This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
Abstract Details
Activity Number:
|
679
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 5, 2010 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Quality and Productivity
|
Abstract - #307386 |
Title:
|
Bayesian Methods for Supercomputer Reliability Data
|
Author(s):
|
Sarah Michalak*+ and Todd Graves and Lori Pritchett-Sheats
|
Companies:
|
Los Alamos National Laboratory and Los Alamos National Laboratory and Los Alamos National Laboratory
|
Address:
|
PO Box 1663, MS F600, Los Alamos, NM, 87545,
|
Keywords:
|
Bayesian Statistics ;
Reliability ;
High-Performance Computing ;
Failure Data
|
Abstract:
|
Efficient use of supercomputer resources requires job scheduling that reflects the reliability of the platform in question. This talk presents results of modeling failure data from a compute resource at Los Alamos National Laboratory, which was used for scientific computation. For each failure, the data include time to failure, number of nodes affected by the failure, the associated downtime, and whether the failure could have caused a user interrupt. A Bayesian model is used for the data. Specifically, heterogeneity in times to failure and downtimes are modeled for different failure types.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2010 program
|
2010 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.