mike - my comments were a bit tongue in cheek. if you're running this constantly you're typically much better off building out your own compute infrastructure. i would be remiss if i didn't point out that there are a lot of folks doing this themselves and a host of folks in this market segment. if you don't have the need to run large simulations on an ongoing basis, then utility compute resources like EC2 are a great way to go and amazon is by no means the only game in town on that, they've just made the process of setup and billing dead easy. On Tue, Jul 7, 2009 at 12:45 PM, Mike Miller<mbmiller+l at gmail.com> wrote: > On Tue, 7 Jul 2009, steve ulrich wrote: > >> mike - >> >> building out your own compute infrastructure is so 2002. ;) >> >> i've used amazon EC2 for a very similar application where i've been >> running large simulations on their infrastructure with my own VM image that >> i use for my purposes. you can simply dial up the number of processors that >> you purchase and use. you're charged by the hour for the the number of CPU >> instances you use. >> >> instead of buying hardware yourself that you have to power up, replace >> HDDs, etc. for and manage connectivity for you let someone pay for that and >> simply use their resources on demand. > > > Once we get things going, we'll probably be using all (80 or so) cores 24/7 > for months on end. I assume the costs for Amazon EC2 would eventually > surpass our initial hardware costs ($25,000). > > Regarding power and management troubles -- someone else is doing that and we > don't have to pay them. I guess it is paid, in theory, by indirect cost > money from our grants to the college. > > Mike > -- steve ulrich (sulrich at botwerks.*)