Message boards :
News :
acemdlong also updated now
Message board moderation
Author | Message |
---|---|
![]() Send message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
The update process is finished also for acemdlong. gdf |
Send message Joined: 22 Jul 11 Posts: 166 Credit: 138,629,987 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Will they run now quicker on fermi gpus ? |
![]() Send message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
No. Next application will be quicker on fermi. This is a minor update. Next application should be around soon also. It has been ready for a long time, but it is slower on G200 cards. gdf |
Send message Joined: 22 Jul 11 Posts: 166 Credit: 138,629,987 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
ok , thanks for that information. i thought it is allready done. greetings from germany |
![]() Send message Joined: 7 Nov 09 Posts: 152 Credit: 16,181,924 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Next application should be around soon also. It has been ready for a long time, but it is slower on G200 cards. Maybe too obvious... Why don't you free the ACEM Beta task for another site (like SETI@home beta and seen in other projects)? This way you could have 3 apps: long, Fermis and shorts for the slowests cards. This way Fermi's go faster and you don't loose funcionality. HOW TO - Full installation Ubuntu 11.10 |
![]() Send message Joined: 23 Apr 09 Posts: 3968 Credit: 1,995,359,260 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Good idea, and might be doable, but I imagine managing several sites (or just more apps) would require more development and maintenance time and therefore less time for science. It would also require more physical resources and several sites with less tasks would individually have more outages. Similar things have been suggested before; more apps, different apps for different GPU's, an alpha site for testing. Some of these and other suggestions were implemented and later withdrawn/put on hold for various reasons. Several alpha phases were run a while back for pre-release apps. A long term obstacle to more apps would be troubleshooting; well, lack of it. We will soon be in a position of having 3 full generations of GPU's; GF200, GF400/500 and GF600. FAQ's HOW TO: - Opt out of Beta Tests - Ask for Help |
![]() Send message Joined: 7 Nov 09 Posts: 152 Credit: 16,181,924 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
As I said too obvious... Real pitty! I was thinking a smart task sender that could choose what app is most suitable for each computer depending on it's graphics cards intalled... like an app optimizer. Of course resources= money. It would also require more physical resources and several sites with less tasks would individually have more outages. The pitty is I'm sure that if you estimate the saving in electricity versus and the improvement in efficiency it will be paid by the spending resources. 1% of improvement from 4.000 computers are 40 computers. 1% of a year is 87 hours Hey guys put a $5/ 5€ paypal transfer each. 4000 x 5 = 20.000. With that you get a programmer that can do this! HOW TO - Full installation Ubuntu 11.10 |
©2025 Universitat Pompeu Fabra