Message boards :
Number crunching :
6.10.1 Posted.
Message board moderation
Previous · 1 · 2 · 3 · 4
Author | Message |
---|---|
Send message Joined: 26 Jan 09 Posts: 589 Credit: 497,834,261 RAC: 0 |
|
Send message Joined: 6 Apr 08 Posts: 2018 Credit: 100,142,856 RAC: 0 |
One setup that doesn't work, Ice, is the blue writing on blue background of your boincstats sig. Some colour combination with greater contrast would make it more legible to these old eyes. :) Oh, I think it's just right, I can read my sig just fine. I'm not sure why anyone else would want to read my sig or thego degoligoghts thagot cagon bego fogound ogon my sigognagoturego agonywagoy, bugot I'm sugorego igot's vegory igontegoregostigong fogor yogou. Negoegodlegoss togo sagoy, I like it just as it is ;) |
Send message Joined: 21 Mar 09 Posts: 15 Credit: 1,545,913 RAC: 0 |
Tried 6.10.3, the GPU scheduling was much better but the CPU scheduler refused to download anything with a short timescale ("won't finish in time" message). Ended up with all four CPU cores idle unless I downloaded Climate Prediction. At one point it was running 8 tasks (I have a quad with 2 GPU), it was running 4 at normal CPU, 2 GPU and 2 CPU High Priority. That just has to be wrong! Gave up and reverted to 6.6.31 Rob. |
Send message Joined: 28 Aug 09 Posts: 23 Credit: 1,265,994,520 RAC: 124,563 |
maybe a little off topic... but, what is the meaning of the two lines ignoring unknown input argument in app_info.xml: --device ignoring unknown input argument in app_info.xml: 0 that started appearing in stderr after upgrading to 6.10.3? |
Send message Joined: 26 Jul 08 Posts: 627 Credit: 94,940,203 RAC: 0 |
maybe a little off topic... but, what is the meaning of the two lines The BOINC clients tell GPU applications which GPU they should use by a command line argument (i.e. "--device 0" for the first GPU in the system, "--device 1" for the second one and so on). The same system is now applied for CUDA and CAL (ATI) cards. For the time being the ATI app ignores those statements. As the app has its own internal scheduling routine (which assigns the device) it doesn't matter in the moment. But when the ATI support of the client has matured, the internal scheduling routine will likely be removed and the app will simply use the assigned GPU. |
©2024 Astroinformatics Group