By Topic

A novel approach to overcome bandwidth limitations of parallel computers based on cmos, Part-1 : General concepts

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)
Narendra K Karmarkar ; Laboratory for Computational Mathematics, India

We present a new approach to overcome the well-known deficiency of CMOS technology pertaining to global communication capability within large-scale, parallel information processing systems such as supercomputers, internet switches and multi-ported storage. This is based on a novel surface-normal communication scheme. It exploits massively parallel quantum tunneling through an array of field emission devices lining the surface of an electromagnetic vacuum chamber and multi-trajectory electron optics through the cavity volume. This results in significantly reduced energy loss per bit communicated, due loss-less nature of quantum tunneling and collision-free movement of electrons through vacuum. Modulation of field-emitted electron beams and the new electron optical system are both enabled by recent insights into optimization problems with multiple global minima. Just as many natural systems governed by potential energy functions with multiple global minima are well understood theoretically (e.g. systems with translational symmetry in crystallography and solid state physics), we are able to analyze behavior of electrons in systems with artificially created symmetries based on finite projective geometry. The resulting physical complexity of connecting n information sources to n destinations is O(n), in contrast with conventional approaches of O(n2) physical complexity.

Published in:

Electron Devices and Semiconductor Technology, 2009. IEDST '09. 2nd International Workshop on

Date of Conference:

1-2 June 2009