Collective communications for scalable programming

Authors:
Sang Boem Lim;Bryan Carpenter;Geoffrey Fox;Han-Ku Lee
Affiliations:
Korea Institute of Science and Technology Information (KISTI), Daejeon, Korea;OMII, University of Southampton, Southampton, UK;Pervasive Technology Labs at Indiana University, Bloomington, IN;School of Internet and Multimedia Engineering, Konkuk University, Seoul, Korea
Venue:
ISPA'05 Proceedings of the Third international conference on Parallel and Distributed Processing and Applications
Year:
2005

Citing 7
Cited 2

Common runtime support for high-performance parallel languages

Proceedings of the 1993 ACM/IEEE conference on Supercomputing
A multigrid tutorial: second edition

A multigrid tutorial: second edition
Java Language Specification, Second Edition: The Java Series

Java Language Specification, Second Edition: The Java Series
An Integrated Runtime and Compile-Time Approach for Parallelizing Structured and Block Structured Applications

IEEE Transactions on Parallel and Distributed Systems
PCRC-based HPF Compilation

LCPC '97 Proceedings of the 10th International Workshop on Languages and Compilers for Parallel Computing
Towards efficient compilation of the hpjava language for high performance computing

Towards efficient compilation of the hpjava language for high performance computing
Jade: a parallel message-driven java

ICCS'03 Proceedings of the 2003 international conference on Computational science: PartIII

APJava: an aspect-oriented parallel programming model in Java

Proceedings of the 2009 International Conference on Hybrid Information Technology
Design of efficient Java message-passing collectives on multi-core clusters

The Journal of Supercomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

HPJava is an environment for scientific and parallel programming using Java. It is based on an extended version of the Java language. One feature that HPJava adds to Java is a multi-dimensional array, or multiarray, with properties similar to the arrays of Fortran. We are using Adlib as our high-level collective communication library. Adlib was originally developed using C++ by the Parallel Compiler Runtime Consortium (PCRC). Many functionalities of this high-level communication library is following its predecessor. However, many design issues are reconsidered and re-implemented according to Java environment. Detailed functionalities and implementation issues of this collective library will be described.