On 1/23/12 12:50 PM, "Rayson Ho" <[email protected]> wrote:
>On Mon, Jan 23, 2012 at 11:35 AM, Lux, Jim (337C) ><[email protected]> wrote: >> The "processors in a sea of memory" model has been around for a while >> (and, in fact, there were a lot of designs in the 80s, at the board if >>not >> the chip level: transputers, early hypercubes, etc.) So this is >> revisiting the architecture at a smaller level of integration. > >I remember 12-15 years ago I was reading quite a few papers published >by the Berkeley Intelligent RAM (IRAM) Project: > >http://iram.cs.berkeley.edu/ > >So 15 years later someone suddenly thinks that it is a good idea to >ship IRAM systems to real customers?? :-D > >Rayson Or maybe, all good ideas keep coming up again, and each time, it's refined a bit, or there's another possible source of funding appearing. Look at "solar power transmitted by microwaves from orbit" as an example. That one has a 15-20 year cycle time. You have an idea which is attractive.. You get some money to run it forward, and then insurmountable problems crop up, discoverable only with significant investment of time/money (>> 1 work month). That puts the idea to sleep for a while until either the reasons are forgotten, or technology has advanced to the point where what might have been unreasonable the previous time is reasonable now. Certainly in the computing world, where 10-15 years is sufficient for many orders of magnitude change in performance along many axes, it pays to revisit things, since what may have been a good balance or trade back then, isn't now. And that's sort of the thrust of their white paper (justifying that now the time is right), as well as staking their claim to a bunch of general applications, few of which are uniquely enabled by their proposed technology. > _______________________________________________ Beowulf mailing list, [email protected] sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
