Spanish engineers are developing a hybrid supercomputer that pairs Tegra ARM CPUs with Nvidia CUDA GPUs.
The large scale system – which is being designed by the Barcelona Supercomputing Center (BSC) – will demonstrate two to five times improvement in energy efficiency compared with today’s most efficient systems.
Indeed, BSC’s ultimate research goal is to deliver exascale-level performance while using 15 to 30 times less power than current supercomputer architectures.
This so-called EU Mont-Blanc Project will explore next-generation HPC architectures, while developing a portfolio of exascale applications that run efficiently on energy-efficient, embedded mobile technologies.
“In most current systems, CPUs alone consume the lion’s share of the energy, often 40 percent or more,” explained Alex Ramirez, leader of the Mont-Blanc Project.
“By comparison, the Mont-Blanc architecture will rely on energy-efficient compute accelerators and ARM processors used in embedded and mobile devices to achieve a four- to 10-times increase in energy-efficiency by 2014.”
It should be noted that Nvidia is coding a new hardware and software development kit to support growing demand for similar ARM-based initiatives.
The kit, with hardware developed by SECO, is slated to feature a quad-core Nvidia Tegra 3 ARM CPU accelerated by a discrete Nvidia GPU. It is expected to be available in the first half of 2012, and will be supported by the Nvidia CUDA parallel programming toolkit.