Newsgroups: comp.parallel From: wender@dolly.par.univie.ac.at (Bernd Wender) Subject: ICS'97 -- Early Registration Deadline Approaching Organization: Institute for Software Technology and Parallel Systems Date: 5 Jun 1997 13:22:32 GMT Message-ID: <5n6eio$47l@server1.ctc.com> Please find enclosed the Advance Program for the 11th ACM International Conference on Supercomputing. Please keep in mind that the early registration deadline is *** June 9, 1997 ***. The following information (and a lot more - including the registration form) can be found at our ICS'97 WWW home page at http://www.par.univie.ac.at/~ics97/ Bernd Wender -- Publicity Chair ICS'97 (wender@par.univie.ac.at) ---------------------------------------------------------------------= -------- Invitation to ICS'97 in Vienna, Austria --------------------------------------- The ACM International Conference on Supercomputing is a forum for engineers and scientists throughout the world to exchange ideas and research results relating to high performance supercomputing systems. The 11th conference in the series will be held in Vienna, Austria, from July 7th through July 11th, 1997. Vienna is the site of one of the oldest universities in the world, which was the home of the Vienna Circle and Kurt G=F6del and, in recent years, became a European Center for high performance parallel computing. The conference program includes * five keynote addresses by top-level researchers, * 43 contributed papers, * four workshops, all of which will take place on July 7th, * two panel sessions, * an exhibit, and * an industrial session. The social events include a reception by the Mayor of the City of Vienna, a formal Conference Dinner at an 18th-century Palais, and an informal evening at a typical Viennese wine restaurant. I would like to take this opportunity to express my appreciation for the many individuals and institutions who contributed to this conference. Special thanks are due to the Program Chair, Steve Wallach, the Vice Program Chairs, Harry Wijshoff, Nikolay Mirenkov and Jim Smith, the other members of the Conference Committee, and the Program Committee. This Advance Program describes the conference in detail. Additional up-to-date information can be found at the ICS'97 World Wide Web page at http://www.par.univie.ac.at/~ics97. I cordially invite you to join us and participate in ICS'97! Hans Zima -- General Chair Conference Committee -------------------- General Chair: Hans Zima, University of Vienna Program Chair: Steve Wallach, HP Convex Vice Program Chair - Applications: Harry Wijshoff, Leiden University Vice Program Chair - Software: Nikolay Mirenkov, University of Aizu Vice Program Chair - Architecture: Jim Smith, University of Wisconsin Finance Chair: G=FCnther Vinek, University of Vienna Local Arrangements Chair: Gerald Quirchmayr, University of Vienna Workshop Chair: Frank Baetke, Hewlett-Packard Exhibition Chair: Erich Schikuta, University of Vienna Publicity Chair: Bernd Wender, University of Vienna Program Committee ----------------- Makoto Amamiya - Kyushu University, Japan Nawaf Bitar - Silicon Graphics Corp., Mountain View, CA, USA Francois Bodin - IRISA/INRIA, Rennes, France Tom Conte - North Carolina State University, Raleigh, NC, USA George Cybenko - Dartmouth College, Hanover, NH, USA Thomas Fahringer - University of Vienna, Austria Susan Flynn-Hummel - Polytechnic University of New York, NY, USA Ian Foster - Argonne National Lab., IL, USA Kyle Gallivan - Computer Systems and Research Lab, Urbana, IL, USA Stratis Gallopoulos - University of Patras, Greece Dennis Gannon - Indiana University, Bloomington, IN, USA Hans Michael Gerndt - KFA J=FClich, Germany Elana Granston - Hewlett-Packard, Cupertino, CA, USA Bill Harrod - Cray Research, Eagan, MN, USA Elias Houstis - Purdue University, West Lafayette, IN, USA Hironori Kasahara - Waseda University, Japan Joe Kazuki - Nara Institute of Science and Technology, Japan David Lilja - University of Minnesota, Minneapolis, MN, USA Kathryn McKinley - University of Massachusetts, USA Piyush Mehrotra - ICASE, NASA Langley Research Center, Hampton, VA, USA John Mellor-Crummey - Rice