Implementing generalized deep-copy in MPI

Joss Whittle, Rita Borgo and Mark W. Jones

Abstract

In this paper we introduce a framework for implementing deep copy on top of MPI. The process is initiated by passing just the root object of the dynamic data structure. Our framework takes care of all pointer traversal, communication, copying and reconstruction on receiving nodes. The benefit of our approach is that MPI users can deep copy complex dynamic data structures without the need to write bespoke communication or serialize / deserialize methods for each object. These methods can present a challenging implementation problem that can quickly become unwieldy to maintain when working with complex structured data. This paper demonstrates our generic implementation, which encapsulates both approaches. We analyze the approach with a variety of structures (trees, graphs (including complete graphs) and rings) and demonstrate that it performs comparably to hand written implementations, using a vastly simplified programming interface. We make the source code available completely as a convenient header file.

Source Materials

PDF iconPaper

DOI

10.7717/peerj-cs.95
https://dx.doi.org/10.7717/peerj-cs.95

Citation

J. Whittle, R. Borgo and M. W. Jones, Implementing generalized deep-copy in MPI, PeerJ Computer Science 2:e96, Nov. 2016. https://dx.doi.org/10.7717/peerj-cs.95

Bibtex

@Article{Jones-MEL2016,
author="Whittle, Joss
and Borgo, Rita
and Jones, Mark W.",
title="Implementing generalized deep-copy in MPI",
journal="PeerJ",
year="2016",
volume="2",
number="95",
doi="10.7717/peerj-cs.95",
url="https://dx.doi.org/10.7717/peerj-cs.95"
}