Topology-aware algorithms for large-scale communication

被引:0
|
作者
Rodrigues, Luís [1 ]
Veríssimo, Paulo [1 ]
机构
[1] Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal
关键词
D O I
10.1007/3-540-46475-1_6
中图分类号
O144 [集合论]; O157 [组合数学(组合学)];
学科分类号
070104 ;
摘要
When designing communication protocols there is always a tradeoff between generality and performance. This chapter reports one approach to achieve right balance between these two aspects, using a network model that can be applied to the majority of existing large-scale networks based on reliable high-speed local-area networks interconnected by slower long-haul connections. The approach consists in making visible relevant topological aspects of the uderlying network infrastructure to the protocol designer, and is illustrated by several algorithms that use topology information to achieve improved performance. © Springer-Verlag Berlin Heidelberg 2000.
引用
收藏
页码:127 / 156
相关论文
共 50 条
  • [1] Topology-aware algorithms for large-scale communication
    Rodrigues, L
    Veríssimo, P
    ADVANCES IN DISTRIBUTED SYSTEMS: ADVANCED DISTRIBUTED COMPUTING: FROM ALGORITHMS TO SYSTEMS, 2000, 1752 : 127 - 156
  • [2] Large-Scale Experiment for Topology-Aware Resource Management
    Georgiou, Yiannis
    Mercier, Guillaume
    Villiermet, Adele
    EURO-PAR 2017: PARALLEL PROCESSING WORKSHOPS, 2018, 10659 : 179 - 186
  • [3] Topology-Aware Mappings for Large-Scale Eigenvalue Problems
    Aktulga, Hasan Metin
    Yang, Chao
    Ng, Esmond G.
    Maris, Pieter
    Vary, James P.
    EURO-PAR 2012 PARALLEL PROCESSING, 2012, 7484 : 830 - 842
  • [4] Topology-aware Sparse Allreduce for Large-scale Deep Learning
    Thao Nguyen Truong
    Wahib, Mohamed
    Takano, Ryousei
    2019 IEEE 38TH INTERNATIONAL PERFORMANCE COMPUTING AND COMMUNICATIONS CONFERENCE (IPCCC), 2019,
  • [5] A scheduling framework for large-scale, parallel, and topology-aware applications
    Kravtsov, Valentin
    Bar, Pavel
    Carmeli, David
    Schuster, Assaf
    Swain, Martin
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2010, 70 (09) : 983 - 992
  • [6] Topology-Aware Data Aggregation for Intensive I/O on Large-Scale Supercomputers
    Tessier, Francois
    Malakar, Preeti
    Vishwanath, Venkatram
    Jeannot, Emmanuel
    Isaila, Florin
    PROCEEDINGS OF FIRST WORKSHOP ON OPTIMIZATION OF COMMUNICATION IN HPC RUNTIME SYSTEMS (COM-HPC 2016), 2016, : 73 - 81
  • [7] TAPIOCA: An I/O Library for Optimized Topology-Aware Data Aggregation on Large-Scale Supercomputers
    Tessier, Francois
    Vishwanath, Venkatram
    Jeannot, Emmanuel
    2017 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER), 2017, : 70 - 80
  • [8] Improving Large-scale Storage System Performance via Topology-aware and Balanced Data Placement
    Wang, Feiyi
    Oral, Sarp
    Gupta, Saurabh
    Tiwari, Devesh
    Vazhkudai, Sudharshan S.
    2014 20TH IEEE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2014, : 656 - 663
  • [9] Topology-Aware Navigation in Large Networks
    Moscovich, Tomer
    Chevalier, Fanny
    Henry, Nathalie
    Pietriga, Emmanuel
    Fekete, Jean-Daniel
    CHI2009: PROCEEDINGS OF THE 27TH ANNUAL CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, VOLS 1-4, 2009, : 2319 - 2328
  • [10] Faster Topology-aware Collective Algorithms Through Non-minimal Communication
    Sack, Paul
    Gropp, William
    ACM SIGPLAN NOTICES, 2012, 47 (08) : 45 - 54