Messages in this thread | | | From | (Alan Cox) | Subject | Re: Remote fork() and Parallel programming | Date | Mon, 15 Jun 1998 17:43:25 +0100 (BST) |
| |
> Quick - name me one parallel computation that would leave a CPU idle > for 60 seconds while the other ones are busy on an SMP. The point?
Ray tracing, when one CPU gets a very simple block of rays.
> All the parallel computations I've seen statically load balance at > initialization time and then never move.
Because people use them for customised specific jobs, partly because thats the most efficient way to do it in CPU terms (and Im not arguing that issue - DSM is less efficient)
> I agree that there are other types of parallel loads, but they > tend to be more of the time sharing sort. I don't think anyone > is suggesting that migrating vi or sendmail is a good idea. Right?
What about big background computations spread across a network of machines also used for desktop timesharing - Condor does exactly this. People login to a desktop and the fortran monster quietly sidles off to another work station.
Alan
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |