by Anton Shilov
11/02/2009 | 10:48 PM
Unofficial information regarding the progress of Nvidia Corp.’s future top-of-the-range Fermi-G300 graphics card vastly contradicts to official claims. If Nvidia states that the new flagship will be commercially available this calendar year, then unofficial sources express belief that Nvidia will only be able to demonstrate working Fermi graphics cards in January.
Unnamed Nvidia partners, which are cited in media reports from DriverHeaven and HardOCP web-sites, claim that the graphics chip designer is doing its best to have working samples of flagship graphics card based on the Fermi-G300 (NV60, GT300, etc) graphics processing unit (GPU) at the Consumer Electronics Show, which takes place in Las Vegas, Nevada, from the 7th till the 10th January, 2010.
Obviously, if the first public demonstration of top-of-the-range Fermi will only take place on the second week of January, commercial availability of the novelty should be expected sometime in February at the earliest. Late availability of Nvidia’s DirectX 11 products means that ATI, graphics business unit of Advanced Micro Devices, will have a lot of time to sell its ATI Radeon HD 5800 lineup without any competition.
The flagship Fermi graphics processor will feature 512 stream processing engines (which are organized as 16 streaming multi-processors with 32 cores in each) that support a type of multi-threading technology to maximize utilization of cores. Each stream processor has a fully pipelined integer arithmetic logic unit (ALU) and floating point unit (FPU). The top-of-the-range chip contains 3 billion of transistors, features 384-bit memory GDDR5 memory controller with ECC and features rather unprecedented 768KB unified level-two cache as well as rather complex cache hierarchy in general. Naturally, the Fermi family is compatible with DirectX 11, OpenGL 3.x and OpenCL 1.x application programming interfaces (APIs). The new chips will be made using 40nm process technology at TSMC.
At the GPU Technology Conference in September ‘09, Nvidia demonstrated the A1 revision of the Fermi-G300 graphics chip made in late August, whereas usually the company uses only A2 or even A3 revisions on commercial products. It usually takes months to create a new revision, therefore, actual availability of commercial Fermi graphics board scheduled on February 2010 is not a huge surprise.
Nvidia did not comment on the news-story.