University, Houston, TX, USA Alex Nicolau - University of California, Irvine, CA, USA Yoshio Oyanagi - University of Tokyo, Japan Yousef Saad - University of Minnesota, Minneapolis, MN, USA Joel Saltz - University of Maryland, College Park, MD, USA David Schneider - Cornell University, Ithaca, NY, USA Steve Scott - Cray Research, Inc., Chippewa Falls, WI, USA J.P. Singh - Princeton University, Princeton, NJ, USA Henk Sips - Delft University of Technology, The Netherlands Guri Sohi - University of Wisconsin-Madison, WI, USA Clemens August Thole - GMD, Sankt Augustin, Germany Josep Torrellas - Univ. of Illinois at Urbana Champaign, IL, USA Mateo Valero - Univ. Politecnica de Catalunya, Barcelona, Spain Stamatis Vassiliadis - Delft University of Technology, The Netherlands Alex Veidenbaum - University of Illinois, Chicago, IL, USA Shlomo Weiss - Tel Aviv University, Israel Lex Wolters - Leiden University, The Netherlands Pen-Chung Yew - University of Minnesota, Minneapolis, MN, USA Workshop Program ---------------- Monday, July 7 -------------- Performance Data Mining: Automated Diagnosis, Adapti= on, And Optimization 9:00 - 18:00 Chairs: Alois Ferscha and Allen D. Malony Univ. of Vienna, Austria; University of Oregon, Port= land, OR, USA Molecular Bioinformatics: Sequence Analysis -- The H= uman Genome Project 13:30 - 17:15 Chairs: Ralf Hofestaedt and Hwa Lim Univ. of Magdeburg, Germany; Pangea Systems Inc., Oa= kland, CA, USA Metacomputing: The Challenge of High Performance Dis= tributed 9:00 - 12:30 Systems Chair: Dennis Gannon Indiana University, Bloomington, IN, USA High Performance Cluster Computing 13:30 - 17:15 Chair: Alok Choudhary Northwestern Univ., Evanston, IL, USA Conference Program ------------------ Tuesday, July 8 --------------- Opening: 9:00 -- 9:30 Invited Talk: 9:30 - 10:30 The Characteristics of the Uniprocessor in Future Supercomputer= s Yale N. Patt, Univ. of Michigan, MI, USA Coffee Break: 10:30 - 11:00 Session 1a: 11:00 - 12:00 Instruction-Level Parallelism and Session 1b: 11:00 - 12:00 Wide-Busses Collective I/O Scalable Instruction-Level Parallelism Implementation of Collective I/O= in Through Tree Instructions the Intel Paragon Parallel File Jaime H. Moreno and Mayan Moudgill System: Initial Experiences IBM T. J. Watson Research Center, Rajesh Bordawekar York California Institute of Technolo= gy, town Heights, NY, USA Pasadena, CA, USA Optimizing Collective I/O Perfor= mance Increasing Memory Bandwidth With on Parallel Computers: A Multisy= stem Wide Buses: Compiler, Hardware and Study Performance Trade-Offs Ying Chen*, Ian Foster, Jarek David Lopez, Mateo Valero, Josep Nieplocha, and Marianne Winslett= * Llosa, and Eduard Ayguade *Univ. of Illinois, Urbana, IL, = USA; Univ. Politecnica de Catalunya, Pacific Northwest National Lab., Barcelona, Spain Richland, WA, USA; Argonne Natio= nal Lab., Argonne, IL, USA Lunch Break: 12:00 - 14:00 Session 2a: 14:00 - 15:30 Session 2b: 14:00 - 15:30 Applications Caches Performance Improvement Through Data Caches for Superscalar Proc= essors Overhead Analysis: A Case Study in Toni Juan, Juan J. Navarro, Oliv= ier Molecular Dynamics Temam* Graham D. Riley, J. Mark Bull, and Univ. Politecnica de Catalunya, John R. Gurd Barcelona, Spain; *Versailles Un= iv., University of Manchester, UK France Generalized Cannon's Algorithm for Parallel Matrix Multiplication Improving Data Cache Performance= by Hyuk-Jae Lee, James P. Robertson, Pre-Executing Instructions Under= a and Jose A.B. Fortes Cache Miss Louisiana Tech. Univ., Ruston, LA, James Dundas and Trevor Mudge USA Univ. of Michigan, Ann Arbor, MI= , USA A High-Order Direct Solver for Eliminating Cache Conflict Misse= s Helmholtz Equations With Neumann Through XOR-Based Placement Func= tions Boundary Conditions Antonio Gonzalez, Mateo Valero, = Nigel Xian-He Sun and Yu Zhuang Topham* and Joan M. Parcerisa Louisiana State University, Baton Univ. Politecnica de Catalunya, Rouge, LA, USA Barcelona, Spain; *Univ. of Edin= burgh, UK Coffee Break: 15:30 - 16:00 Panel Session: 16:00 - 18:00 Debate: On The Relative Merits Of Parallel Programming Using a Single-Address-Space Model