Archives by Day

About Rainier

PC gamer, WorthPlaying EIC, globe-trotting couch potato, patriot, '80s headbanger, movie watcher, music lover, foodie and man in black -- squirrel!


NVIDIA Unveils New Graphics Cards and Technology

by Rainier on Nov. 8, 2006 @ 1:58 p.m. PST

NVIDIA introduced the GeForce 8800 GPU and the nForce 680i SLI media and communications processor (MCP) designed specifically for Intel Core 2 Quad and Core 2 Duo CPUs, and also introduced the CUDA technology, a new architecture for computing on NVIDIA graphics processing units.

The GeForce 8800 GPUs are the world's first to support Microsoft DirectX 10, the next-generation programming interface that will be introduced with the upcoming Microsoft Vista(TM) operating system. The GeForce 8800 GPUs feature a number of groundbreaking technologies including:

  • A revolutionary new unified shader architecture comprised of up to 128-parallel, 1.35GHz stream processors that deliver amazing floating point processing power for unmatched gaming performance
  • NVIDIA Quantum Effects physics processing technology that ushers in a new generation of visual effects and graphics realism
  • Simultaneous 16x anti-aliasing and 128-bit High Dynamic Range (HDR) lighting for unparalleled image quality

Throughout the GeForce 8800's development process, NVIDIA worked in close partnership with the world's top game designers to develop next-generation DirectX 10 titles on next-generation NVIDIA GPUs, enabling them to take full advantage of the increased performance and new features. As a result, more than 20 next-generation titles, including Crysis, Hellgate: London, World in Conflict, Company of Heroes, Microsoft Flight Simulator X, and Age of Conan -- all with jaw-dropping visuals, were on display at the Company's official unveiling which took place today in San Jose, CA -- all running on new GeForce 8800 GTX GPUs.

The other half of the definitive gaming platform is the new NVIDIA nForce 680i SLI MCP, which was designed to deliver the highest performance for Intel Core 2 Quad and Core 2 Duo-based PCs. Aimed squarely at the hard-core enthusiast, the NVIDIA nForce 680i SLI MCP is a motherboard solution that provides extensive support for the latest cutting-edge technologies -- including enhanced support for NVIDIA SLI multi-GPU technology. With its dual Gigabit Ethernet ports and advanced storage features, the NVIDIA nForce 680i SLI MCP can, in about one second, send a 30-minute television show between PCs and store hundreds of high-definition movies. Featuring what customers are saying is the most advanced overclocking solution in the market, the NVIDIA nForce 680i SLI MCP can more than double the front-side bus (FSB) speed of many Intel Core 2 Duo CPUs. Also included is support for SLI-Ready high- performance memory DIMMs, and a third PCIe graphics slot for extended multi- display environments or future physics processing.

In addition to providing silicon to the world's leading motherboard manufacturers, NVIDIA also announced today it has started to design and manufacture its own line of enthusiast-class NVIDIA nForce 680i SLI-based motherboards, which are being offered as a turnkey solution for select channel partners. This "Designed by NVIDIA" program allows NVIDIA partners -- such as EVGA and others, to bring NVIDIA nForce 680i SLI-based motherboards to market faster than ever before, and lets consumers know that the motherboard they are purchasing fully supports all of the hardware and software features that are offered with the NVIDIA nForce 680i SLI MCP.

"EVGA is proud to be a launch partner for the new NVIDIA GeForce 8800 series and we are beyond ecstatic to be the first company to bring an NVIDIA nForce 680i SLI-based motherboard to the enthusiast market," said Andrew Han, President and CEO of EVGA. "EVGA would like to applaud NVIDIA for the astonishing performance enhancements found in both the NVIDIA nForce 680i SLI core logic and GeForce 8800 GTX graphics solutions."

GeForce 8 series GPUs, including the GeForce 8800 GTX and GeForce 8800 GTS, NVIDIA nForce 680i SLI-based motherboards, and fully-equipped Windows- based PCs are now available from leading retail outlets, system builders, and OEMS.

GPU computing with CUDA is a new approach to computing where hundreds of on-chip processor cores simultaneously communicate and cooperate to solve complex computing problems up to 100 times faster than traditional approaches. This breakthrough architecture is complemented by another first -- the NVIDIA C-compiler for the GPU. This complete development environment gives developers the tools they need to solve new problems in computation-intensive applications such as product design, data analysis, technical computing, and game physics.

Available today on the new GeForce 8800 graphics card and future NVIDIA Quadro® Professional Graphics solutions, computing with CUDA transcends the limitations of traditional GPU stream computing by enabling GPU processor cores to communicate, synchronize, and share data.

CUDA-enabled GPUs offer dedicated features for computing, including the Parallel Data Cache, which allows 128, 1.35GHz processor cores in newest generation NVIDIA GPUs to cooperate with each other while performing intricate computations. Developers access these new features through a separate computing driver that communicates with DirectX and OpenGL, and the new NVIDIA C compiler for the GPU, which obsoletes streaming languages for GPU computing.

A CUDA-enabled GPU operates as either a flexible thread processor, where thousands of computing programs called threads work together to solve complex problems, or as a streaming processor in specific applications such as imaging where threads do not communicate. CUDA-enabled applications use the GPU for fine grained data-intensive processing, and the multi-core CPUs for complicated coarse grained tasks such as control and data management.

blog comments powered by Disqus