This text describes the machine model designed to support parallel interface, the design of the Kleng language, the design and implementation of the parallel interface engine, the programming tools, the runtime system, and some evaluation results. The architecture of the PIE 64 is tuned specially to support parallel inference. The compiler and runtime systems proposed here are designed to reduce the overhead that inevitably incurrs when using fine granularity processing.
This volume contains the proceedings of an international workshop on parallelism in inference systems held in Germany in December 1990. The topicof the workshop is still rather young and several papers in the book are overview articles intended to provide a first orientation toward some of the more intensively investigated subtopics. The main part of the book is a compilation of research papers on parallelization in special domains ofinference such as rewriting, automatic reasoning, logic programming, andconnectionist inference. Appended to the book is a collection of short project summaries received in response to a worldwide email call. The book is intended primarily for researchers working on inference systems who are interested in parallelizing their systems.
This volume contains most of the papers presented at the 6th Logic Programming Conference held in Tokyo, June 22-24, 1987. It is the successor of Lecture Notes in Computer Science volumes 221 and 264. The contents cover foundations, programming, architecture and applications. Topics of particular interest are constraint logic programming and parallelism. The effort to apply logic programming to large-scale realistic problems is another important subject of these proceedings.
It has been widely recognized that artificial intelligence computations offer large potential for distributed and parallel processing. Unfortunately, not much is known about designing parallel AI algorithms and efficient, easy-to-use parallel computer architectures for AI applications. The field of parallel computation and computers for AI is in its infancy, but some significant ideas have appeared and initial practical experience has become available. The purpose of this book has been to collect in one volume contributions from several leading researchers and pioneers of AI that represent a sample of these ideas and experiences. This sample does not include all schools of thought nor contributions from all leading researchers, but it covers a relatively wide variety of views and topics and in this sense can be helpful in assessing the state ofthe art. We hope that the book will serve, at least, as a pointer to more specialized literature and that it will stimulate interest in the area of parallel AI processing. It has been a great pleasure and a privilege to cooperate with all contributors to this volume. They have my warmest thanks and gratitude. Mrs. Birgitta Knapp has assisted me in the editorial task and demonstrated a great deal of skill and patience. Janusz S. Kowalik vii INTRODUCTION Artificial intelligence (AI) computer programs can be very time-consuming.
This constitutes the final report of work performed under AFOSR grant number 90-0027 to investigate parallel problem solving and deductive databases. Under the grant experiments were performed on the PRISM parallel inference system on the BBN Butterfly. The experiments evaluated alternative message passing strategies for distributing tasks to processors at run-time. Several enhancements were made to PRISM during the grant period. These are: a new inference engine was implemented which provides more efficient support for the full control language of PRISM; and a stack based inference engine was implemented which provides efficient support for the use of limited set of control strategies. Simulation studies were performed which evaluate alternative methods for scheduling tasks on parallel architectures. Two methods were examined which allow the OR-parallel execution of logic programs with no communication overhead. A study was performed evaluating two alternative methods for incorporating integrity constraints into query processing in PRISM. In the first method, separate constraint processors are introduced which check constraints at run-time. In the second method, constraints are incorporated through compile-time transformations. The study indicates that constraints are useful inquiry processing and that the compile-time methodology results in more efficient performance than checking constraints at run-time. In addition to the above, work continued in the area of informative answers to queries in deductive databases.
This volume contains the papers presented, and subsequently submitted for publication, at the 5th Logic Programming Conference, held June 23-26, 1986 in Tokyo. Topics covered include Prolog machine architecture, Prolog processors, variations of Prolog language, and applications of Prolog to natural language understanding, and expert systems. Most of the works reported in the volume are related to the Japanese Fifth Generation Computer Project allowing readers to compare results from this project with those from similar projects currently being conducted in other countries.
Parallel and distributed computing are becoming increasingly important as cost-effective ways to achieve high computational performance. Symbolic computations are notable for their use of irregular data structures and hence parallel symbolic computing has its own distinctive set of technical challenges. The papers in this book are based on presentations made at a workshop at MIT in October 1992. They present results in a wide range of areas including: speculative computation, scheduling techniques, program development tools and environments, programming languages and systems, models of concurrency and distribution, parallel computer architecture, and symbolic applications.
The 2004 International Conference on Parallel and Distributed Computing, - plications and Technologies (PDCAT 2004) was the ?fth annual conference, and was held at the Marina Mandarin Hotel, Singapore on December 8–10, 2004. Since the inaugural PDCAT held in Hong Kong in 2000, the conference has - come a major forum for scientists, engineers, and practitioners throughout the world to present the latest research, results, ideas, developments, techniques, and applications in all areas of parallel and distributed computing. The technical program was comprehensive and featured keynote speeches, te- nical paper presentations, and exhibitions showcased by industry vendors. The technical program committee was overwhelmed with submissions of papers for presentation, from countries worldwide. We received 242 papers and after - viewing them, based on stringent selection criteria, we accepted 173 papers. The papers in the proceedings focus on parallel and distributed computing viewed from the three perspectives of networking and architectures, software systems and technologies, and algorithms and applications. We acknowledge the great contribution from all of our local and international committee members and - perreviewerswhodevotedtheirtimeinthereviewprocessandprovidedvaluable feedback for the authors. PDCAT 2004 could never have been successful without the support and ass- tance of several institutions and many people. We sincerely appreciate the s- port from the National Grid O?ce and IEEE, Singapore for technical co-sponsorship.The?nancialsponsorshipsfromtheindustrialsponsors,Hewlett- Packard Singapore; IBM Singapore; Sun Microsystems; SANDZ Solutions; S- icon Graphics, and Advanced Digital Information Corporation, are gratefully acknowledged.
