The Community for Technology Leaders
2013 42nd International Conference on Parallel Processing (1993)
Syracuse University
Aug. 16, 1993 to Aug. 20, 1993
ISBN: 0-8493-8983-6
TABLE OF CONTENTS
Introduction

Preface (PDF)

pp. viii
SESSION 1B:MODELSPARADIGM

Using Synthetic-Perturbation Techniques for Tuning Shared Memory Programs (Abstract)

Raghu Kacker , National Institute of Standards and Technilogy, Maryland
Joseph Jaja , National Institute of Standards and Technilogy, Maryland
Gordon Lyon , National Institute of Standards and Technilogy, Maryland
Robert Snelick , National Institute of Standards and Technilogy, Maryland
pp. 2-10

Comparing Data-Parallel and Message-Passing Paradigms (Abstract)

Alexander C. Klaiber , University of Washington
James L. Frankel , Thinking Machine Corporation, MA
pp. 11-20

Function-Parallel Computation in a Data-Parallel Environment (Abstract)

Anthony P. Reeves , Cornell University
Alex L. Cheung , Sandia National Laboratories
pp. 21-24
SESSION 2B: COMPILER

Automating Parallelism of Regular Computations for Distributed-Memory Multicomputers in the Paradigm Compiler (Abstract)

Ernesto Su , University of Illinois at Urbana-Champaign
Prithviraj Banerjee , University of Illinois at Urbana-Champaign
Daniel J. Palerrno , University of Illinois at Urbana-Champaign
pp. 30-38

Compilation Techniques for Optimizing Communication on Distributed-Memory Systems (Abstract)

Chun Gong , University of Pittsburgh
Rajiv Gupta , University of Pittsburgh
Rami Melhem , University of Pittsburgh
pp. 39-46

Meta-State Conversion (Abstract)

G. Krishnamurthy , Purdue University
H.G. Dietz , Purdue University
pp. 47-56
SESSION 3B:TOOLS

A Unified Model for Concurrent Debugging (Abstract)

J. C. Browne , University of Texas at Austin
S. I. Hyder , University of Texas at Austin
J. F. Werth , University of Texas at Austin
pp. 58-67

PARSA: A Parallel Program Scheduling and Assessment Environment (Abstract)

Krishna Kavi , University of Texas at Arlington
A.R. Hurson , Pennsylvania State University
Prasenjit Biswas , Cyrix Corporation, TX
Behrooz Shirazi , Texas advanced Technology Program
pp. 68-72

VSTA: A prolog-Based Formal Verifier for Systtolic Array Designs (Abstract)

Timothy Shih , Santa Clara University, Santa Clara, CA.
Nam Ling , Santa Clara University, Santa Clara, CA.
pp. 73-76

A Parallel Program Tuning Environment (Abstract)

Gary J. Nutt , University of Colorado, Boulder
pp. 77-81

Decremental Scattering for Data Transport Between Host and Hypercube Nodes (Abstract)

Mukesh Sharma , Lehigh University, Bethlehem, PA
Meghanad D. Wagh , Lehigh University, Bethlehem, PA
pp. 82-85
SESSION 4B: CACHE/MEMORY MANAGEMENT

Memory Reference Behavior of Compiler Optimized Programs on High Speed Architectures (Abstract)

John W. C. Fu , Intel Corporation, Folsom, CA
Janak H. Patel , University of Illinois at Urbana-Champaign
pp. 87-94

Performance and Scalability Aspects of Directory-Based Cache Coherence in Shared Multiprocessors (Abstract)

Silvio Picano , Purdue University
Eugene D. III Brooks , Lawrence Livermore National Laboratory
David G. Meyer , Purdue University
Joseph E. Hoag , Lawrence Livermore National Laboratory
pp. 103-106

Compiling for Hierarchical Shared Memory Multiprocessors (Abstract)

J. D. Martens , Ohio State University
D. N. Jayasimha , Ohio State University
pp. 107-110
SESSION 58: MAPPING/SCHEDULING

Efficient Use of Dynamically tagged Directories Through Compiler Analysis (Abstract)

Zhiyuan Li' , University of Minnesota
David J. Lilja , University of Minnesota
Trung N. Nguyen , University of Minnesota
pp. 112-119

Contention-Free 2D-Mesh Cluster Allocation in Hypercubes (Abstract)

Stephen W. Turner , Michigan State University
Betty H.C. Cheng , Michigan State University
Lionel M. Ni , Michigan State University
pp. 125-129

A Task Allocation Algorithm In a Multiprocessor Real-Time System (Abstract)

Jean-Pime BEAUVAIS , Ecole Cende & Nan teslUniversitE de Nantes, Cedex, France
Anne-Marie DEPLANCHE , Ecole Cende & Nan teslUniversitE de Nantes, Cedex, France
pp. 130-133

Processor Allocation and Scheduling of Macro Dataflow Graphs on Distributed Memory Multicomputers by the PARADIGM Compiler (Abstract)

Shankar Ramaswamy , University of Illinois at Urbana-Champaign
Prithviraj Banerjee , University of Illinois at Urbana-Champaign
pp. 134-138
SESSION 68: COMPILER

Locality and Loop Scheduling on NUMA Multiprocessors (Abstract)

Hui Li , University of Toronto
Michael Stumm , University of Toronto
Sudarsan Tandri , University of Toronto
Kenneth C. Sevcik , University of Toronto
pp. 140-147

Compile-Time Charactirization Recurrent Patterns in Irregular Computations (Abstract)

Chua-Huang Huang , Ohio State University
Kalluri Eswar , Ohio State University
P. Sadayappan , Ohio State University
pp. 148-155

Investigating Properties of Code Transformations (Abstract)

Mary Lou Soffa , University of Pittsburgh
Deborah Whitfield , Slippery Rock University
pp. 156-160

Compiling Efficient Programs for Tightly-Coupled Distributed Memory Computers (Abstract)

PeiZong Lee , Academia Sinica, Taiwan
Tzung-Bow Tsai , Chung-cheng University, Taiwan
pp. 161-165
SESSION 7B: SIMD/DATA PARALLEL

Solving Dynamic and Irregular Problems on SIMD Architectures with Runtime Support (Abstract)

WEI SHU , State University of New York, Buffalo, NY
MIN-YOU WU , State University of New York, Buffalo, NY
pp. 167-174

Evaluation of Data Distribution Patterns in Distributed-Memory Machines (Abstract)

Lionel M. Ni , Michigan State University
Edgar T. Kalns , Michigan State University
Hong Xu , Michigan State University
pp. 175-183

Activity Counter: New Optimization for the dynamic scheduling of SIMD Control Flow (Abstract)

Ronun Keryell , Centre de Recherche en Infonnatique, Ecole des Mines de Paris, Cedex, France
Nicolas Paris , Hyperparallel Technologies, Ecole Polytechnique X-POLE, Cedex, France
pp. 184-187

SIMD Optimizations in a Data Parallel C (Abstract)

Maya Gokhale , Supercomputing Research Center, Bowie, MD
Phil Pfeiffer , East Stroudsburg University, PA
pp. 188-191
SESSION 8B : RESOURCE ALLOCATION/OS

A Fair Fast Scalable Rea,der-Writer Lock (Abstract)

Michael Stumm , University of Toronto,Canada
Orran Krieger , University of Toronto,Canada
Jonathan Hanna , University of Toronto,Canada
Ron Unrau , University of Toronto,Canada
pp. 201-204

Experiments With Configurable Locks for Multiprocessors (Abstract)

Karsten Schwan , Georgia lnstitute of Technology
Bodhisattwa Mukherjee , Georgia lnstitute of Technology
pp. 205-208

On Resources Allocation in Binary n-Cube Network Systems (Abstract)

