powered by Jive Software

Epiphany-IV for clustering?

I bought a raspberry pi “simply because”. At six times the cost more computing power per watt

http://www.adapteva.com/white-papers/ten-myths-debunked-by-the-epiphany-iv-64-co re-accelerator-chip/

Parallella devices would be fully functioning computers, shipping with an Ubuntu 11.10 port to ARM, with 1GB RAM, two USB 2.0 ports, 16GB of MicroSD storage, HDMI, and Gigabit Ethernet. An open source SDK would allow development of applications for Adapteva’s Epiphany architecture using C, C++, and OpenCL. Sizewise, Parallella would be 3.4’’ x 2.1’’, very similar to the Raspberry Pi.

There are obvious similarities between Parallella and hobbyist projects like Raspberry Pi, the $35 Linux computer, and the $30 Arduino, but Olofsson said Parallella will offer anywhere from 10 to 50 times the performance of Raspberry Pi, with the latter figure coming from the potential 64-core version. While it’s three times pricier than the Raspberry Pi, $99 is dramatically cheaper than most parallel computing platforms, he notes. Boards containing Adapteva chips that are already sold by partner company Bittware cost thousands of dollars


I’m trying to rationalize purchase

Well, if they’re comparing to the Raspberry, and saying you’re getting between 10 and 50 better performance on a 64 core solution, that means you’re getting far less performance in single threaded processes than the Raspberry Pi.

So the only benefit in my opinion would be specially dedicated software for the platform. There’s very few applications (if there’s any) ported to ARM that can take benefit of multiple threads, so you will probably be stuck with specially designed code for the Epiphany platform. Not worth it if you’re not a developer.