Optimizing MPI Runtime Parameter Settings by Using Machine Learning

Authors:
Simone Pellegrini;Jie Wang;Thomas Fahringer;Hans Moritsch
Affiliations:
Distributed and Parallel Systems Group, University of Innsbruck, Innsbruck, Austria 6020;Distributed and Parallel Systems Group, University of Innsbruck, Innsbruck, Austria 6020;Distributed and Parallel Systems Group, University of Innsbruck, Innsbruck, Austria 6020;Distributed and Parallel Systems Group, University of Innsbruck, Innsbruck, Austria 6020
Venue:
Proceedings of the 16th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Year:
2009

Citing 6
Cited 3

Neural networks for pattern recognition

Neural networks for pattern recognition
STAR-MPI: self tuned adaptive routines for MPI collective operations

Proceedings of the 20th annual international conference on Supercomputing
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
A Tool for Optimizing Runtime Parameters of Open MPI

Proceedings of the 15th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Designing an Efficient Kernel-Level and User-Level Hybrid Approach for MPI Intra-Node Communication on Multi-Core Systems

ICPP '08 Proceedings of the 2008 37th International Conference on Parallel Processing
An approach to performance prediction for parallel applications

Euro-Par'05 Proceedings of the 11th international Euro-Par conference on Parallel Processing

Adaptive MPI multirail tuning for non-uniform input/output access

EuroMPI'10 Proceedings of the 17th European MPI users' group meeting conference on Recent advances in the message passing interface
Methodology for MPI applications autotuning

Proceedings of the 20th European MPI Users' Group Meeting
Tools for machine-learning-based empirical autotuning and specialization

International Journal of High Performance Computing Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Manually tuning MPI runtime parameters is a practice commonly employed to optimise MPI application performance on a specific architecture. However, the best setting for these parameters not only depends on the underlying system but also on the application itself and its input data. This paper introduces a novel approach based on machine learning techniques to estimate the values of MPI runtime parameters that tries to achieve optimal speedup for a target architecture and any unseen input program. The effectiveness of our optimization tool is evaluated against two benchmarks executed on a multi-core SMP machine.