| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Beta Testing
Forum: Beta Test Support Forum
Thread: Beta for HCC ver 6.42 Windows Only |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 86
|
|
| Author |
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Test total so far was 3,821 results returned with an average (weighted) run time of 1.5645 hours... 1 hour 34 minutes.
--//-- |
||
|
|
TimAndHedy
Senior Cruncher Joined: Jan 27, 2009 Post Count: 267 Status: Offline Project Badges: 
|
Anyone know what the change actually is? New Compiler, Library, Tightened Code, different Alg?
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
A chef cook never tells on the exact recipe and order of preparation, but guessing per the 50% rule of weekend billionaires, I'd dismiss 3 and 4 ;>)
----------------------------------------[Edit 1 times, last edit by Former Member at Mar 19, 2011 4:54:59 PM] |
||
|
|
TimAndHedy
Senior Cruncher Joined: Jan 27, 2009 Post Count: 267 Status: Offline Project Badges:
|
A chef cook never tells on the exact recipe and order of preparation They do if they are smart. There is more money in Cook Books than one little restaurant will make. Perhaps that is the case here also. but guessing per the 50% rule of weekend billionaires, I'd dismiss 3 and 4 ;>) Your probably right, at least 9 out of 10 times, the quick and easy route is very seductive. However they have shown interest in improvement in the past. |
||
|
|
RT
Master Cruncher USA - Texas - DFW Joined: Dec 22, 2004 Post Count: 2636 Status: Offline Project Badges: 
|
I would like to know just how they are going about improving the performance for one simple reason. That is, if they are using a different compiler/assembler, then it bodes well for this same sort of advancement in other projects for windows. If it is something else, then perhaps not-so-much. You see, some of my machines are used by folks for their everyday business. Some are dedicated crunchers. All the dual purpose machines are on one of the Windows while the dedicated machines are on Ubuntu.
----------------------------------------Frankly, I do not like having to mess with both Operating Systems and only do it because the Ubuntu machines produce more throughput. Now since I mostly run HCC, then the success of this project will let me, go back to one opsys. I would love to think that new projects and the existing ones will all be improved by this new whatever it is. Make sense? EDIT> spelling  ---------------------------------------- [Edit 1 times, last edit by RT at Mar 21, 2011 2:21:28 PM] |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Soon as HCC 6.4x 64 bit goes in production I'll be running a half dozen each on W7-64 to compare to Ubuntu 10.10. No matter how fast though it will be, I've not remotely been able to get 99.95% efficiency I'm seeing on Ubuntu, with the exception of CEP2, so even when on par, end of the day think Ubuntu (x11/gdm GUI stopped) will continue to do more ''real'' work in a day. That said, some did report that Windows had the lower run time in Windows pre-6.40 for C4CW. Don't know if that's the case with the 64 bit version. The dual boot test is still outstanding for this science. That all said, the quad is a dedicated cruncher, barely used for anything that would require to boot into W7 or VM session.
--//-- |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges: 
|
I would like to know just how they are going about improving the performance for one simple reason. That is, if they are using a different compiler/assembler, then it bodes well for this same sort of advancement in other projects for windows. If it is something else, then perhaps not-so-much. You see, some of my machines are used by folks for their everyday business. Some are dedicated crunchers. All the dual purpose machines are on one of the Windows while the dedicated machines are on Ubuntu. Frankly, I do not like having to mess with both Operating Systems and only do it because the Ubuntu machines produce more throughput. Now since I mostly run HCC, then the success of this project will let me, go back to one opsys. I would love to think that new projects and the existing ones will all be improved by this new whatever it is. Make sense? EDIT> spelling RT, We were able to investigate using a different compiler on this application. Now, the main question is do the results still produce a valid answer that the researchers expect. If not then we will need to look into what compile options were used and as you can tell this all takes time. BTW, the results are on their way to the researchers from the BETA to compare with the other results. Thanks, -Uplinger |
||
|
|
RT
Master Cruncher USA - Texas - DFW Joined: Dec 22, 2004 Post Count: 2636 Status: Offline Project Badges:
|
I would like to know just how they are going about improving the performance for one simple reason. That is, if they are using a different compiler/assembler, then it bodes well for this same sort of advancement in other projects for windows. If it is something else, then perhaps not-so-much. You see, some of my machines are used by folks for their everyday business. Some are dedicated crunchers. All the dual purpose machines are on one of the Windows while the dedicated machines are on Ubuntu. Frankly, I do not like having to mess with both Operating Systems and only do it because the Ubuntu machines produce more throughput. Now since I mostly run HCC, then the success of this project will let me, go back to one opsys. I would love to think that new projects and the existing ones will all be improved by this new whatever it is. Make sense? EDIT> spelling RT, We were able to investigate using a different compiler on this application. Now, the main question is do the results still produce a valid answer that the researchers expect. If not then we will need to look into what compile options were used and as you can tell this all takes time. BTW, the results are on their way to the researchers from the BETA to compare with the other results. Thanks, -Uplinger Thanks Guys. I appreciate the response. I suppose that there are many more Windows machines than the other types and so this should be a real boon to the HCC project. I assume that since this is a compiler change, there is potential to improve the efficency of other projects on windows as well. As to being as efficient Sekerob, all we have to do is get close and I will take the opportunity to make my life simpler... 99.95 is a big number to try to match.  |
||
|
|
uplinger
Former World Community Grid Tech Joined: May 23, 2005 Post Count: 3952 Status: Offline Project Badges:
|
First batch for HCC1 looked great. We are going to load up another batch from a different series to get them some more data on the how the application runs. But so far things are looking great. Thank you again for your assistance in testing the new agent.
Thanks, -Uplinger |
||
|
|
RT
Master Cruncher USA - Texas - DFW Joined: Dec 22, 2004 Post Count: 2636 Status: Offline Project Badges:
|
No problem.... we are loving it.
---------------------------------------- |
||
|
|
|