once by default. If
a WU has not been returned when the Preferred Deadline is reached, then
the WU is assigned to another client.
Some newer WUs are duplicate work in a sense, they verify the results of
the new SMP client & core on single CPU/core machines.
Each assigned WU is verified at upload, the information used in this
verification is stored in the queue.dat (which you can dump with qd).
See:
http://linuxminded.xs4all.nl/software/qd-tools/documentation/queue.dat-layout/queue-assignment-info-present.html
Regards,
Bas
- --
GnuPG: 0x77A975AD
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.6 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
iD8DBQFGfQybRWRRA3epda0RAnrJAJ9SehxyhwAlOK6uyCsWbuzqmFqPeACfXLjZ
wP/yVr89HEKcthIt6nXNiBU=
=m7cV
-----END PGP SIGNATURE-----
Reply to: