Modular smartphones could be reused as computer clusters

26.01.2015
The promise of modular smartphones like Google's Project Ara is that buyers will be able to upgrade components at will -- and now Finnish company Circular Devices has come up with a use for discarded computing modules.

Circular Devices is working on its own modular smartphone concept, Puzzlephone, and hopes to ship working products before the end of the year even though it hasn't yet released a prototype.

The idea behind the Puzzlephone and Project Ara is to increase the longevity of smartphones and reduce waste in the process. With the Puzzlecluster platform, Circular Devices is aiming to take waste reduction one step further.

"It makes no sense to discard a perfectly working computer just because you have upgraded your smartphone. The Puzzlecluster will extend the usable life of the Brain modules way beyond any other smartphone processor," Alejandro Santacreu, CEO at Circular Devices, said in a blog post on Saturday.

The Brain module includes the CPU, which will help power the clusters. The plan is also to reuse old battery modules for back-up power. Drawings of the Puzzlecluster architecture show a chassis with slots for the reused modules, which can then be interconnected with others to create the cluster. Just one unit could also be used as a desktop computer.

Circular Devices didn't provide any details on when Puzzlecluster would start shipping or what software would be used to manage the hardware. But assuming the company is able to ship the first Puzzlephones this year, the first CPU modules should be available for reuse by 2017. So the company has plenty of time to turn its drawings into a real product.

The goal is to deliver a product that's scalable enough to be used by home users, small and medium enterprises, public institutions and data centers. Potential applications include rendering and data analytics, according to Circular Devices. If the cost is low enough, hobbyists and students could use it to learn more about programming for parallel computing.

For anyone that wants to build a cheap cluster now, though, the Rasberry Pi single-board computer already offers a good alternative, and Nvidia has published a helpful how-to onbuilding Raspberry Pi clusters.

Send news tips and comments to mikael_ricknas@idg.com

Mikael Ricknäs