Message boards : News : acemdlong also updated now
| Author | Message |
|---|---|
 GDFVolunteer moderator Project administrator Project developer Project tester Volunteer developer Volunteer tester Project scientist Send message Joined: 14 Mar 07 Posts: 1957 Credit: 629,356 RAC: 0 Level  Scientific publications     | |
|
The update process is finished also for acemdlong. | |
ID: 23746 | Rating: 0 | rate:
 /   Reply
Quote
| |
|
Rantanplan 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 ? | |
| ID: 23751 | Rating: 0 | rate:
/ Reply
Quote
| |
|
GDF Volunteer moderator Project administrator Project developer Project tester Volunteer developer Volunteer tester Project scientist Send message Joined: 14 Mar 07 Posts: 1957 Credit: 629,356 RAC: 0 Level Scientific publications | |
|
No. Next application will be quicker on fermi. | |
| ID: 23752 | Rating: 0 | rate:
/ Reply
Quote
| |
|
Rantanplan Send message Joined: 22 Jul 11 Posts: 166 Credit: 138,629,987 RAC: 0 Level Scientific publications | |
|
ok , thanks for that information. | |
| ID: 23755 | Rating: 0 | rate:
/ Reply
Quote
| |
|
Damaraland 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 | |
| ID: 23759 | Rating: 0 | rate:
/ Reply
Quote
| |
|
skgiven Volunteer moderator Volunteer tester  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 Some of these and other suggestions were implemented and later withdrawn/put on hold for various reasons.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. | |
| ID: 23770 | Rating: 0 | rate:
/ Reply
Quote
| |
|
Damaraland 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. 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 | |
| ID: 23784 | Rating: 0 | rate:
/ Reply
Quote
| |
Message boards : News : acemdlong also updated now
