Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Controls/MCUs

NVIDIA GPUs increase performance by four times

Posted: 12 Feb 2002 ?? ?Print Version ?Bookmark and Share

Keywords:nvidia. graphic processor unit? gpu? graphics card? video card? geforce4?

NVIDIA has unveiled the GeForce4 family of GPUs, for the desktop PCs, Macs and notebook computers. The family includes the GeForce4 Ti, Mx and the Go mobile GPUs. They are claimed to deliver up to four times the performance over previous products. It also features the company's Accuview Antialiasing feature and the nView display technology that provides multi-display.

The GeForce4 Ti line includes the 4600, 4400 and 4200 versions. They are powered with an nfiniteFX engine and are capable of driving complex geometries and character animations.

The GeForce4 460, 440 and 420 of the MX line are targeted for mainstream desktop PCs, while the GeForce4 440 and 420 Go are positioned for the mobile PC platform.

The Accuview Antialiasing engine provides visual displays without the "jaggies" associated with objects rendered with pixel-based displays. The engine utilizes hardware-implemented, high-resolution multisampling techniques, including 2x, 4x, Quincunx and a new 4XS mode. The company claims that this engine delivers up to five times the antialiased performance of previous NVIDIA solutions.

The nView multidisplay technology supports arrangements of CRTs, televisions, and digital flat panel displays that can be combined to drastically increase a computer's desktop workspace. The technology incorporates built-in attribute and performance tuning for each of the individual display devices it supports.

nView also features hot key binding, smart Windows management enhancements, and the ability to name and save up to 32 different desktop configurations.

The GeoForce4 family utilizes Lightspeed Memory Architecture (LMA) II, an advanced 128-bit DDR memory interface to double available memory bandwidth. The architecture includes NVIDIA's second-generation Z-occlusion culling to pre-determine which objects in a scene are visible to the eye.

LMA II can also compress the values of distances between objects that are stored in the GPU Z-buffer at a ratio of four to one, without any degradation in accuracy. It also features the Quad Cache memory cache that allows instant rendering pipeline access.

Article Comments - NVIDIA GPUs increase performance by ...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top