Third International Workshop on
High-Level Parallel Programming Models and Supportive Environments
(HIPS'98)

held in conjunction with

IPPS/SPDP 1998
12th International Parallel Processing Symposium
& 9th Symposium on Parallel and Distributed Processing

March 30 - April 3, 1998
Orlando, Florida


IPPS/SPDP'98
HIPS'98
Workshop Organizer
Program Committee
Program
Authors' Instructions
Important Dates


HIPS'98

HIPS'98 is a full-day workshop to be held at the IPPS/SPDP 1998 focusing on high-level programming of networks of workstations and of massively-parallel machines. Its goal is to bring together researchers working in the areas of applications, language design, compilers, system architecture, and programming tools to discuss new developments in programming such systems.

Invited presentation

John Carter from the University of Utah, well known for his contributions in the field of distributed shared memory systems, will give an overview of the current status of programming massively parallel systems with global address space.

Background

With the advent of the de facto standards Parallel Virtual Machine (PVM) and Message Passing Interface (MPI), parallel programming using the message-passing style has reached a certain level of maturity. However, in terms of convenience and productivity, this parallel programming style is often considered to correspond to assembler-level programming of sequential computers.

One of the keys for a (commercial) breakthrough of parallel processing, therefore, are high-level programming models that allow to produce truly efficient code. Along this way, languages and packages have been established which are more convenient than explicit message passing and allow higher productivity in software development; examples are High Performance Fortran (HPF), thread packages for shared memory-based programming, and Shared Virtual Memory (SVM) environments.

Yet, current implementations of high-level programming models often suffer from low performance of the generated code, from the lack of corresponding high-level development tools, e.g. for performance analysis, and from restricted applicability, e.g. to the data parallel programming style. This situation requires strong research efforts in the design of parallel programming models and languages that are both at a high conceptual level and implemented efficiently, in the development of supportive tools, and in the integration of languages and tools into convenient programming environments. Hardware and operating system support for high-level programming, e.g. distributed shared memory and monitoring interfaces, are further areas of interest.

Workshop topics

This workshop provides a forum for researchers and commercial developers to meet and discuss the various hardware and software issues involved in the design and use of high-level programming models and supportive environments. Papers are invited in areas such as the following:

Papers should describe the interaction of high-level programming models with compilers, run time systems, and hardware support. Specialized papers on the lower implementation levels of programming models might fit also very well into other workshops, e.g. RTSPP; see http://www.ippsxx.org/ipps98/ipps98cfp.html.


IPPS/SPDP'98

In 1998, the Symposium on Parallel and Distributed Processing (SPDP) will join the International Parallel Processing Symposium (IPPS) to hold a combined event referred to as IPPS/SPDP 1998. It will be held March 30 - April 3, 1998 at the Delta Orlando Resort, Orlando, Florida, USA. With continued sponsorship from the Technical Committee on Parallel Processing, the symposium remains the committee's primary forum for engineers and scientists from around the world to present their latest research findings in the field. For detailed information please refer to WWW: http://www.ippsxx.org/ipps98/ipps98cfp.html.


Authors' Instructions

To submit an original research article, send an electronic version of your complete manuscript in postscript format to: hips98@fz-juelich.de. Please make sure that the postscript file is viewable using the "ghostview" tool. Papers must not exceed 17 double-spaced pages of text, including title, author(s), abstract, five key words, figures, tables, and references, and using 12-point type on 8.5x11-inch pages.

All manuscripts will be reviewed. Manuscripts must be received by November 1, 1997. Notification of review decisions will be mailed by December 20, 1997. Camera-ready papers are due January 31, 1998. The research articles will be published by IEEE CS Press. Proceedings will be available at HIPS'98 and through the publisher thereafter.

Please include your postal address, e-mail address, telephone and fax numbers with any submission.


Workshop Organizer

Michael Gerndt
Research Centre Jülich
Central Institute for Applied Mathematics
D-52425 Jülich, Germany
Email: m.gerndt@fz-juelich.de
Phone: +49-2461-616569
Fax: +49-2461 616656

Contact: hips98@fz-juelich.de


Program Committee

Arndt Bode, Technische Universität München, Germany
Helmar Burkhart, Universität Basel, Switzerland
John Carter, University of Utah, USA
Michel Cosnard, Ecole Normale Superieure de Lyon, France
Karsten Decker, Swiss Center for Scientific Computing, Switzerland
Dennis Gannon, Indiana University, USA
Michael Gerndt, Research Centre Jülich, Germany
Hermann Hellwagner, Technische Universität München, Germany
Francois Irigoin, Ecole des Mines de Paris, France
Vijay Karamcheti, University of Illinois at Urbana-Champaign, USA
Pete Keleher, University of Maryland, USA
Ulrich Kremer, Rutgers University, USA
Ron Perrott, Queens University Belfast, United Kingdom
Thierry Priol, INRIA, France
Klaus E. Schauser, University of California at Santa Barbara, USA
Domenico Talia, ISI-CNR, Italy
Hans P. Zima, University of Vienna, Austria


Program

on Monday, March 30, 1998

Session 1, 9:00 – 10:00: Invited Presentation

Distributed Shared Memory: Past, Present and Future

J. Carter

Session 2, 10:30 – 12:30: Distributed Shared Memory

Constructive and Adaptable Distributed Shared Memory

J. Bataller, J. Bernabeu-Auban

ViC*: A Compiler for Virtual-Memory C*

A. Colvin, Th. H. Cormen

Parallel and Distributed Programming with Pthreads and Rthreads

B. Dreier, M. Zahn, Th. Ungerer

Session 3, 14:00 – 16:00: Data Parallelism

Language Bindings for a Data-Parallel Runtime

B. Carpenter, G. Fox, X. Li, Y. Wen, G. Zhang

ZPL's WYSIWYG Performance Model

B.L. Chamberlain, S. Choi, E.CH. Lewis, C. Lin, L. Snyder, W.D. Weathersby

A Graph-Based Framework for the Definition of Tools Dealing with Sparse and Irregular Distributed Data Structures

S. Chaumette, J.-M. Lepine, F. Rubi

Session 4, 16:30 – 18:30: Implementation and Optimization Techniques

Implementing Automatic Coordination on Networks of Workstations

Ch. Weiss, J. Knopp, H. Hellwagner

Improving Performance of Multi-Dimensional Array Redistribution on Distributed Memory Machines

M. Guo, Y. Yamashita, I. Nakata

Further Results for Improving Loop Interchange in Non-Adjacent and Imperfectly Nested Loops

T.-Ch. Huang, Ch.-M. Yang

 


Important Dates

November

1,

1997:

Paper Submission Deadline

December

20,

1997:

Paper Review Decisions Mailed

January

31,

1998:

Camera-ready Manuscript Due


Forschungszentrum Jülich, ZAM, hips98@fz-juelich.de
10-Mar-1998
URL: <http://www.kfa-juelich.de/hips98/hips98.html>