Lucid’s Multi-GPU Technology Finally Available, Demonstrated

Intel-Funded Multi-GPU Tech Demonstrated

by Anton Shilov
08/19/2008 | 03:41 PM

Lucid Technologies, a company funded by Intel Capital, demonstrated its multi-GPU technology that claims to be agnostic to graphics processing units (GPUs), but to enable exceptional scalability in multi-GPU configurations, at Intel Developer Forum. Lucida claims that its’ Hydra engine enables unprecedented performance.

 

“Designers interested in evaluating the Hydra 100-series engine for their systems will quickly see the amazing graphics capabilities supported by its truly scalable processing power,” said Moshe Steiner, Lucid’s chief executive officer.

The Hydra engine sits between the chipset and multi-GPUs and acts like a dispatch processor within a graphics processing unit (GPU) to distribute tasks among the processors. The technology drives the GPUs, performing scalable rendering of a particular image or scene, and relies on “unique adaptive decomposition and acceleration algorithms to overcome bottlenecks”. The Hydra engine combines a PCI Express 1.1. system-on-chip (Tensilica Diamond 212GP programmable general purpose processor) with exclusive software technologies that load-balances graphics processing tasks, delivering near-linear to above-linear performance with two, three or more graphics cards.

“One of the Hydra engine’s main benefits to OEMS is that they can develop a single motherboard to work with either AMD or Nvidia multi-GPU configurations,” said Mr. Steiner.

The Hydra 100-series is available now for customer validation with volume delivery expected in Q4 2008.