Concurrency and Computation:Practice and Experience

Here are instructions for Java Grande 2000 Special Issue. This issue is being reviewed now

This homepage supports referees.

Standard Referee Form

Journal Vision

Below you will find active abstracts.

Please send email to Geoffrey Fox, fox@csit.fsu.edu, if you wish to referee any article.

We will send you link to full text online.

Articles under Consideration for Journal

• C467: VGDS: A Distributed Data Structure Framework for Scientific Computation
  • Abstract: This paper gives an overview of the VGDS (Virtual Global Data Structure) project. The VGDS effort focuses on developing an integrated, distributed environment that allows fast prototyping of a diverse set of simulation problems in irregular scientific and engineering domains, focusing on computations with irregular and adaptive structures. The framework defines two base libraries: unstructured mesh and adaptive tree, that capture major data structures involved inirregular scientic computation. The framework defines multiple layers of class libraries which work together to provide data-parallel representations to application developers while encapsulate parallel implementation details into lower layers of the framework. The layered approach enables easy extension of the base libraries to a variety of application-specific data structures. Experimental results on a network of workstations is reported.
  • Pangfeng Liu, Jan-Jan Wu
  • mailto:wuj@iis.sinica.edu.twmailto:pangfeng@cs.ccu.edu.tw
  • Submitted April 21, 2000
  • Comments To Authors October 1 2000
• C468: cJVM: A Cluster JVM Architecture for Single System Image
  • Abstract:cJVM is a Java Virtual Machine (JVM) which provides a single system image of a traditional JVM while executing in a distributed fashion on the nodes of a cluster. cJVM virtualizes the cluster, supporting any pure Java application without requiring that applications be tailored specifically for it. The aim of cJVM is to obtain improved scalability for a class of Java Server Applications by distributing the application's work among the cluster's computing resources. cJVM is based on a novel object model which distinguishes between an application's view of an object (e.g., every object is a unique data structure) and its implementation (e.g., objects may have consistent replications on different nodes). This enables us to exploit knowledge on the usage of individual objects to improve performance (e.g., using object replications to increase locality of access to objects). Currently, we have already completed a prototype which runs pure Java applications on a cluster of NT workstations connected via a Myrinet fast switch. The prototype provides a single system image to applications, distributing the application's threads and objects over the cluster. We have used cJVM to run without change a real Java Server Application containing over 10K loc and achieve high scalability for it on a cluster. We also achieved linear speedup for another application with a large number of independent threads. This paper discusses cJVM's architecture and implementation. It focuses on achieving a single system image for a traditional JVM on a cluster while describing in short how we aim at obtaining scalability.
  • Yariv Aridor, Michael Factor and Avi Teperman
  • mailto:teperman@il.ibm.com
  • Submitted May 1, 2000
  • Comments To Authors October 1 2000
• C474: Parallel solution of rotating flows in cavities
  • Abstract:In this paper, we investigate the parallel solution to the rotating internal flow problems, using the Navier-Stokes equations as proposed in [16] and [15]. A Runge-Kutta time-stepping scheme was applied to the equations and both sequential and message- passing implementations were developed, the latter using MPI , and were tested on an SGI Origin200 distributed, global shared memory parallel computer. The results show that our approach to parallelize the sequential implementation requires little effort whilst providing good results even for medium-sized problems, on this particular computer.
  • Rudnei Dias da Cunha and Alvaro Luiz de Bortoli
  • mailto:rudnei@mat.ufrgs.br
  • Submitted May 14, 2000
  • Comments To Authors October 1 2000
• C475: Analysis and Measurement of the Effect of Kernel Locks in SMP Systems
  • Abstract:This paper reports the use of case studies to evaluate the performance degradation caused by the kernel-level lock. We define the lock ratio as a ratio of the execution time for critical sections to the total execution time of a parallel program. The kernel-level lock ratio determines how effective programs work on Symmetric MultiProcessor systems. We have measured the lock ratios and the performance of three types of parallel programs on SMP systems with Linux 2.0: matrix multiplication, parallel make, and WWW server programs. Experimental results show that the higher the lock ratio of parallel programs, the worse their performance becomes. keywords: SMP Systems, Operating Systems, Parallel Programs, Per- formance Evaluation, Kernel Lock
  • Akihiro Kaieda and Yasuichi Nakayama; Atsuhiro Tanaka, Takashi Horikawa, Toshiyasu Kurasugi and Issei Kino
  • mailto:yasu@cs.uec.ac.jp
  • Submitted May 24, 2000
  • Comments To Authors October 1 2000
• C476: Effective Multicast Programming in Large Scale Distributed Systems:The DACE Approach
  • Abstract:Many distributed applications have a strong requirement for efficient dissemination of large amounts of information to widely spread consumers in large networks.These include applications in e-commerce and telecommunication.Publish/subscribe is considered one of the most important interaction styles to model communication at large scale.Producers publish information for a topic and consumers subscribe to the topics they wish to be informed of.The decoupling of producers and consumers in time and in space makes the publish/subscribe paradigm very attractive for large scale distribution,especially in environments like the Internet. This paper describes the architecture and implementation of DACE (Distributed Asynchronous Computing Environment),a framework for publish/subscribe communication based on an object- oriented programming abstraction in the form of Distributed Asynchronous Collection (DAC).DACs capture the different variations of publish/subscribe,without blurring their respective advantages. The architecture we present is tolerant to network partitions and crash failures.The underlying model is based on the notion of Topic Membership:a weak membership for the parties involved in a topic.We present how Topic Membership enables the realization of a robust and efficient reliable multicast for large scale.The protocol ensures that,inside a topic,even a subscriber that is temporarily partitioned away eventually receives a published message.
