All the latest quantum computer articles

See the latest stories on quantum computing from eeNews Europe

Thursday, March 11, 2010

GE puts CUDA on single board computer

Single board computer combines Intel Core2 Duo, NVIDIA CUDA and OpenVPX for 390GFLOPS in a slot

GE Intelligent Platforms has launched a rugged 6U OpenVPX Single Board Computer (SBC) that is the first with an integrated GPGPU (general purpose computing on a graphics processing unit) capability. The IPN250 delivers high levels of computing performance for size, weight and power (SWaP) constrained platforms at lower cost, creating new application opportunities. It enables system integrators to deploy a single COTS module where previously multiple disparate modules would have been required – undertaking, for example, front end processing of sensor-acquired data, digital signal processing, backend processing and graphics/video processing, and delivering high resolution mission critical data more rapidly than has previously been possible.
The IPN250 is the second product from GE to feature NVIDIA’s CUDA technology: the CUDA-enabled GRA111 3U graphics board was announced in November 2009. CUDA is becoming increasingly attractive to systems integrators in military and aerospace since it has been demonstrated to be capable of enabling performance gains of up to 100x in a range of applications: its innovative technology and openness create the opportunity for improved productivity and sustainable competitive advantage. It is increasingly mandated by some Department of Defense (DoD) program offices because it offers increased flexibility and reduced cost of ownership when compared with previous FPGA-centric solutions.
“The IPN250 allows customers to easily deploy sophisticated applications developed on NVIDIA-enabled PCs directly onto a rugged GPGPU platform, reducing risk to schedules and shortening time to deployment,” said Peter Cavill, General Manager, Military & Aerospace Products at GE Intelligent Platforms. “It reduces cost by leveraging the growing ecosystem of software programmers creating high performance computing applications in standard development environments such as CUDA, OpenCL, OpenGL and MATLAB, to support long term code portability across multiple generations of COTS hardware platforms.”
The IPN250 combines NVIDIA’s latest GT240 96-core GPU with an Intel® Core™2 Duo processor operating at 2.26GHz and 8 GBytes of DDR3 SDRAM to deliver up to 390 GFLOPS of performance per card slot, depending on the application. It is designed from the ground up to be compliant with the OpenVPX standard, ensuring interoperability with a broad range of other OpenVPX boards. Providing a computationally-dense platform, the IPN250 is ideal for demanding applications that are constrained in terms of size, weight and power (SWaP). It is also VITA48/REDI-compliant, allowing it to be deployed in the harshest environments: build options for air-, spray- and conduction cooling are available.
The IPN250 feature set includes two primary data plane, 10 Gigabit Ethernet ports supporting multi-board switched fabric OpenVPX architectures. A 16-lane PCI Express gen2 interface on the P2 expansion plane provides high speed interconnect for multi-board GPGPU clusters as well as system I/O to PCI Express-enabled sensor modules such as GE’s family of Xilinx Virtex5 and Virtex6 mezzanine cards. Two 1000Base-T and two 1000Base-Bx control plane ports are available, together with additional PCI Express, USB 2.0 , SATA, COM ports, GPIO , audio and TV input. Video and multimedia is supported via the dual link DVI, HDMI and VGA ports directly into the NVIDIA GT240 device to cater for a wide range of interfaces.
GE Intelligent Platforms’ AXISLib advanced multiprocessor software development VSIPL, DSP and math libraries for CUDA and INTEL SSE4 facilitate application development and code portability for the IPN250 and future GPGPU platforms. In addition to NVIDIA’s CUDA environment, supported software includes Linux, Windows, Microsoft DirectX, OpenCL, OpenGL and MATLAB, together with NVIDIA’s PureVideo Technology and PhysX.

Reblog this post [with Zemanta]

No comments: