Soft Error Detection and Mitigation in Computer System

Cosmic ray induced soft errors have become a major concern for systems designers and end users in recent years due to the increased memory density and smaller design rules used. Several techniques exist to detect and mitigate the occurrence of these soft upsets, such as error detection, error correction, cache scrubbing and array interleaving. This tutorial addresses the tradeoffs of these techniques in terms of area, power and performance penalties vs increased reliability. In most system applications, a combination of several techniques is required to meet the necessary reliability and data integrity targets.

Charles Slayman

Charles Slayman received his BA degree in Physics, 1974 and PhD in Electrical Engineering and Computer Science, 1980 from the University of California at Berkeley, CA. He is currently employed at Sun Microsystems, Inc in Menlo Park, CA in quality and reliability of memory technology. Prior to joining Sun in 1997, he held positions as Foundry Operations Manager at Alliance Semiconductor, R&D Pilot Line Manager at Cypress Semiconductor and Fab Engineering Manager at PowerHybrids, a division of M/A Com, Inc. After graduating from UC Berkeley, he joined Hughes Research Laboratories, a division of Hughes Aircraft Co, where he worked on high-speed integrated and fiber-optic devices, and development of advanced ion and electron beam lithography.