  • Romain Boichat, Patrick Th. Eugster, Rachid Guerraoui, Joe Sventek
  • Swiss Federal Institute of Technology, Lausanne and Agilent Laboratories Scotland, Edinburgh
  • Email:Patrick.Eugster@lsesun6.epfl.ch
  • Submitted July17, 2000
• C486: Parallel Versions of Stone’s Strongly Implicit (SIP) Algorithm
  • Abstract:In this paper, we describe various methods of deriving a parallel version of Stone’s Strongly Implicit Procedure (SIP) for solving sparse linear equations arising from finite difference approximation to partial differential equations (PDE’s). Sequential versions of this algorithm have been very successful in solving semi-conductor, heat conduction and flow simulation problems and an efficient parallel version would enable much larger simulations to be run. An initial investigation of various parallelising strategies was undertaken using a version of High Performance Fortran (HPF) and the best methods were reprogrammed using the MPI message passing libraries for increased efficiency. Early attempts concentrated on developing a parallel version of the characteristic wavefront computation pattern of the existing sequential SIP code. However, a red-black ordering of grid points, similar to that used in parallel versions of the Gauss-Seidel algorithm, is shown to be far more efficient. The results of both the wavefront and red-black MPI based algorithms are reported for various size problems and number of processors on a sixteen node IBM SP2.
  • J.S. Reeve, A.D. Scurr and J.H. Merlin
  • Department of Electronics and Computer Science, University of Southampton
  • Email:jsr@ecs.soton.ac.uk
  • Submitted August 24, 2000
• C487: Real-time Multi-spectral Image Fusion
  • Abstract:This paper describes a novel real-time multi-spectral imaging capability for surveillance applications. The capability combines a new high-performance multi-spectral camera system with a distributed algorithm that computes a spectral-screening Principal Component Transform (PCT). The camera system uses a novel filter wheel design together with a high-bandwidth CCD camera to allow image cubes to be delivered at 110 frames per second with spectral resolution between 400 and 1000 nm. The filters used in a particular application are selected to highlight a particular object based on its spectral signature. The distributed algorithm allows image streams from a dispersed collection of cameras to be disseminated, viewed, and interpreted by a distributed group of analysts in real-time. It operates on networks of commercial-off-the-shelf multiprocessors connected with high-performance (e.g. gigabit) networking, taking advantage of multi-threading where appropriate. The algorithm uses a concurrent formulation of the PCT to de-correlate and compress a multi-spectral image cube. Spectral screening is used to give features that occur infrequently (e.g. mechanized vehicles in a forest) equal importance to those that occur frequently (e.g. trees in the forest). A human-centered color-mapping scheme is used to maximize the impact of spectral contrast on the human visual system. To demonstrate the efficacy of the multi-spectral system, plant-life scenes with both real and artificial foliage are used. These scenes demonstrate the systems ability to distinguish elements of a scene, based on spectral contrast, that cannot be distinguished with the naked eye. The capability is evaluated in terms of visual performance, scalability, and real-time throughput. Our previous work on predictive analytical modeling is extended to answer practical design questions such as “For a specified cost, what system can should be constructed and what performance will it attain?”
  • Tiranee Achalakul, Stephen Taylor
  • Department Computer Science, Syracuse University
  • Email:tachalak@syr.edu
  • Submitted September 14, 2000
• C488: Efficient Communication Using Message Prediction for Cluster of Multiprocessors
  • Abstract:With the increasing uniprocessor and SMP computation power available today,interprocessor communication has become an important factor that limits the performance of cluster of workstations.Many factors including communication hardware overhead,communication software overhead,and the user environment overhead (multithreading,multiuser) affect the performance of the communication subsystems in such systems. A significant portion of the software communication overhead belongs to a number of message copying.Ideally,it is desirable to have a true zero-copy protocol where the message is moved directly from the send buffer in its user space to the receive buffer in the destination without any intermediate buffering.However due to the fact that message-passing applications at the send side do not know the final receive buffer addresses,early arrival messages have to be buffered at a temporary area.In this paper,we show that there is a message reception communication locality in message-passing applications.We have utilized this communication locality and devised different message predictors at the receiver sides of communications.In essence,these message predictors can be efficiently used to drain the network and cache the incoming messages even if the corresponding receive calls have not been posted yet.The performance of these predictors,in terms of hit ratio,on some parallel applications are quite promising and suggest that prediction has the potential to eliminate most of the remaining message copies .We also show that the proposed predictors do not have sensitivity to the starting message reception call,and that they perform better than (or at least equal to) our previously proposed predictors in [3 ].
  • Ahmad Afsahi, Nikitas J.Dimopoulos
  • Queens University and University of Victoria, Canada
  • Email:ahmad@ee.queensu.ca
  • Submitted September 14, 2000