Data Locality Aware Strategy for Two-Phase Collective I/O

• Published in: High Performance Computing for Computational Science - VECPAR 2008 pp. 137 - 149
• Main Authors: Filgueira, Rosa, Singh, David E., Pichel, Juan C., Isaila, Florin, Carretero, Jesús
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2008
• Series: Lecture Notes in Computer Science
• Subjects: Collective Operation; Communication Operation; Cooperative Cache; Hungarian Algorithm; Linear Assignment Problem
• ISBN: 3540928588; 9783540928584
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-540-92859-1_14

This paper presents Locality-Aware Two-Phase (LATP) I/O, an optimization of the Two-Phase collective I/O technique from ROMIO, the most popular MPI-IO implementation. In order to increase the locality of the file accesses, LATP employs the Linear Assignment Problem (LAP) for finding an optimal distribution of data to processes, an aspect that is not considered in the original technique. This assignment is based on the local data that each process stores and has as main purpose the reduction of the number of communication involved in the I/O collective operation and, therefore, the improvement of the global execution time. Compared with Two-Phase I/O, LATP I/O obtains important improvements in most of the considered scenarios.