A Model-Based Case for Redundant Computation
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- IBM Research, Dublin (Ireland)
Despite its seemingly nonsensical cost, we show through modeling and simulation that redundant computation merits full consideration as a resilience strategy for next-generation systems. Without revolutionary breakthroughs in failure rates, part counts, or stable-storage bandwidths, it has been shown that the utility of Exascale systems will be crushed by the overheads of traditional checkpoint/restart mechanisms. Alternate resilience strategies must be considered, and redundancy is a proven unrivaled approach in many domains. We develop a distribution-independent model for job interrupts on systems of arbitrary redundancy, adapt Daly’s model for total application runtime, and find that his estimate for optimal checkpoint interval remains valid for redundant systems. We then identify conditions where redundancy is more cost effective than non-redundancy. These are done in the context of the number one supercomputers of the last decade, showing that thorough consideration of redundant computation is timely - if not overdue.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1113872
- Report Number(s):
- SAND2011--5909; 464290
- Country of Publication:
- United States
- Language:
- English
Similar Records
Redundant computing for exascale systems.
Combining Partial Redundancy and Checkpointing for HPC
Implementing Software Resiliency in HPX for Extreme Scale Computing
Technical Report
·
Tue Nov 30 23:00:00 EST 2010
·
OSTI ID:1011662
Combining Partial Redundancy and Checkpointing for HPC
Conference
·
Sat Dec 31 23:00:00 EST 2011
·
OSTI ID:1081906
Implementing Software Resiliency in HPX for Extreme Scale Computing
Technical Report
·
Wed Apr 15 00:00:00 EDT 2020
·
OSTI ID:1614897