@inproceedings{b9d2c0d8530f44db948d6f7074521e6e,
title = "ACCT: Automatic collective communications tuning",
abstract = "The performance of the MPI{\textquoteright}s collective communications is critical in most MPI-based applications. A general algorithm for a given collective communication operation may not give good performance on all systems due to the differences in architectures, network parameters and the buffering scheme of the underlying MPI implementation. In this paper, we discuss an approach in which the collective communications are tuned for any given system by conducting a series of experiments on the system. We also discuss a dynamic topology method that uses the tuned static topology shape, but re-orders the logical addresses to compensate for changing run time variations. A series of experiments were conducted comparing our tuned MPI_Bcast to various native vendor MPI implementations. The results obtained were encouraging, and show that our implementations of collective algorithms can significantly improve the performance of current MPI implementations.",
author = "Fagg, {Graham E.} and Vadhiyar, {Sathish S.} and Dongarra, {Jack J.}",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2000.; 7th European Parallel Virtual Machine and Message Passing Interface Users{\textquoteright} Group Meeting, PVM/MPI 2000 ; Conference date: 10-09-2000 Through 13-09-2000",
year = "2000",
doi = "10.1007/3-540-45255-9_48",
language = "English",
isbn = "3540410104",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "354--361",
editor = "Jack Dongarra and Peter Kacsuk and Norbert Podhorszki",
booktitle = "Recent Advances in Parallel Virtual Machine and Message Passing Interface - 7th European PVM/MPI Users{\textquoteright} Group Meeting, Proceedings",
}