Paper Info
Title
Automatic tuning of MPI runtime parameter settings by using machine learning
Abstract
MPI implementations provide several hundred runtime parameters that can be tuned for performance improvement. The ideal parameter setting does not only depend on the target multiprocessor architecture but also on the application, its problem and communicator size. This paper presents ATune, an automatic performance tuning tool that uses machine learning techniques to determine the program-specific optimal settings for a subset of the Open MPI's runtime parameters. ATune learns the behaviour of a target system by means of a training phase where several MPI benchmarks and MPI applications are run on a target architecture for varying problem and communicator sizes. For new input programs, only one run is required in order for ATune to deliver a prediction of the optimal runtime parameters values. Experiments based on the NAS Parallel Benchmarks performed on a cluster of SMP machines are shown that demonstrate the effectiveness of ATune. For these experiments, ATune derives MPI runtime parameter settings that are on average within 4% of the maximum performance achievable on the target system resulting in a performance gain of up to 18% with respect to the default parameter setting.
Year
DOI
Venue
2010
10.1145/1787275.1787310
Conf. Computing Frontiers
Keywords
Field
DocType
open mpi,mpi runtime parameter setting,machine learning,communicator size,target system,automatic tuning,mpi benchmarks,mpi implementation,mpi application,maximum performance,hundred runtime parameter,automatic performance,tuning
Multiprocessor architecture,Architecture,Computer science,Parallel computing,Real-time computing,Implementation,Automatic tuning,Artificial intelligence,Performance tuning,Machine learning,Performance improvement
Conference
Citations 
PageRank 
References 
6
0.50
2
Authors
4
Name
Order
Citations
PageRank
Simone Pellegrini1726.09
Thomas Fahringer22847254.09
Herbert Jordan37011.83
Hans Moritsch4506.78