[lug] Parallella: low-power, cheap, flexible board with 16, 64, ... epiphany cores

[Steve Rogers]

IIRC Epiphany has 32 kb on chip memory for each processor for both code and
data.  Effectively utilizing Parallella's capabilities looks like an
interesting challenge as one may need to distribute the solution across the
Epiphany, the ARM cores, and the FPGA depending upon the problem being
solved.


On Wed, Jul 16, 2014 at 9:33 AM, <stimits at comcast.net> wrote:

> Here's another people may find interesting...it isn't technically for
> anything but test purposes via the EULA (it lacks FCC certification), but
> otherwise is an amazing system intended for developing CUDA parallel apps
> which utilize the GPU:
>
> https://developer.nvidia.com/jetson-tk1
>
> GPU computing is one of the more interesting topics for myself because it
> allows a tremendous amount of power in a tiny space, and is one of the
> fastest growing trends in hardware.
>
>
> _______________________________________________
> Web Page:  http://lug.boulder.co.us
> Mailing List: http://lists.lug.boulder.co.us/mailman/listinfo/lug
> Join us on IRC: irc.hackingsociety.org port=6667 channel=#hackingsociety
>



-- 
Steve Rogers
http://www.linkedin.com/in/shrogers
“"Don't worry about what anybody else is going to do… The best way to
predict the *future* is to *invent* it."* -*- Alan Kay
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lug.boulder.co.us/pipermail/lug/attachments/20140716/6a697cc7/attachment.html>