A large scale study of failures in high-performance-computing systems. Bianca Schroeder and Garth A. Gibson. In International Symposium on Dependable Systems and Networks (DSN), June 2006. (URL)
@INPROCEEDINGS { gibson_dsn06,
AUTHOR = { Bianca Schroeder and Garth A. Gibson },
TITLE = { A large scale study of failures in high-performance-computing systems },
BOOKTITLE = { International Symposium on Dependable Systems and Networks (DSN) },
MONTH = { June },
YEAR = { 2006 },
URL = { http://www.cs.cmu.edu/~bianca/dsn06.pdf },
}