ISC'12—Hamburg, Germany, 18th June 2012 SECO® is pleased to announce that the NVIDIA® CUDA® on ARM Development Kit, codename CARMA DevKit, is now available to order from www.seco.com/carmakit
. The CARMA DevKit is designed to support the growing demand for computing initiatives around the world for all developers looking to create energy-efficient high-performance computing (HPC) solutions with ARM architecture.
The CARMA DevKit features the NVIDIA Tegra® 3 Quad-core ARM A9 CPU and the NVIDIA Quadro® 1000M GPU with 96 CUDA cores. It ships preinstalled with the latest version NVIDIA CUDA parallel programming environment to run existing CUDA applications, offering HPC developers a simple way to create CUDA applications for GPU-accelerated systems with ARM processors.
“Growing energy demands and rising costs are forcing the HPC market to find more power efficient solutions. And, customers are increasingly turning to hybrid architectures that combine ARM cores with advanced GPU accelerators,” comments Gianluca Venere, sales director of SECO. “Thanks to hybrid architectures based on ARM, it is possible to parallelize any application with at least an order of magnitude reduction in power consumption compared to x86-based architectures. The CARMA platform will help developers, researchers and solution designers build simple, economical, efficient, and scalable systems for small, medium and large-scale demands.”
“The growing energy demands of next-generation supercomputers threaten to limit the future growth of computational science,” said Ian Buck, general manager of GPU computing at NVIDIA. “The HPC community needs to invest in developing applications for ARM-based systems, which combine the world’s most energy-efficient processors with high-performance GPU accelerators. The CARMA DevKit includes a rich set of software tools that make it easy for developers to create and optimize science and engineering applications on this new platform.”
The CARMA kit is the outcome of BSC's research into energy-efficient computing solutions based on the use of embedded technology for HPC. It builds on the experience of our Tegra2 cluster, developed in the context of the PRACE-1IP project" says Alex Ramirez, group leader at the Barcelona Supercomputing Center. "It is of great importance to provide access to Hybrid ARM-GPU solutions to the community, to accelerate development of system software and applications. This way, we will be ready when market solutions appear."
Scalability is one of the features that make CARMA DevKit an ideal platform for not only standalone development but also for research cluster deployments.
- Energy-efficient NVIDIA Tegra 3 quad-core ARM A9 processor with 2 GB processor memory
- NVIDIA Quadro 1000M GPU with 96 CUDA cores and 2 GB DDR3 memory
- 270 single precision GFlops performance
- Preinstalled with NVIDIA CUDA parallel programming environment
- 4x PCIe Gen1 link connecting processor to GPU
- 1 Gigabit Ethernet network support
- Direct attach storage support with SATA port
- USB ports
CARMA DevKit will start shipping in July at a suggested retail price of 529 EUR, and will be comprised of:
Quadmo747-X/T30 - Qseven 1.2 specs module, NVIDIA Tegra 3 with 2 GB RAM and 4GB eMMC
- NVIDIA Quadro 1000M
- Carma carrier board
- Power supply
- Cable kit
Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) hosts the supercomputer MareNostrum. It also counts with well-known supercomputing research groups that develop tools for the academia and industry.
BSC focuses its research areas in Computer Sciences, Life and Earth Sciences and Computer Applications in Science and Engineering. In the context of this multi-disciplinary approach, BSC counts with more than 350 researchers and experts in HPC (High Performing Computing) and 100 of those are from outside Spain.
BSC-CNS was constituted as a public consortium formed by the current Spanish Ministry of Economy and Competitivity (Ministerio de Economía y Competitividad), the Department of Economy and Knowledge of the Catalan Government and the Technical University of Catalonia. Barcelona Tech (UPC), and is headed by Professor Mateo Valero.
In 2011, the BSC-CNS was recognized as a “Severo Ochoa Centre of Excellence” for its contributions and research agenda in the area of computing and applications. In the first edition of the Severo Ochoa programme, the Ministry of Science and Innovation selected 8 research centres and units in Spain to be among the best in the world in their respective fields.