October 29, 2012
Chipmaker Adapteva has hit its funding goal for the company's Parallella project. As HPCwire reported last month, the company decided to employ the micro-investor platform known as Kickstarter to speed development of its manycore Epiphany floating point accelerator. The latest design promises a stunning 50 gigaflops per watt, but getting the silicon into the hands of developers has been a challenge.
The company set out to get at least $750,000 worth of pledges to fund a project that would deliver an Epiphany coprocessor board to all interested parties – mainly programmers who were looking to kick the tires on a unique and highly parallel computing architecture. The pledge window was just 30 days, which began on September 27. When the Kickstarter clock ran out, Parallela had signed up $898,921 from 4,965 backers.
The pitch was that for $99 investors would receive a PCIe "supercomputing" board equipped with a dual-core ARM A9 chip driving Adapteva's 16-core, (26-gigaflop) Epiphany accelerator. Of course, 26 gigaflops is hardly a supercomputer by today's standards, but the ability to develop a 16-way parallel application on a hundred dollar platform is quite valuable in and of itself.
An investment of $199 would have allowed for the more powerful (100-gigaflop) 64-core chip if $3 million of total funding was pledged. Alas that "stretch goal" did not come to pass.
When HPCwire spoke with Adapteva CEO and founder Andreas Olofsson last month, he said the money would be used to produce the Epiphany processors in greater volumes, thereby reducing the cost to a few dollars per chip. And now, since thousands of developers will soon be getting their own Adapteva board, the Epiphany architecture will get the additional benefit of more applications and software tools ported to the platform.
For a deeper dive into the Epiphany architecture and Parallela, check out the Kickstarter site for the project.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?