Home // International Journal On Advances in Software, volume 6, numbers 1 and 2, 2013 // View article
Authors:
Alexey Cheptsov
Bastian Koller
Keywords: High Performance Computing, Big Data, Semantic Web, Performance, Scalability, Message-Passing Interface, Open MPI
Abstract:
The age of Big Data introduces a variety of challenges in how to store, access, process, and stream massive amounts of structured and unstructured data effectively. Among those domains that are impacted by the Big Data problem at most, the Semantic Web holds a leading position. By current estimates, the volume of Semantic Web data is exceeding the order of magnitude of billions of triples. Using High Performance Computing infrastructures is essential in dealing with these massive data volumes. Unfortunately, the most Semantic Web applications are developed in Java language, which makes them incompatible with the traditional high performance computing software solutions, which are tailored for compiled codes developed in C and Fortran languages. The known attempts to port existing parallelization frameworks, such as the Message-Passing Interface, to the Java platform have proved either a poor efficiency in terms of performance and scalability, or a limited usability due to a considerable configuration and installation overhead. We present an efficient porting of Java bindings based on Open MPI - one of the most popular Message-Passing Interface implementations for the traditional (C, C++, and Fortran) supercomputing applications.
Pages: 45 to 55
Copyright: Copyright (c) to authors, 2013. Used with permission.
Publication date: June 30, 2013
Published in: journal
ISSN: 1942-2628