Make Home Page
Add to Favorites
XbitLabs is using Twitter
Windows Live Alerts
Nvidia Corp. to demonstrate its next-generation code-named Fermi graphics processing unit (GPU) live for the second time at SC09 conference. The demonstration of next-gen GPU at a high-profile super computing dedicated event further underlines importance of high-performance computing (HPC) for Nvidia.
At the SC09, which takes place in Portland, Oregon, on November 17 – November 19, 2009, Nvidia will demonstrate its Fermi-G300 (NV60, GT300) in action. This will be the second time ever, when Nvidia will show its next-generation chip in public. The company first demonstrated its Fermi at its own GPU Technology Conference show in late September. But while the firm showcased demos using actual pre-production Fermi chip and a prototype card, the firm displayed dummy Fermi graphics card on stage, a rather controversial move.
“Come see a live demonstration of the next generation CUDA GPU computing architecture, codenamed “Fermi”. The Fermi-based Tesla GPUs are mass market parallel processors and fuel the HPC industry’s transition to parallel processing. Compared to the latest quad-core CPUs, the Fermi-based Tesla GPUs deliver equivalent performance at 1/20th the power consumption and 1/10th the cost,” a statement at Nvidia’s web-site reads.
Nvidia last week publicly admitted that it would only start mass production of Fermi-G300 chips in the first quarter of calendar 2010. As a consequence, the company will not be able to start commercial shipments of its next-gen chips this year, despite earlier claims. No surprise that Nvidia is not showing gaming capabilities of its new product that is compatible with DirectX 11 and is concentrating on computing performance of the chip in the HPC space.
It is rather remarkable that the presentation, which will take place on the 19th of November, is called “The Next Generation CUDA Architecture, Code Named Fermi: The Soul of a Supercomputer in the Body of a GPU”, which further underlines importance of HPC for Nvidia. So far, the company has to become a significant supplier of chips for super computers, but the firm shows that it sees HPC as a major source of its revenue going forward.
