Posted on Monday, November 14 2011 @ 19:56 CET by Thomas De Maesschalck
NVIDIA reports the Barcelona Supercomputing Center (BSC) is working on world's first hybrid supercomputer with the low-power NVIDIA Tegra ARM-based processors together with NVIDIA CUDA-supporting GPUs.
NVIDIA today announced that the Barcelona Supercomputing Center (BSC) is developing a new hybrid supercomputer that, for the first time, uses energy-efficient, low-power NVIDIA(R) Tegra(TM) ARM CPUs, together with high-performance NVIDIA(R) CUDA(R) GPUs.
BSC is planning to develop the first large scale system based on this technology, with a near term goal of demonstrating two to five times improvement in energy efficiency compared with today's most efficient systems. BSC is showing the system design publicly for the first time at this week's SC11 Conference, which runs Nov. 14-17 in Seattle, Wash., in exhibit booth #235.
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 and develop a portfolio of exascale applications that run efficiently on these kinds of energy-efficient, embedded mobile technologies.
"In most current systems, CPUs alone consume the lion's share of the energy, often 40 percent or more," said 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."
To support growing demand for similar ARM-based initiatives around the world, NVIDIA also announced plans to develop a new hardware and software development kit. The kit, with hardware developed by SECO, will 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.
In recognition of its ground-breaking work leveraging NVIDIA GPUs and CUDA technology to drive education and research programs across a range of scientific disciplines, BSC was named a CUDA Center of Excellence by NVIDIA. The CUDA Center of Excellence program rewards and fosters collaboration with leading institutions that are at the forefront of parallel computing research.
BSC joins an elite network of 14 institutions around the world that are advancing awareness of parallel computing and empowering academics and scientists to conduct world-changing research. For more information about the CUDA Center of Excellence program visit: http://research.nvidia.com/content/cuda-centers-excellence.
