Preliminary Program: ACM ICS'95

Barcelona, Spain, July 3-7, 1995
Sponsored by ACM/SIGARCH

• Monday, July 3
  Tutorial: Recent Advances in Compilers for Parallel Machines, Monica Lam, Stanford Univ.
  Conference registration starts at 18:00
• Tuesday, July 4
  • 9:00 - Clemens Thole (invited), GMD (Germany)
    EUROPORT: Porting Industrial Applications onto Parallel Architectures
  • 10:15 - Synchronization (chair: Sartaj Sahni)
    • The Performance Impact of Fast Synchronization in Parallel Computers, T. Stricker, J. Stichnoth, D. O'Hallaron, S. Hinrichs, T. Gross
    • Techniques for Reducing Overheads of Shared-Memory Multiprocessing, A. Kagi, N.M. Aboulenein, D.C. Burger and J.R. Goodman (best paper award)
  • 10:15 - Compiler Optimizations (chair: Guang R. Gao)
    • Compiler Cache Optimizations for Banded Matrix Problems, W. Li
    • Optimum Modulo Schedules for Minimum Register Requirements, A.E. Eichenberger, E.S. Davidson, S.G. Abraham
  • 11:15 - break
  • 11:45 - Programming Models (chair: Daniel A. Reed)
    • Upper Time Bounds for Executing PRAM Programs on the LogP-Machine , W. Loewe and W. Zimmermann
    • On the Utility of Threads for Data Parallel Programming, T. Fahringer, M. Haines, P. Mehrotra
    • The DMBC: Architecture and Fundamental Operations, S. Sahni
  • 11:45 - Distributed Memory Compilers (chair: Hironori Kasahara)
    • A Comparison of Compilers for Shared and Distributed Memory Machines, C-W. Tseng, J.M. Anderson, S.P. Amarasinghe, M.S. Lam
    • A Compiler-Directed Distributed Shared Memory System, T-C. Chiueh and M. Verma
    • Reducing Communication by Honoring Multiple Alignments, D.A. Garza-Salazar and W. Bohm
  • 13:15 - lunch
  • 15:00 - Performance Analysis (chair: Thomas Fahringer)
    • Multiprocessor Scalability Predictions Through Detailed Program Execution Analysis, X. Zhang and Z. Xu (best paper award)
    • Petri Net Modeling of Interconnection Networks for Massively Parallel Architectures, J. A. Gregorio, F. Vallejo, R. Beivide, and C. Carrion
  • 15:00 - Compiling Unstructured Code (chair: Thomas Gross (ETH Zuerich/CMU))
    • Efficient Resolution of Sparse Indirections in Data-Parallel Compilers , M. Ujaldon and E.L. Zapata
    • Extending High Performance Fortran for the Support of Unstructured Computations, A. Muller and R. Ruhl
    • Run-Time Methods for Parallelizing Partially Parallel Loops, L. Rauchwerger, N.M. Amato, D.A. Padua
  • 16:30 - break
  • 17:00 - Industry Panel: The Future of High Performance Computing
  • 19:00 - break
  • 20:00 - Convex and Hewlett-Packard Welcome Reception
• Wednesday, July 5
  • 9:00 - Monica Lam, Stanford University (invited)
    The Stanford SUIF Parallelizing Compiler
  • 10:15 - Interconnection Networks (chair: Tzi-cker Chiueh)
    • A Near-Optimal Broadcasting Algorithm in All-Port Wormhole-Routed Hypercubes, C-M. Wang and C-Y. Ku
    • A Comparative Study of Single Hop WDM Interconnections for Multiprocessors, K.R. Desai and K. Ghose
  • 10:15 - Dynamic Load Balancing (chair: Josep Torrellas)
    • Dynamic Load Balancing for the Simulation of Granular Materials, R. Knecht and G. A. Kohring
    • Dynamic Load Balancing of Data Parallel Applications on a Distributed Network, M. Hamdi and C-K. Lee
  • 11:15 - break
  • 11:45 - Compiling High Performance Fortran (chair: Emilio L. Zapata)
    • Efficient Address Generation for Block-Cyclic Distributions, K. Kennedy, N. Nedeljkovic, A. Sethi
    • Using Asynchronous and Bulk Communications to Construct an Optimizing Compiler for Distributed Memory Machines with Consideration Given to Communication Costs, H. Sato, T. Nanri, M. Shimasaki
    • HPF Compiler for the AP1000, T. Shindo, H. Iwashita, T. Doi, J. Hagiwara, S. Kaneshiro
    • The Threaded Communication Library: Preliminary Experience on a Multiprocessor with Dual-Processor Nodes, N. Elmasri, H.H.J. Hum, G.R. Gao
  • 11:45 - Parallel Applications (chair: Mitsuru Ikei)
    • Amon: A Parallel Slice Router, H. Keshk, S-I. Mori, H. Nakashima, S. Tomita
    • Implementation of Sparta, a Highly Parallel Circuit Simulator by the Preconditioned Jacobi Method, on a Distributed Memory Machine, R. Suda and Y. Oyanagi