Versus Message-Passing Between Multiple A= ddress Spaces Chair: John Gurd, Univ. of Manchester, UK Reception - City of Vienna (City Hall) Wednesday, July 9 ----------------- Invited Talk: 8:30 - 9:30 Title: Computers in the Drug Discovery Cycle Hwa Lim, Pangea Systems Inc., Oakland, CA, USA Session 3a: 9:30 - 10:30 Scheduling and Processor Session 3b: 9:30 - 10:30 Assignment Parallel Architectures Performance Study on Optimal Processor Assignment in Parallel pSNOW: A Tool to Evaluate Architect= ural Relational Databases Issues for NOW Environments Kevin H. Liu Mangesh Kasbekar, Shailabh Nagar, A= nand Victoria University of Sivasubramaniam Technology, Melbourne, Australia Pennsylvania State Univ., PA, USA Multiprocessor Scheduling with Client Resources to Improve the CP-PACS: A Massively Parallel Proce= ssor Response Time of WWW For Large Scale Scientific Calculat= ions Applications T. Boku, K. Itakura, H. Nakamura an= d K. Daniel Andresen and Tao Yang Nakazawa University of California, Santa Univ. of Tsukuba, Japan Barbara, CA, USA Coffee Break: 10:30 - 11:00 Session 4a: 11:00 - 12:00 Session 4b: 11:00 - 12:00 Object-Oriented Programming Routing A Methodology for Specifying Data Distribution Using Only Standard Object-Oriented Impact of Selection Functions on Ro= uting Features Algorithm Performance in Multicompu= ter Naohito Sato, Satoshi Matsuoka, Networks Jean-Marc Jezequel, Akinori Wu-chang Feng, Kang G. Shin Yonezawa Univ. of Michigan, Ann Arbor, MI, U= SA Univ. of Tokyo, Japan HPC++: Experiments with the Parallel Standard Template Library Performance Benefits of Virtual Cha= nnels Elizabeth Johnson, Dennis And Adaptive Routing: An Gannon, and Peter Beckman* Application-Driven Study Indiana Univ., Bloomington, IN, Aniruddba S. Vaidya, Anand USA; Sivasubramaniam, and Chita R. Das *Los Alamos National Lab., NM, Pennsylvania State Univ., PA, USA USA Lunch Break: 12:00 - 14:00 Session 5a: 14:00 - 15:30 Session 5b: 14:00 - 15:30 Synchronization Performance Performance Evaluation of Message-D= riven Distributed Shared Memory Parallel VLSI CAD Applications on G= eneral Systems with Improved Barrier Purpose Multiprocessors Synchronization And Data John G. Holm, John A. Chandy*, Stev= en Transfer Parkes*, Sumit Roy, Venkatram Nian-Feng Tzeng and Angkul Krishnaswamy, Gagan Hasteer, and Kongmunvattana Prithviraj Banerjee** Univ. of Southwestern Louisiana, University of Illinois, Urbana, IL,= USA; Lafayette, LA, USA *Sierra Vista Research, Los Gatos, = CA, USA; **Northwestern University, Eva= nston, IL, USA Incorporating Application Dependent A Graph Based Approach to Information In An Automatic Code Barrier Synchronisation Generating Environment Minimisation R. van Engelen, I. Heitlager, L. Wo= lters, E.A. St=F6hr and Michael F. P. and G. Cats* O'Boyle Leiden University, The Netherlands; Univ. of Manchester, UK *Royal Netherlands Meteorological Institute, Ae de Bilt, The Netherla= nds The Importance of Synchronization Structure in Sparse Code Generation for Imperfec= tly Parallel Program Optimization Nested Loops With Dependencies Arjan J.C. van Gemund Vladimir Kotylar and Keshav Pingali Delft Univ. of Technology, The Cornell University, Ithaca, NY, USA Netherlands =20 Coffee Break: 15:30 - 16:00 Panel Session: 16:00 - 18:00 Debate: On The Implementation Aspects of a Single-Address-Space M= odel Versus a Message-Passing Model As Seen From Independent Software Pro= viders Chair: Frank Baetke, Hewlett Packard, Munich, Germany Conference Dinner (Palais Pallavicini): 20:00 Thursday, July 10 ----------------- Invited Talk: 8:30 - 9:30 Problem Solving Environments and Netsolve: A Network Server for So= lving Computational Science Problems Jack Dongarra, Univ. of Tennessee, Knoxville, TN, USA Session 6a: 9:30 - 10:30 Session 6b: 9:30 - 10:30 Prefetching Communication and Multicast= s Speculative Execution Via Address Performance Considerations in So= ftware Prediction and Data Prefetching Multicasts Jose Gonzalez and Antonio Gonzalez Joerg Cordsen, H.