Gui-Liang Feng , University of Southwestern Louisiana
Nian-Feng Tzeng , University of Southwestern Louisiana
pp. 209-212

A Distributed Load Balancing Scheme for Data Parallel Applications (Abstract)

Walid R. Tout , Michigan State University
Sakti Pramanik , Michigan State University
pp. 213-216

Would You Run it Here or There? AHS: Automatic Heterogeneous Supercomputing (Abstract)

H. G. Dietz , Purdue University
B.K. Grant , Purdue University
W.E. Cohen , Purdue University
pp. 217-221
SESSION 9B: TASK GRAPH/DATA FLOW

A Concurrent Dynamic Task Graph (Abstract)

Theodore Johnson , University of Florida
pp. 223-230

Unified Static Scheduling on Various Models (Abstract)

Liang-Fang Chao , Princeton University
Edwin Hsing-Mean Sha , University of Notre Dame
pp. 231-235

Dataflow Graph Optimization for Dataflow Architectures a Dataflow Otimizing Compiler (Abstract)

Masanori Mizoguchi , NEC Corporation, Japan
Sholin Kyo , NEC Corporation, Japan
Shin'ichiro Okazaki , NEC Corporation, Japan
pp. 236-240

Increasing Instruct ion-level Parallelism through Multi-way Branching (Abstract)

Soo-Mook Moon , IBM Thomas J. Watson Research Center, NY
pp. 241-245

Optimizing Parallel Programs Using Affinity Regions (Abstract)

Bill Appelbe , Georgia Institue of Technology, Atlanta, GA
Batakrishnan Lakshmanan , Georgia Institue of Technology, Atlanta, GA
pp. 246-249
SESSION 10B: DATA DISTRIBUTION/PARTITIONING

A Model for Automatic Data Partitioning (Abstract)

Paul D. Hovland , University of Illinois at Urbana-Champaign
Lionel M. Ni , Michigan State Universiby
pp. 251-259

Multi-Level Communication Structure for Heirarchical Gain Aggregation (Abstract)

T.E Gerasch , The MITRE Corporation, McLean, Virginia
C.L McCreary , Auburn University, Alabama
T.J Smith , The MITRE Corporation, McLean, Virginia
D. H Gill , The MITRE Corporation, McLean, Virginia
pp. 260-264

Communication-Free Data Allocation Techniques for Parallelizing Compilers on Multicomputers (Abstract)

Tzung-Shi Chen , National Central University, Taiwan
Jang-Ping Sheu , National Central University, Taiwan
pp. 273-277
SESSION 11B: MISCELLANEOUS

Improving RAID-5 Performance by Un-striping Moderate-Sized Files (Abstract)

Badrinath Roysam , Rensselaer Polytechnic Institute, Troy, New York
Ronald K. McMurdy , Rensselaer Polytechnic Institute, Troy, New York
pp. 279-282

On Performance and Efficiency of VLIW and Superscalar (Abstract)

Soo-Mook Moon , IBM Thomas J. Watson research, NY
kemal Ebcioglu , IBM Thomas J. Watson research, NY
pp. 283-287

Efficient Broadcast in All-Port Wormhole-Routed Hypercubes (Abstract)

Philip K. McKinley , Michigan State University
Christian Trefftz , Michigan State University
pp. 288-291

Implementing Speculative Parallelism in Possible Computational Worlds (Abstract)

James Hearne , Western Washington University
Debra S. Jusak , Western Washington University
Hilda Halliday , Western Washington University
pp. 292-296

On Compiling Array Expressions for Efficient Execution on Distributed-Memory Machines (Abstract)

S. Mufti , Ohio State University Columbus
C.-H. Huang , Ohio State University Columbus
P. Sadayappan , Ohio State University Columbus
S. Sharma , Ohio State University Columbus
S. D. Kaushik , Ohio State University Columbus
S. K. S. Gupta , Ohio State University Columbus
pp. 301-305
Author Index

Author Index (PDF)

pp. 306
81 ms
(Ver )