Data Locality Aware Strategy for Two-Phase Collective I/O
Rosa Filgueira (University Carlos III)
David Singh (University Carlos III)
Juan Carlos Pichel (University Carlos III)
Florin Isaila (University Carlos III)
Jesus Carretero (University Carlos III)
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.
Parallel and Distributed Computing, Cluster Computing
Toulouse | France | 2008 | June | 24  25  26  27