Fault resilience of the algebraic multi-grid solver
Authors:
Open Access
- 25 June 2012
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 91-100
Abstract
As HPC system sizes grow to millions of cores and chip feature sizes continue to decrease, HPC applications become increasingly exposed to transient hardware faults. These faults can cause aborts and performance degradation. Most importantly, they can corrupt results. Thus, we must evaluate the fault vulnerability of key HPC algorithms to develop cost-effective techniques to improve application resilience. We present an approach that analyzes the vulnerability of applications to faults, systematically reduces it by protecting the most vulnerable components and predicts application vulnerability at large scales. Weinitially focus on sparse scientific applications and apply our approachin this paper to the Algebraic Multi Grid (AMG) algorithm. We empirically analyze AMG's vulnerability to hardware faults in both sequential and parallel (hybrid MPI/OpenMP) executions on up to 1,600 cores and propose and evaluate the use of targeted pointer replication to reduce it. Our techniques increase AMG's resilience to transient hardware faults by 50-80% and improve its scalability on faulty computational environments by 35%. Further, we show how to model AMG's scalability in fault-prone environments to predict execution times of large-scale runs accurately.Keywords
This publication has 18 references indexed in Scilit:
- Patterns and statistical analysis for understanding reduced resource computing2010
- Relax2010
- Extending stability beyond CPU millennium2007
- Distance‐two interpolation for parallel algebraic multigridNumerical Linear Algebra with Applications, 2007
- An algorithm-based error detection scheme for the multigrid methodIEEE Transactions on Computers, 2003
- Tests and tolerances for high-performance software-implemented fault detectionIEEE Transactions on Computers, 2003
- Inexact Preconditioned Conjugate Gradient Method with Inner-Outer IterationSIAM Journal on Scientific Computing, 1999
- Algorithm-based error-detection schemes for iterative solution of partial differential equationsIEEE Transactions on Computers, 1996
- A linear algebraic model of algorithm-based fault toleranceIEEE Transactions on Computers, 1988
- GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear SystemsSIAM Journal on Scientific and Statistical Computing, 1986