GPU

What is GPU Co-processing?

GPU co-processing technology bundles multiple GPUs within an integrated system, either on board or through deskside/rackmount add-on modules, and uses the massively parallel architecture of the graphics processor for general-purpose computing tasks. Because of that parallelism, single-precision and double-precision floating-point operations can speed up dramatically.

Applications such as molecular modeling, weather modeling, and geophysical research can immensely benefit from GPU technology.

Aeon Computing can configure compute platforms with nVidia Tesla Kepler (K20/K40) GPUs using the CUDA programming environment or AMD/ATi FirePRO S10000 GPUs using the OpenCL programming environment.

Aeon Computing offers a fully-integrated NVIDIA Tesla powered Personal SuperComputer system in the EclipseGP™. With up to 4 NVIDIA Tesla/Fermi/Kepler GPUs or up to 4 AMD/ATI FirePRO S10000 GPUs, the EclipseGP™ can achieve computational speeds of more than 16 TFLOPs (single precision). For GPU friendly applications the EclipseGP™ can essentially be a supercomputing resource at a fraction of the cost and size of a CPU-only cluster. The EclipseGP™ is available as a desktop workstation or as 1U, 2U or 4U rackmount server.