OmpiJava: a tool for development of high-performance reasoning applications for the semantic web

Abstract

The World Wide Web has naturally been evolving towards processing extra-large data volumes, such as collected by Linked Life Data or Open PHACTS repositories, capable of hosting billions of information entities (e.g., RDF triples used in Semantic Web) and beyond. In view of the explosive data growth along with excessive QoS requirements on scalability and processing time constraints, the Web is expected to dominate the data-centric computing already in the next decade. On the other hand, most of the current HPC infrastructures, both academic and industrial, do not support parallel Web applications, e.g., developed in the Hadoop framework, due to their service-oriented implementation in the Java programming language, which is (and will surely remain) prevalent for the Web programming. As a reaction to novel challenges of promoting data-centric supercomputing to the Web, we present a solution that introduces the Message Passing Interface (MPI) bindings to Java, seamlessly integrated in one of the most popular current MPI implementations - Open MPI. Our implementation enables Java-based Semantic Web applications to be successfully ported to the most of modern HPC systems. We also discuss the design features of Open MPI that enable the proliferation of MPI into Java applications. Finally, we present a pilot Semantic Statistics scenario implemented with MPI, Random Indexing, and discuss future work in terms of promising Semantic Web applications, such as Reasoning.