By Topic

GPU technology trends and future requirements

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
John Y. Chen ; NVIDIA Corporation, Santa Clara, CA, USA

Inherent massive parallelism makes GPUs (Graphic Processing Units) a natural beneficiary of Moore's law (1). Even modern GPU chips that contain billions of transistors are a long way from achieving perfect simulation and rendering of real-world scenes. The desire to have more transistors continues. In addition, the use of GPUs for parallel computing is only beginning to enable many exciting applications. This paper begins with GPU basics and its evolution with technology, then connects GPU requirements such as FLOPS, power and product variations to device and process technology. It will also address technological opportunities and challenges for future GPU advancement.

Published in:

2009 IEEE International Electron Devices Meeting (IEDM)

Date of Conference:

7-9 Dec. 2009