ASYNCHRONOUS PROBLEMS ON SIMD PARALLEL COMPUTERS

被引:7
作者
SHU, W
WU, MY
机构
[1] Department of Computer Science, State University of New York at Buffalo, Buffalo
基金
美国国家科学基金会;
关键词
SIMD PARALLEL COMPUTERS; PORTABLE PROGRAMMING ENVIRONMENT; LOAD BALANCING; THREAD MODEL; SCALABILITY; IRREGULAR AND DYNAMIC APPLICATIONS;
D O I
10.1109/71.395399
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
One or the essential problems in parallel computing is: Can SIMD machines handle asynchronous problems? This is a difficult, unsolved problem because of the mismatch between asynchronous problems and SIMD architectures, We propose a solution to let SIMD machines handle general asynchronous problems, Our approach is to implement a runtime support system which can run MIMD-like software on SIMD hardware, The runtime support system, named P kernel, is thread-based. There are two major advantages of the thread-based model. First, for application problems with irregular and/or unpredictable features, automatic scheduling can move some threads from overloaded processors to underloaded processors. Second, and more importantly, the granularity of threads can be controlled to reduce system overhead. The P kernel is also able to handle bookkeeping and message management, as well as to make these low-level tasks transparent to users. Substantial performance has been obtained on Maspar MP-1.
引用
收藏
页码:704 / 713
页数:10
相关论文
共 50 条
  • [31] Enhancing scalability and load balancing of Parallel Selected Inversion via tree-based asynchronous communication
    Jacquelin, Mathias
    Yang, Chao
    Lin, Lin
    Wichmann, Nathan
    2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2016), 2016, : 192 - +
  • [32] Numerically and Parallel Scalable TFETI based Algorithms for Contact Problems
    Kozubek, T.
    Markopoulos, A.
    Brzobohaty, T.
    PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ENGINEERING COMPUTATIONAL TECHNOLOGY, 2010, 94
  • [33] State of the art in parallel search techniques for discrete optimization problems
    Grama, A
    Kumar, V
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1999, 11 (01) : 28 - 35
  • [34] A Parallel Skeleton for Divide-and-conquer Unbalanced and Deep Problems
    Millán A. Martínez
    Basilio B. Fraguela
    José C. Cabaleiro
    International Journal of Parallel Programming, 2021, 49 : 820 - 845
  • [35] An Efficient Multicore based Parallel Computing Approach for TSP Problems
    Li, Ying
    Ma, Kai
    Zhang, Jiong
    2013 NINTH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG), 2013, : 98 - 104
  • [36] A Parallel Skeleton for Divide-and-conquer Unbalanced and Deep Problems
    Martinez, Millan A.
    Fraguela, Basilio B.
    Cabaleiro, Jose C.
    INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING, 2021, 49 (06) : 820 - 845
  • [37] A parallel generalized conjugate gradient method for large scale eigenvalue problems
    Yu Li
    Hehu Xie
    Ran Xu
    Chun’guang You
    Ning Zhang
    CCF Transactions on High Performance Computing, 2020, 2 : 111 - 122
  • [38] Scalable parallel algorithms for difficult combinatorial problems: A case study in optimization
    Abu-Khzam, FN
    Langston, MA
    Shanbhag, P
    Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, 2004, : 649 - 654
  • [39] A Comparison of Accuracy and Efficiency of Parallel Solvers for Fractional Power Diffusion Problems
    Ciegis, Raimondas
    Starikovicius, Vadimas
    Margenov, Svetozar
    Kriauziene, Rima
    PARALLEL PROCESSING AND APPLIED MATHEMATICS (PPAM 2017), PT I, 2018, 10777 : 79 - 89
  • [40] A parallel generalized conjugate gradient method for large scale eigenvalue problems
    Li, Yu
    Xie, Hehu
    Xu, Ran
    You, Chun'guang
    Zhang, Ning
    CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING, 2020, 2 (02) : 111 - 122