KOSEN 한인과학기술자네트워크

이 자료는 보안 문서로 등록이 되어 있습니다. 문서를 열람하시기 원하시는 분은 다음의 사용자 암호를 입력하신 후 사용하시기 바랍니다. 사용자 암호 : www.kosen21.org Topic 06 - Complexity Theory and Algorithms - Beyond External Computing : Analysis of the Cycle Structure of Permutations - Heaps Are Better than Buckets : Parallel Shortest Paths on Unbalanced Graphs - Efficient Synchronization of Asynchronous Processes Topic 07 - Applications on High-Performance Computers - Scanning Biosequence Databases on a Hybrid Parallel Architecture - A Parallel Computation of Power System Equations - Level-3 Trigger for a Heavy Ion Experiment at LHC - Experiences in Using MPI-IO on Top of GPFS for the IFS Weather Forecast Code Topic 08 - Instruction-Level Parallelism and Computer Architecture - Branch Prediction Using Profile Data - An Efficient Indirect Branch Predictor - The Behavior of Efficient Virtual Machine Interpreters on Modern Architectures - Improving Conditional Brach Prediction on Speculative Multithreading Architectures - Instruction Wake-up in Wide Issue Superscalars - Execution Latency Reduction via Variable Latency Pipeline and Instruction Reuse - Memory Bandwidth : The True Bottleneck of SIMD Multimedia Performance on a Superscalar Processor - Macro Extension for SIMD Processing - Performances of a Dynamic Threads Scheduler Topic 09 - Distributed Systems and Algorithms - Self-stabilizing Neighborhood Unique Naming under Unfair Scheduler - Event List Management in Distributed Simulation - Performance Evaluation of Plausible Clocks - Building TMR-Based Reliable Servers Despite Bounded Input Lifetimes - Fractional Weighted Reference Counting Topic10 - Parallel Programming : Models, Methods and Programming Languages - Accordion Clocks : Logical Clocks for - Partial Evaluation of Concurrent Programs - A Transparent Operating System Infrastructure for Embedding adaptability to Thread-Based Programming Models - Nepal - Nested Data Paraleelism in Haskell - Introduction of Static Load Balancing in Incremental Parallel Programming - A Component Framework for HPC Applications - Towards Formally Refining BSP Barriers into Explicit Two - Sided Communications - Solving Bi-knapsack Problem Using Tiling Approach for Dynamic Programming Topic 11 - Numerical Algorithms - Parallel Implementation of a Block Algorithm for Matrix 1-Norm Estimation - Eigenvalue Spectrum Estimation and Photonic Crystals - Polynomial Preconditioning for Specially Structured Linear Systems of Equations - Parallel Application of a Novel Domain Decomposition Preconditioner for the Stable Finite Element Solution of Three-Dimensional Convection-Dominated PDEs - Performance of High-Accuracy PDE Solvers on a Self-Optimizing NUMA Architecture