Tsubame 2 supercomputer 3.4X more efficient
NVIDIA championed a milestone for supercomputers Wednesday with the launch of a new supercomputer cluster that focuses on eco-friendly power. Tsubame 2.0, at the Tokyo Institute of Technology, uses a mix of traditional processors with Tesla cards to dramatically step up the potential maximum performance without having to ramp up the energy it uses. Although it can calculate at up to 1.19 petaflops, it uses a comparatively modest 1.2MW of power, making it 3.4 times more efficient at getting work done than Los Alamos National Laboratory's processor-only Cielo Cray.
DirectX 11 with GPGPU Tech
Microsoft's next version of DirectX will have its own alternative to the OpenCL standard proposed by Apple, the company revealed yesterday at its GamesFest conference. DirectX 11 will have support for "compute shader technology" that allows modern, more generalized video cards' effects processors to perform tasks other than rendering video, including physics calculations and other chores that would normally be handled by the main system processor.
The Khronos Group late yesterday established a new alliance between vendors that could see standards for high performance computing such as OpenCL gain a foothold across many operating systems and hardware platforms. Called the Computer Working Group, the team includes graphics rivals 3DLabs, AMD, and NVIDIA, processor makers such as ARM, Freescale, Intel, and Qualcomm, and end product manufacturers such as Motorola and Nokia, all of whom hope to create and maintain genuinely open and royalty-free standards for using newer graphics hardware to process very demanding compute tasks.