Image Image Image Image Image Image Image Image Image Image

ParityPortal | September 30, 2014

Scroll to top

Top

One Comment

$99 Parallella supercomputing boards start shipping

$99 Parallella supercomputing boards start shipping
Ravi Mandalia

Adapteva has started shipping its $99 Parallella parallel processing single-board supercomputer to initial Kickstarter backers.

Multiple commercial off-the-shelf (COTS) products like the Raspberry Pi are available in the market which when used in multiple numbers with Linux operating system can effectively be used as supercomputers but, these systems don’t natively support parallel computing which is the corner stone of today’s supercomputers.

Parallella is powered by Adapteva’s 16-core and 64-core Epiphany multicore processors. Announcing the development, Adapteva founder and CEO Andreas Olofsson said, “Yesterday we shipped the first credit card sized gen-0 Parallella board to a Kickstarter backer and approximately 40 more will go out this week to other early access backers (ROLF, 64-CORE-PLUS, and DEVELOPER reward levels) and folks who generously answered our cry for help a month back.”

The company has started accepting preorders on its website and the CEO has announced that the company will be keeping the entry point at $99 without making any loss. The company has further revealed that all the Kickstarter backers will be receiving their Parallella units after some final refinements.

The first model to be shipped has the following specifications: a Zynq-7020 dual-core ARM A9 CPU complemented with Epiphany Multicore Accelerator (16 or 64 cores), 1GB RAM, MicroSD Card, two USB 2.0 ports, optional four expansion connectors, Ethernet and an HDMI port.

Parallella is capable of running Ubuntu out of the box and Adapteva recommends the same. The support for other operating system will depend on how active the developer community is. Further the company is going to ship its open source Epiphany development tools [PDF] which comes with a multicore debugger, C compiler, Eclipse IDE, OpenCL SDK/compiler, and run-time libraries.