Lenovo Developing 64-Bit ARM Server Powered by Cavium

Chinese hardware giant Lenovo is developing an ARM server powered by Cavium’s 64-bit Thunder System on Chip. The project is part of a computing energy efficiency research effort funded by a U.K. government organization.

ARM Holdings, a U.K. processor company, licenses its chip architecture to chip makers. ARM processors power most of the world’s smartphones, but because they consume relatively little energy, numerous companies have been working on adapting the architecture for servers.

Cavium is one of the more recent comers to the ARM server scene, where other major players include Applied Micro, AMD, and Texas Instruments. There also used to be an Austin-based company called Calxeda, but it went bankrupt in 2013, its intellectual property gobbled up by a Taiwanese gaming company late last year.

Lenovo has been expanding its server play in leaps and bounds. Last year, the company bought IBM’s entire commodity x86 server business, instantly becoming the largest server vendor in China and one of the largest worldwide.

The prototype ARM server the company is developing will be part of its NeXtScale line, which consists of products for high-performance computing. A single NeXtScale enclosure can hold up to 12 ARM servers or pack 1,152 cores in the space of six standard rack units.

Efficiency of high performance computing systems is the focus of Lenovo’s joint research project with the Hartree Centre, an organization formed by the U.K. government’s Science and Technology Facilities Council. The project’s aim is to explore performance of scale-out and scale-up computing systems given a defined power budget.

“This is a fantastic opportunity to meet the challenge of developing a computationally powerful and energy-efficient platform based on the 64-bit ARM v8 microprocessor,” Neil Morgan, program manager for energy efficient computing at the Hartree Centre, said in a statement. “The Hartree Centre will be actively developing a robust software ecosystem encompassing compilers, linkers, numerical libraries and tools – all of which are fundamental to the adoption of these types of technologies.”