Chief executive officer of Silicon Graphics International said that his company was working with developers of graphics processing units (GPUs) over integration of graphics chips into its server and high-performance computing platforms. This is one of the first time when leading makers of servers express claim that general purpose computing on GPUs (GPGPU) is the future of computing.
“The GPU is not just for gamers anymore. SGI believes there is an enormous customer benefit to incorporating the GPU into its core platforms for both computational acceleration and for visualization. This is why we are now focusing more R&D investment into advancing GPU products by means of its integration into our core platforms and applying these products to real-world problems,” said Mark Barrenechea, chief executive officer of SGI.
GPGPU is already not something new for proprietary applications like oil and gas exploration, medical imaging, financial analysis and other. However, GPGPU still has to reach mainstream market and when a leading maker of servers and high-performance computers promises to incorporate GPUs to accelerate stream computing across the board, it seems that GPGPU technologies are about to enter the mainstream markets.
“Our vision is to provide an end-to-end visual computing solution through our core platform technology and expert services. The building block for our scalable platforms contains GPU as a core component. […] Further, our next generation platform, Ultraviolet, will also support GPUs,” said the head of SGI.
Graphics processors are much more efficient than traditional central processing units when it comes to processing of highly-parallel workloads. SGI recently expanded its GPGPU support with the introduction of the CloudRack X2 Workgroup Cluster incorporating “a wider set of options from ATI/AMD and Nvidia Corp. Later on other platforms from SGI will also be equipped with GPUs.
“This is why we are focused on working closely with Nvidia, ATI/AMD and Intel many-core Larrabee, integrating their advanced graphics technology into our core platforms versus writing software to replace the GPU. When speed truly matters, put it in hardware. Shift Happens. And the shift is the GPU,” concluded Mr. Barrenechea.