ATLAS joining Einstein@home - RFC
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4332
Credit: 251794631
RAC: 36260
2 Sep 2008 16:26:36 UTC
Topic 193893
(moderation:
Hi!
In the near future we intend to add the (spare) computing power of ATLAS (5368 Core2 cores) to Einstein@home. This will probably generate a lot of "credits" which we have no real use for.
We are aware that, if the account joins a team, this will have effects on the team statistics that will not necessarily be desirable. To avoid this, we are thinking of two different alternatives:
1. ATLAS doesn't join a team at all.
2. Once every few days (~ a week to start with) ATLAS will join a random team present (and possibly active) on Einstein@home. This will result in some kind of lottery of additional credit for the teams at this project, as both the team and the amount of credit is really rather random.
AFAIK there is no "poll" option in the current BOINC web code, so I'd just ask for people having strong feelings about one or the other alternative to express them in this thread.
BM
BM
ATLAS joining Einstein@home - RFC
)
I'd say the best approach would be either Atlas does not join any team OR Atlas forms its own team. The random team approach does not strike me as a good solution.
My two cents.
RE: I'd say the best
)
I concur.
Michael
Team Linux Users Everywhere
RE: RE: I'd say the best
)
And a me too from here!
[edit]
Bernd,
Although your offer is appreciated, in all fairness to the teams AND to users who have chosen NOT to join a team, it would be best to keep Atlas as its own entity.
[/edit]
Seti Classic Final Total: 11446 WU.
RE: RE: RE: I'd say
)
+1
Reno, NV Team: SETI.USA
RE: RE: RE: RE: I'd
)
I think that option 2 is a pretty good thing. Prof Bruce Allen did it two times with his crunchin farm. First he entered Boinc Australia and after a time he went to Ireland.
Just a curiosity. ATLAS has a
)
Just a curiosity. ATLAS has a number of cores roughly equal to the number of units to be crunched in S5R4. Does this mean that the work shall be finished in about one week or Einstein@home will be given only a fraction of the available CPU power? As for the main question, I think ATLAS should start its own team.
Tullio
Sorry, I mistook a dot for a comma (in Europe the dot is a separator). I should have said the units are one thousand times the number of cores.The second answer remains.
The random team thing has a
)
The random team thing has a certain silly appeal, but I would say that the potential for problems exists so I concur that simply leaving it teamless would probably be the best approach.
I'm thinking that if Atlas crunched for my team for even a few days that would probably instantly create the highest rank we'd ever have the possibility of getting. That sorta spoils the fun of trying to climb on our own. ;)
So bring it on and let's see R5 burned through a little faster! :-D
RE: AFAIK there is no
)
I think ATLAS should work for the team of its maintainer ( or without team if it's not possible ).
RE: RE: AFAIK there is no
)
That would be either "Einstein at work" or "Albert-Einstein-Institut Hannover (AEI)"
BM
BM
I wouldn't object to it being
)
I wouldn't object to it being part of the AEI team. It's their baby, so why not?
(Of course, my team has little hope of ever reaching their performance with or without ATLAS, so that colors my view) ;)