High Performance Computing: International Symposium, Ishpc '97, Fukuoka, Japan, November 4-6, 1997: Proceedings (Lecture Notes in Computer Science)

This Book Constitutes The Refereed Proceedings Of The International Symposium On High Performance Computing, Ishpc '97, Held In Fukuoka, Japan In November 1997. The Volume Presents Four Distinguished Papers And 16 Revised Regular Papers Selected From More Than 40 Submissions On The Basis Of At Least Three Peer Reviews. Also Included Are Seven Invited Contributions By Leading Authorities And 10 Selected Poster Presentations. The Papers Are Organized In Topical Chapters On High Performance Systems Architectures, Networks, Compilers, Systems Software, And Applications In Various Areas. The Generation Of Optimized Codes Using Nonzero Structure Analysis -- On The Importance Of An End-to-end View Of Memory Consistency In Future Computer Systems -- High Performance Distributed Object Systems -- Instruction Cache Prefetching Using Multilevel Branch Prediction -- High Performance Wireless Computing -- High-performance Computing And Applications In Image Processing And Computer Vision -- Present And Future Of Hpc Technologies -- Evaluation Of Multithreaded Processors And Thread-switch Policies -- A Multithreaded Implementation Concept Of Prolog On Datarol-ii Machine -- Thread Synchronization Unit (tsu): A Building Block For High Performance Computers -- Data Dependence Path Reduction With Tunneling Load Instructions -- Performance Estimation Of Embedded Software With Pipeline And Cache Hazard Modeling -- An Implementation And Evaluation Of A Distributed Shared-memory System On Workstation Clusters Using Fast Serial Links --^ Designing And Optimizing 3-connectivity Communication Networks Using A Distributed Genetic Algorithm -- Adaptive Routing On The Recursive Diagonal Torus -- Achieving Multi-level Parallelization -- A Technique To Eliminate Redundant Inter-processor Communication On Parallelizing Compiler Tinpar -- An Automatic Vectorizing/parallelizing Pascal Compiler V-pascal Ver. 3 -- An Algorithm For Automatic Detection Of Loop Indices For Communication Overlapping -- Naraview: An Interactive 3d Visualization System For Parallelization Of Programs -- Hybrid Approach For Non-strict Dataflow Program On Commodity Machine -- Resource Management Methods For General Purpose Massively Parallel Os Sss-core -- Scenario-based Hypersequential Programming: Formulation Of Parallelization -- Parallelization Of Space Plasma Particle Simulation -- Implementing Iterative Solvers For Irregular Sparse Matrix Problems In High Performance Fortran -- Parallel Navigation In An A-netl Based Parallel Oodbms --^ High Performance Parallel Fft On Distributed Memory Parallel Computers -- Parallel Computation Model Logpq -- Cost Estimation Of Coherence Protocols Of Software Managed Cache On Distributed Shared Memory System -- A Portable Distributed Shared Memory System On The Cluster Environment: Design And Implementation Fully In Software -- An Object-oriented Framework For Loop Parallelization -- A Method For Runtime Recognition Of Collective Communication On Distributed-memory Multiprocessors -- Improving The Performance Of Automated Forward Deduction System Encal -- Efficiency Of Parallel Machine For Large-scale Simulation In Computational Physics -- Parallel Pdb Data Retriever “pdb Diving Booster” -- A Parallelization Method For Neural Networks With Weak Connection Design -- Exploiting Parallel Computers To Reduce Neural Network Training Time Of Real Applications. Constantine Polychronopoulos ... [et Al.], Eds. Includes Bibliographical References And Index. The generation of optimized codes using nonzero structure analysis....Pages 1-29 On the importance of an end-to-end view of memory consistency in future computer systems....Pages 30-41 High performance distributed object systems....Pages 42-50 Instruction cache prefetching using multilevel branch prediction....Pages 51-70 High performance wireless computing....Pages 71-71 High-performance computing and applications in image processing and computer vision....Pages 72-72 Present and future of HPC technologies....Pages 73-74 Evaluation of multithreaded processors and thread-switch policies....Pages 75-90 A multithreaded implementation concept of prolog on Datarol-II machine....Pages 91-106 Thread Synchronization Unit (TSU): A building block for high performance computers....Pages 107-118 Data dependence path reduction with tunneling load instructions....Pages 119-130 Performance estimation of embedded software with pipeline and cache hazard modeling....Pages 131-142 An implementation and evaluation of a distributed shared-memory system on workstation clusters using fast serial links....Pages 143-158 Designing and optimizing 3-connectivity communication networks using a distributed genetic algorithm....Pages 159-170 Adaptive routing on the Recursive Diagonal Torus....Pages 171-182 Achieving multi-level parallelization....Pages 183-194 A technique to eliminate redundant inter-processor communication on parallelizing compiler TINPAR....Pages 195-204 An automatic vectorizing/parallelizing Pascal compiler V-Pascal ver. 3....Pages 205-216 An algorithm for automatic detection of loop indices for communication overlapping....Pages 217-230 NaraView: An interactive 3D visualization system for parallelization of programs....Pages 231-242 Hybrid approach for non-strict dataflow program on commodity machine....Pages 243-254 Resource management methods for general purpose massively parallel OS SSS-CORE ....Pages 255-266 Scenario-based hypersequential programming: Formulation of parallelization....Pages 267-280 Parallelization of space plasma particle simulation....Pages 281-292 Implementing iterative solvers for irregular sparse matrix problems in high performance Fortran....Pages 293-304 Parallel navigation in an A-NETL based parallel OODBMS....Pages 305-316 High performance parallel FFT on distributed memory parallel computers....Pages 317-326 Parallel computation model logPQ....Pages 327-334 Cost estimation of coherence protocols of software managed cache on distributed shared memory system....Pages 335-342 A portable distributed shared memory system on the cluster environment: Design and implementation fully in software....Pages 343-350 An object-oriented framework for loop parallelization....Pages 351-360 A method for runtime recognition of collective communication on distributed-memory multiprocessors....Pages 361-370 Improving the performance of automated forward deduction system EnCal....Pages 371-380 Efficiency of parallel machine for large-scale simulation in computational physics....Pages 381-388 Parallel PDB data retriever “PDB diving booster”....Pages 389-396 A parallelization method for neural networks with weak connection design....Pages 397-404 Exploiting parallel computers to reduce neural network training time of real applications....Pages 405-414