Non-blocking java communications support on clusters
TL;DR: A non-blocking communication library to efficiently support specialized communication hardware and provides the basis for a Java Message-passing library to be implemented on top of it.
read more
Abstract: This paper presents communication strategies for supporting efficient non-blocking Java communication on clusters. The communication performance is critical for the overall cluster performance. It is possible to use non-blocking communications to reduce the communication overhead. Previous efforts to efficiently support non-blocking communication in Java have led to the introduction of the Java NIO API. Although the Java NIO package addresses scalability issues by providing select() like functionality, it lacks support for high speed interconnects. To solve this issue, this paper introduces a non-blocking communication library to efficiently support specialized communication hardware. This library focuses on reducing the startup communication time, avoiding unnecessary copying, and overlapping computation with communication. This project provides the basis for a Java Message-passing library to be implemented on top of it. Towards the end, this paper evaluates the proposed approach on a Scalable Coherent Interface (SCI) and Gigabit Ethernet (GbE) testbed cluster. Experimental results show that the proposed library reduces the communication overhead and increases computation and communication overlapping.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Dissertation
Design of efficient Java communications for high performance computing
Guillermo L. Taboada
- 01 Jan 2009
TL;DR: The use of Java for HPC is feasible and even advisable when looking for productive development, provided that efficient communication middleware is made available, such as the projects presented in this Thesis.
References
Combining measurement and stochastic modelling to enhance scheduling decisions for a parallel mean value analysis algorithm
Gagarine Yaikhom,Murray Cole,Stephen Gilmore +2 more
- 28 May 2006
TL;DR: The high-level modelling language PEPA is applied to the performance analysis of a parallel program with a pipeline skeleton which computes the Mean Value Analysis (MVA) algorithm for queueing networks.
MPIJAVA: An Object-Oriented JAVA Interface to MPI
Mark Baker,Bryan Carpenter,Geoffrey C. Fox,Sung Hoon Ko,Sang Lim +4 more
- 12 Apr 1999
TL;DR: This paper describes and discusses the syntax, functionality and performance of mpiJava, an object-oriented Java interface to MPI, and discusses some performance measurements made of communications bandwidth and latency to compare mpi Java on these systems.
An Approach to Asynchronous Object-Oriented Parallel and Distributed Computing on Wide-Area Systems
Michele Di Santo,Franco Frattolillo,Wilma Russo,Eugenio Zimeo +3 more
- 01 May 2000
TL;DR: In this paper, the authors present a model for object-oriented parallel programming in both local and wide area contexts and its implementation as a Java package, which allows programmers to express asynchronous, complex interactions, so overcoming some of the limitations of the models based on message passing and RPC.
141
•Proceedings Article
High-performance local area communication with fast sockets
Steven H. Rodrigues,Thomas Anderson,David E. Culler +2 more
- 06 Jan 1997
TL;DR: Fast Sockets is developed, a local-area communication layer that utilizes a high-performance protocol and exports the Berkeley Sockets programming interface, and transparently reverts to standard TCP/IP protocols for wide- area communication.
140
Parallel and distributed processing
Alois Goller,Ian Glendinning,Dieter Bachmann,Rainer Kalliany +3 more
- 01 May 2001
TL;DR: In order to increase computing times of large image data considerably, algorithms or jobs may be split into packages that may be processed in parallel.
125