Posts by Magister

1) Message boards : Number crunching : Lastest Stock Apps - Optimized or Not (Message 50754) Posted 19 Aug 2011 by Magister Post: So.. now that it works... we got a few new apps supporting Intel SSE4.1, Intel SSE3 and Intel/AMD SSE2 (PENTIUM4_SSE2 and AMD SSE2) Using the SSE4.1 app v0.91 (I have a Xeon supporting up to SEE4.2), my units fail within a second with: <core_client_version>6.10.58</core_client_version> <![CDATA[ <message> - exit code -1073741515 (0xc0000135) </message> ]]> All the same exit code. EDIT: it works with the SSE3 application.
2) Message boards : Number crunching : Is MW going to be a GPU project now? (Message 48342) Posted 29 Apr 2011 by Magister Post: yup, thanks Crunch3r! and if you need a beta tester for your optimized CPU app... ;-)
3) Message boards : Number crunching : Is MW going to be a GPU project now? (Message 48322) Posted 28 Apr 2011 by Magister Post: I don't do it for credit, I run Seti for 11 years now and since boinc exists I run seti/einstein/lhc/milkyway only. It's just dissapointing that milkyway credits went down like this, but I still run it.
4) Message boards : Number crunching : Is MW going to be a GPU project now? (Message 48273) Posted 27 Apr 2011 by Magister Post: On a Quad XEON I had a RAC of about 4800 to 5000 credit/day with the old 0.21SSE3 optimized app. Now with the standard 0.50SSE2 it went down to about 800 credit/day. A unit takes more than 12 hours to complete now, before it was something like 4h30 IIRC.
5) Message boards : News : and a little payback (Message 48069) Posted 20 Apr 2011 by Magister Post: I agree, with the old 0.21SSE3 optimized app it took about 3 hours per unit, now with the default 0.50SSE2 it takes up to 12 hours... credits/day got cut by 75% too :)
6) Message boards : News : updated the CPU applications (Message 42678) Posted 8 Oct 2010 by Magister Post: hackgrav: tree-incest detected I got an error with this message in the log, see the unit log here http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=213678672 I'm using milkyway_nbody_0.07_windows_intelx86__sse2.exe What's this tree-incest?
7) Message boards : Number crunching : Computation Error on NBody Model (Message 42346) Posted 24 Sep 2010 by Magister Post: got a second one... http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=150666061 I will stop using Nbody for the moment.
8) Message boards : Number crunching : Computation Error on NBody Model (Message 42328) Posted 23 Sep 2010 by Magister Post: Just got one also http://milkyway.cs.rpi.edu/milkyway/workunit.php?wuid=150393135 and I'm not the only one on this one :-(