ON THE GRANULARITY AND CLUSTERING OF DIRECTED ACYCLIC TASK GRAPHS

被引:138
|
作者
GERASOULIS, A
YANG, T
机构
[1] Department of Computer Science, Rutgers University, New Brunswick, NJ
基金
美国国家科学基金会;
关键词
CLUSTERING; DAGS; GAUSS-JORDAN ALGORITHM; GRANULARITY; PARALLEL ARCHITECTURES; PARTITIONING; SCHEDULING;
D O I
10.1109/71.242154
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper we consider the impact of the granularity on scheduling task graphs. Scheduling consists of two parts, the processors assignment of tasks and the ordering of tasks for execution in each processor. The processor assignment part is also known as clustering in the literature when there is no limitation in the number of processors and the architecture is completely connected. We introduce two types of clusterings, the nonlinear and linear clusterings. A clustering is nonlinear if two parallel tasks are mapped in the same cluster otherwise is linear. Linear clustering fully exploits the natural parallelism of a given DAG while nonlinear clustering sequentializes independent tasks to reduce parallelism. We also introduce a new quantification of the granularity of a DAG and define a coarse grain DAG as the one whose granularity is greater than one. We prove the following interesting result: Every nonlinear clustering of a coarse grain DAG can be transformed into a linear clustering which has less or equal parallel time than the nonlinear. We use this result to prove the optimality of some important linear clusterings used in parallel numerical computing. We also present experiments with an actual architecture that verify our theoretical results. These results provide a justification for the popularity of linear clustering in the literature.
引用
收藏
页码:686 / 701
页数:16
相关论文
共 50 条
  • [31] Information Flow on Directed Acyclic Graphs
    Donders, Michael
    More, Sara Miner
    Naumov, Pavel
    LOGIC, LANGUAGE, INFORMATION AND COMPUTATION, WOLLIC 2011, 2011, 6642 : 95 - 109
  • [32] On counting homomorphisms to directed acyclic graphs
    Dyer, Martin
    Goldberg, Leslie Ann
    Paterson, Mike
    AUTOMATA, LANGUAGES AND PROGRAMMING, PT 1, 2006, 4051 : 38 - 49
  • [33] Covering Pairs in Directed Acyclic Graphs
    Beerenwinkel, Niko
    Beretta, Stefano
    Bonizzoni, Paola
    Dondi, Riccardo
    Pirola, Yuri
    COMPUTER JOURNAL, 2015, 58 (07): : 1673 - 1686
  • [34] Transformers over Directed Acyclic Graphs
    Luo, Yuankai
    Thost, Veronika
    Shi, Lei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [35] Demand-driven Execution of Static Directed Acyclic Graphs Using Task Parallelism
    Kambadur, Prabhanjan
    Gupta, Anshul
    Hoefler, Torsten
    Lumsdaine, Andrew
    16TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING (HIPC), PROCEEDINGS, 2009, : 284 - 293
  • [36] Directed Acyclic Graphs in Surgical Research
    Gongola, AlleaBelle
    Bradshaw, Jace C.
    JOURNAL OF SURGICAL RESEARCH, 2023, 282 : 285 - 288
  • [37] Ternary directed acyclic word graphs
    Miyamoto, S
    Inenaga, S
    Takeda, M
    Shinohara, A
    THEORETICAL COMPUTER SCIENCE, 2004, 328 (1-2) : 97 - 111
  • [38] Sparse directed acyclic word graphs
    Inenaga, Shunsuke
    Takeda, Masayuki
    STRING PROCESSING AND INFORMATION RETRIEVAL, PROCEEDINGS, 2006, 4209 : 61 - 73
  • [39] Covering Pairs in Directed Acyclic Graphs
    Beerenwinkel, Niko
    Beretta, Stefano
    Bonizzoni, Paola
    Dondi, Riccardo
    Pirola, Yuri
    LANGUAGE AND AUTOMATA THEORY AND APPLICATIONS (LATA 2014), 2014, 8370 : 126 - 137
  • [40] Directed acyclic graphs in clinical research
    Dekkers, Olaf M.
    Laugesen, Kristina
    Groenwold, Rolf H. H.
    EUROPEAN JOURNAL OF ENDOCRINOLOGY, 2024, 190 (04) : E5 - E7