| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
 |
World Community Grid Forums
Category: Support
Forum: Suggestions / Feedback
Thread: Why don't we work on projects sequentially? |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 14
|
|
| Author |
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
One only needs to look at where the Help Fight Childhood Cancer scientists are with their analysis and wet-lab testing, something like target 3 (S2), see http://www.m.chiba-u.ac.jp/class/bioinfor/wcg/e/hfcc_e/news.html, when we're already on target 7, to know that wisdom was not born yesterday in why parallel processing of multiple sciences has many attractions, to include holding allot of concentrated power, that if need be, with volunteers cooperation, can be redirected for a large part, such as a super-promising experiment for science X Y or Z. We had a few and they were raced through, which with a stand alone grid would not likely have happened. After 18 projects, WCG is getting good at it, the FLU1 project from request > proposal to go-live in 1 week. That's the collective power of World Community Grid, and only scratching the surface of what can be mentioned in addition to the once already noted in this thread.\
Crunching On. --//-- |
||
|
|
Hypernova
Master Cruncher Audaces Fortuna Juvat ! Vaud - Switzerland Joined: Dec 16, 2008 Post Count: 1908 Status: Offline Project Badges: 
|
Many projects scramble to keep adding to their server capacity as results keep streaming in from WCG. Occasionally we have to slow them down until they can get an addition to their grant to buy more capacity. To me this comment from lawrencehardin is an excellent one. It justifies very clearly that we must have in parallel many projects. In this way the WCG crunching capability will be best used in its entirety. The addition of projects does slow naturally certain projects to allow enough time for the scientists to analyze. For projects that would have the capacity to absorb much more valid WU's than WCG can offer there is a very clear solution, and that is to port those projects on GPUs. In this way everybody, crunchers and scientists will be happy and the world a better place.   |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Even 1 thread without GPU comments would by now equate to a blessing. If the scientists could, they would. Try converting a sequential/serial 1 million line Fortran program evolved over years into something that processes parallel and can do few tricks.
thx --//-- |
||
|
|
Hypernova
Master Cruncher Audaces Fortuna Juvat ! Vaud - Switzerland Joined: Dec 16, 2008 Post Count: 1908 Status: Offline Project Badges:
|
Here it is Sekerob.
---------------------------------------- |
||
|
|
|