41) Message boards : LHC@home Science : LHC@Home Alpha Test (Message 11501)
Posted 28 Nov 2005 by Profile Chrulle
Post:
No, we will not open the account creation on the alpha site.

42) Message boards : Number crunching : What is happening with Geant4? (Message 11474)
Posted 25 Nov 2005 by Profile Chrulle
Post:
Well, the problem is that when the physicist do a simulation, they compile the model together with the environment which then gives a 1 gb executable. This binary can then be used for a few runs but nothing that would warrant such a large download.

So, Mike is right we have to split the jobs up in a way that the calculation that just need a bit of data is done on BOINC and the bits that really need the entire 1 gb environment are done at CERN.

Or we have to teach the physicist to write modular code and used shared libraries.
The only problem is that that will probably take longer. ;-)

BTW. A few more runs coming along soon.
43) Message boards : Cafe LHC : VIRUS with BOINC related Header !!!! (Message 11451)
Posted 23 Nov 2005 by Profile Chrulle
Post:
I have just heard that a variant of the W32.beagle virus is spreading as an email attachment at the moment. It will send itsefl with random sender email and subject but with an attachment called 1.exe. Do not run this file.
44) Message boards : Number crunching : What is happening with Geant4? (Message 11450)
Posted 23 Nov 2005 by Profile Chrulle
Post:
Well the software has been ported. The next step is taking one of the models probably the modelling of the Atlas detector and then decoupling the Geant 4 bit from the rest of the Atlas simulation. Figuring out a way to do bits of the simulation on boinc and then finishing it up at cern where the environment is complete. The problem with many of these physics application is that they need on the order of 1 GB of data for a simulation.
45) Message boards : Number crunching : new work eta? (Message 11433)
Posted 22 Nov 2005 by Profile Chrulle
Post:
Another small study (150000 jobs) was run last week, but people grab the stuff so fast that it never really showed. The last few results of that run returned yesterday late afternoon. I have been asking the physicist what is planned for the future, but no news yet.
46) Message boards : Number crunching : Newbie Needs Help (Message 11404)
Posted 18 Nov 2005 by Profile Chrulle
Post:
Well for the moment it could also be because there is no work on the server.
47) Message boards : Number crunching : WOW Linux Box just got Work (Message 11291)
Posted 9 Nov 2005 by Profile Chrulle
Post:
I do not really understand this thread. I thought workunits for linux and windows were the same, only different clients of course. Do you say that linux computers don't get as much work units as windows computers? I planned to install the client on my linux-based workstations as well, so I'm a little confused now and wonder if there's any sense in doing so.


No i am saying that of the work we gave out, 7 % was done by linux machines. A linux machine can get just as much work as a windows machine. There are just a lot fewer.

48) Message boards : Number crunching : WOW Linux Box just got Work (Message 11277)
Posted 8 Nov 2005 by Profile Chrulle
Post:
Well, we had linux machines in our beta test, and they delivered about 7% of the overall chrunching power, back in september 2004.
49) Message boards : Number crunching : LHC uses very little L2 cache (Message 11257)
Posted 7 Nov 2005 by Profile Chrulle
Post:
Well, i wrote some automatic benchmarking tools for chpstl (http://www.cphstl.dk/). It uses PAPI (http://icl.cs.utk.edu/papi/) which will allow you to access the performance counting registers on the CPU. With this in your program you can see how big a percentage of your memory accesses that causes a miss in the caches or how many pagefaults your program creates. Very useful stuff.
50) Message boards : Number crunching : BBCode (Message 11100)
Posted 28 Oct 2005 by Profile Chrulle
Post:
We only converted the posts. We do not want to touch users profiles/signatures.
51) Message boards : Number crunching : Host corruption solved? (Message 11032)
Posted 26 Oct 2005 by Profile Chrulle
Post:
Well, since the new processes where installed after 1100 UTC it could still work.
52) Message boards : Number crunching : Host corruption solved? (Message 11025)
Posted 26 Oct 2005 by Profile Chrulle
Post:
I have installed a new validator and a new assimilator. Let us see if this solves the problem.
53) Message boards : Number crunching : show_host_detail.php malformed since v5 upgrade (Message 10982)
Posted 25 Oct 2005 by Profile Chrulle
Post:
credit is still being granted and the reported results seem to be valid, so we'll see what happens.


Yeah, i gathered that the physics and the credit was doing fine, so i put the server back online. This way useful work will be done while we figure out what is going on.
54) Message boards : Number crunching : Host corruption (Message 10980)
Posted 25 Oct 2005 by Profile Chrulle
Post:
Ok, so it seems the problem can be found in the credit granting. So it is probably the validator that is doing something horrible.

I will take a look at it tomorrow at work.

I am sorry that you did not report it Keith... It was you that had asked me to be added as alpha tester right? I tried to add you, but in v. 5 they have removed the admins abillity to add users. I could have done it manually in the database, but i did not have the time.
55) Message boards : Number crunching : Host corruption (Message 10877)
Posted 25 Oct 2005 by Profile Chrulle
Post:
If your host is getting corrupted write here what version of the boinc client you are using, and when you connected last. Are all your hosts getting corrupted?

56) Message boards : Number crunching : Attention LHC Developers! (Message 10821)
Posted 21 Oct 2005 by Profile Chrulle
Post:
version 5 should be up and running on the alpha site, so if we have any v.5 client users here who used to do alpha reattach and tell me how it works.
57) Message boards : Number crunching : Attention LHC Developers! (Message 10800)
Posted 20 Oct 2005 by Profile Chrulle
Post:
Well, i am back in switzerland. Strangely the weather was much better in Denmark.

All that the "talk" patch does is allow version 5 clients to not fail when connecting, but they will still not get any jobs, so it is pretty useless.

I am in the process of installing the new server version on the alpha test server.
It is always a lot trickier than one would think, for now i have discovered that i am obviously not supposed to use the stable branch of cvs because that is only stable for the client and not for the server. Then i found out that i needed newer versions of automake and -conf.

Now i am ready to upgrade the database which i hope will not crash everything but we shall see. :-)

If everything works out we will install v.5 on the normal server soon.
58) Message boards : Cafe LHC : BOINC and Public Universities (Message 10780)
Posted 18 Oct 2005 by Profile Chrulle
Post:
A friend of mine used to work as sysadmin at the institute of medicine at the university of Copenhagen. He installed seti@home classic on all the machines there.(it was before the days of BOINC) So it is possible that they will allow it.

59) Message boards : Number crunching : Workunits Coming Soon? (Message 10746)
Posted 15 Oct 2005 by Profile Chrulle
Post:
Yeah sorry about that but i am on vacation in Denmark, so i have not had time to follow up on the status of work.
60) Questions and Answers : Sixtrack : Sixtrack causing graphics problems (Message 10691)
Posted 11 Oct 2005 by Profile Chrulle
Post:
what version of the client are you using?


Previous 20 · Next 20


©2024 CERN