    • Integral Knapsack Problems: Parallel Algorithms and their Implementations on Distributed Systems, D. Morales, J. Roda, F. Almeida, C. Rodriguez, F. Garcia
    • Optimization and Parallelization of a Commodity Trade Model for the IBM SP-1/2 Using Parallel Programming Tools, D. Bergmark
  • 13:45 - lunch
  • 15:30 - IBM Deep Blue Chess Machine Session
    • Overview and History of Computer Chess, Deep Thought, and Deep Blue, C.J. Tan
    • The Deep Blue Machine: Hardware and Software, M.S. Campbell, F.-H. Hsu, and A.J. Hoane
  • 16:30 - Chess Match: Miguel Illescas (Spanish International Chess Grand Master) vs. IBM Deep Blue
  • 18:30 - break
• Thursday, July 6
  • 9:00 - Yuji Oinaga, Fujitsu (invited)
    Advantage of Vector Parallel Architecture and Its View
  • 10:15 - Data Caching (chair: James R. Goodman)
    • Hardware Implementation Issues of Data Prefetching, N. Drach
    • Data Forwarding in Scalable Shared-Memory Multiprocessors, D.A. Koufaty, X. Chen, D.K. Poulsen, J. Torrellas
  • 10:15 - Parallelization I (chair: Peiyi Tang)
    • Enhancing Array Dataflow Dependence Analysis with On-Demand Global Value Propagation, V. Maslov
    • Optimal Tile Size Adjustment in Compiling General DOACROSS Loop Nests, H. Ohta, Y. Saito, M. Kainaga, H. Ono
  • 11:15 - break
  • 11:45 - Data Mapping (chair: Wim Bohm)
    • Efficient Embeddings into the Hypercube Using Matrix Transformations, M. Hamdi and S.W. Song
    • Architecture-Independent Locality Improving Transformations of Computational Graphs Embedded in k-Dimensions, C-W. Ou, M. Gunwani, S. Ranka
    • Semi-Linear and Bi-Base Storage Schemes Classes: General Overview and Case Study, J. Jorda, A. Mzoughi, D. Litaize
  • 11:45 - Advanced Compilers (chair: Kleanthis Psarris)
    • A Dataflow Language with Object-based Extension and Its Implementation on a Commercially Available Parallel Machine, S. Kusakabe, T. Nagai, Y. Yamashita, R-I. Taniguchi, M. Amamiya
    • Compiler Reduction of Synchronisation in Shared Virtual Memory Systems, M. O'Boyle and F. Bodin
    • A Macrotask-level Unlimited Speculative Execution on Multiprocessors, H. Yamana, M. Sato, Y. Kodama, H. Sakane, S. Sakai, Y. Yamaguchi
  • 13:15 - lunch
  • 15:00 - University Panel: The Future of High Performance Computing
  • 17:00 - Chess Match: IBM Deep Blue vs. Miguel Illescas (Spanish International Chess Grand Master)
  • 19:00 - break
  • 20:00 - Conference Banquet
• Friday, July 7
  • 9:00 - Thierry van der Pyl, EU Commission (invited)
    HPCN: European Perspectives
  • 10:15 - Processors (chair: William Auld)
    • A Data Cache with Multiple Caching Strategies Tuned to Different Types of Locality, A. Gonzalez, C. Aliagas, M. Valero
    • Scalar Processor of the VPP500 Parallel Supercomputer, Y. Nakashima, T. Kitamura, H. Tamura, M. Takiuchi, K. Miura
  • 10:15 - Using Higher Level Languages (chair: )
    • A Comparison of Parallel Programming Paradigms and Data Distributions for a Limited Area Numerical Weather Forecast Routine, R. van Engelen and L. Wolters
    • The Portable Parallel Implementation of Two Novel Mathematical Biology Algorithms in ZPL, M.D. Dikaiakos, C. Lin, D. Manoussaki, D.E. Woodward
  • 11:15 - break
  • 11:45 - Input/Output (chair: )
    • Performance Optimization for Parallel Tape Arrays, T-C. Chiueh
    • PPFS: A High Performance Portable Parallel File System, J.V. Huber, Jr., C.L. Elford, D.A. Reed, A.A. Chien, D. S. Blumenthal
    • Communication Strategies for Out-of-Core Programs on Distributed Memory Machines, R. Bordawekar and A. Choudhary
    • Performance Evaluation of a Parallel I/O Architecture, S.J. Baylor, C. Benveniste, Y. Hsu
  • 11:45 - Parallelization II (chair: Zhiyuan Li)
    • Gated SSA-Based Demand-Driven Symbolic Analysis for Parallelizing Compilers, P. Tu and D. Padua (best paper award)
    • Advanced Compilation Techniques in the PARADIGM Compiler for Distributed-Memory Multicomputers, E. Su, A. Lain, S. Ramaswamy, D.J. Palermo, E.W. Hodges, P. Banerjee
    • Vectorization beyond Data Dependences, P. Tang and N. Gao
    • Idiom Recognition in the Polaris Parallelizing Compiler, B. Pottenger and R. Eigenmann
  • 13:45 - Conference Closing and lunch