-W. Pohl, and W= olfgang Univ. Politecnica de Catalunya, Schr=F6der-Preikschat* Barcelona, Spain GMD-First Berlin, Germany; *Univ= . of Potsdam, Germany Adaptive Data Prefetching Using Iteration Space Slicing And Its Cache Information Application To Communication Ando Ki, Alan Knowles Optimization Univ. of Manchester, UK William Pugh and Evan Rosser Univ. of Maryland, MD, USA Coffee Break: 10:30 - 11:00 Session 7a: 11:00 - 12:00 Tree-based and Semi-Structured Session 7b: 11:00 - 12:00 Applications Distributed Shared Memory Compiler And Run-Time Support For Design and Performance of the Sh= asta Semi-Structured Applications Distributed Shared Memory Protoc= ol Nikos Chrisochoides, Induprakas Daniel J. Scales and Kourosh Kodukula, and Keshav Pingali Gharachorloo Cornell University, Ithaca, NY, USA Digital Western Research. Lab., = Palo Alto, CA, USA Conflict-Free Template Access in An I/O Network Architecture of t= he k-ary and Binomial Trees Distributed Shared-Memory Massiv= ely Sajal K. Das, Falguni Sarkar, and M.Christina Pinotti* Parallel Computer JUMP-1 University of North Texas, Denton, H. Nakajo, S. Ohtani, T. Matsumo= to, M. TX, USA; *IEI, Consiglio Nazionale Kohata, K. Hiraki and Y. Kaneda delle Ricerche, Pisa, Italy Kobe Univ., Japan Lunch Break: 12:00 - 14:00 Session 8a: 14:00 - 15:30 Session 8b: 14:00 - 15:30 Compilers Hardware Features for Performa= nce Symbolic Evaluation for Parallelizing Compilers Implementation and Analysis of P= ath Thomas Fahringer and Bernhard History in Dynamic Branch Predic= tion Scholz Schemes Univ. of Vienna, Austria; Vienna Shlomo Reches, Shlomo Weiss Univ. of Technology, Austria Tel Aviv Univ., Israel A Compiler Algorithm for Optimizing Locality in Loop Nests Mahmut T. Kandemir, J. Ramanujam, A Victim Cache for Vector Regist= ers and Alok Choudhary Roger Espasa, Mateo Valero Syracuse Univ., NY, USA; Louisiana Univ. Politecnica de Catalunya, State Univ., Baton Rouge, LA, USA; Barcelona, Spain Northwestern Univ., Evanston, IL, USA The Performance Impact of Exploi= ting Compile-Time Minimisation of Load Branch ILP with Tree Representat= ion of Imbalance in Loop Nests ILP Code Rizos Sakellariou and John R. Gurd Soo-Mook Moon, Kemal Ebcioglu Univ. of Manchester, UK Seoul Nat. Univ., South Korea; I= BM T. J. Watson Research Center, Yorkt= own Heights, NY, USA Coffee Break: 15:30 - 16:00 Industrial Session: 16:00 - 18:00 Sightseeing Tour and Heurigen Dinner: 19:00 Friday, July 11 --------------- Invited Talk: 8:30 - 9:30 The Road to a Petaflops Computer Paul Smith, Department of Energy, Washington, DC, USA (Speaker= ) Martin Sokoloski, Science and Technology Corp., Hampton, VA, U= SA Invited Talk: 9:30 - 10:30 SPOCK: Rapid Product Development via Computer-Based Communicati= on Stefan Rill, Daimler Benz Aerospace Airbus / Univ. of Bremen, Germ= any Coffee Break: 10:30 - 11:00 Session 9a: 11:00 - 12:30 Data Placement and Transformation Session 9b: 11:00 - 12:00 Performance Prediction and Codi= ng Non-singular data transformations: Definition, Developing Architecture Adaptive Validity and Applications Algorithms using Simulation with Michael F.P. O'Boyle and P.M.W MISS-PVM for Performance Predictio= n Knijnenburg Dieter F. Kvasnicka and Christoph = W. Univ. of Manchester, UK; Leiden Ueberhuber Univ., The Netherlands Vienna Univ. of Technology, Austri= a Cache Miss Equations: An Optimizing Matrix Multiply using P= HiPAC: Analytical Representation of a Portable, High-Performance, ANSI= C Cache Misses Coding Methodology Somnath Ghosh, Margaret Jeff Bilmes, Krste Asanovic, Chee-= Whye Martonosi, and Sharad Malik Chin, and Jim Demmel Princeton Univ., NJ, USA Univ. of California at Berkeley, C= A, USA Adaptive Migratory Scheme for Distributed Shared Memory Jai-Hoon Kim, Nitin H. Vaidya Texas A&M Univ., College Station, TX, USA End of Conference: 12:30 ---------------------------------------------------------------------= ----- Bernd Wend= er, Univ. of Vienna, Institute for Software Technology and Parallel Syste= ms. ------------ ``What makes the universe so hard to comprehend --------= ---- --------------- is that there's nothing to compare it with'' --------= ---- -- Articles to parallel@ctc.com (Administrative: bigrigg@ctc.com) Archive: http://www.hensa.ac.uk/parallel/internet/usenet/comp.parallel