[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] regrouping efforts

Have you looked at the master-worker framework?



On 2010-08-16, at 6:09 PM, andrew.downs@xxxxxxxx wrote:

> Thanks for the replies I've gotten so far.   It seems that in my case, the only tasks that could really be split up at BSP 
> (which takes almost no time, even on my insanely complex designs, it's just not a resource intensive process)
> Vis,  and Light
> My main interest is...if there a way to cluster computers so that I could run an executable on the master node, 
> and it'd offload the stress onto slave nodes, that's what I'm looking for.  
> Just some program that has client/server parts and would spread the work across a few machines.
> Does that exist?  If it doesn't, I'm thinking it would be more cost effective to just try to 
> port the compiler (which is open source) to CUDA and stuff a computer full of gpus, as this is the kind of math that gpus are perfect for anyway.
> Thanks again.
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
> The archives can be found at:
> https://lists.cs.wisc.edu/archive/condor-users/