Task-Parallel Reductions in OpenMP and OmpSs

被引：0
|
作者：
Ciesko, Jan [1 ]
Mateo, Sergi [1 ]
Teruel, Xavier [1 ]
Beltran, Vicenc [1 ]
Martorell, Xavier [1 ,2 ]
Badia, Rosa M. [1 ,3 ]
Ayguade, Eduard [1 ,2 ]
Labarta, Jesus [1 ,2 ]
机构：
[1] Barcelona Supercomp Ctr, Barcelona, Spain
[2] Univ Politecn Cataluna, E-08028 Barcelona, Spain
[3] CSIC, Artificial Intelligence Res Inst IIIA, Barcelona, Spain
来源：
USING AND IMPROVING OPENMP FOR DEVICES, TASKS, AND MORE | 2014年 / 8766卷
关键词：
OpenMP; Task; Reduction; Recursion; OmpSs;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
The wide adoption of parallel processing hardware in mainstream computing as well as the raising interest for efficient parallel programming in the developer community increase the demand for parallel programming model support for common algorithmic patterns. In this work we present an extension to the OpenMP task construct to add support for reductions in while-loops and general-recursive algorithms. Further we discuss implications on the OpenMP standard and present a prototype implementation in OmpSs. Benchmark results confirm applicability of this approach and scalability on current SMP systems.
引用
收藏
页码：1 / 15
页数：15
相关论文
共 50 条
  • [1] Task-parallel reductions in OpenMP and OmpSs
    [J]. 1600, Springer Verlag (8766):
  • [2] Task-parallel reductions in openMP and OmpSs
    [J]. 1600, Springer Verlag (8766):
  • [3] Towards Task-Parallel Reductions in OpenMP
    Ciesko, Jan
    Mateo, Sergi
    Teruel, Xavier
    Martorell, Xavier
    Ayguade, Eduard
    Labarta, Jesus
    Duran, Alex
    de Supinski, Bronis R.
    Olivier, Stephen
    Li, Kelvin
    Eichenberger, Alexandre E.
    [J]. OPENMP: HETEROGENOUS EXECUTION AND DATA MOVEMENTS, IWOMP 2015, 2015, 9342 : 189 - 201
  • [4] Task-Parallel LU Factorization of Hierarchical Matrices using OmpSs
    Aliaga, Jose I.
    Carratala-Saez, Rocio
    Quintana-Orti, Enrique S.
    Krimann, Ronald
    [J]. 2017 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2017, : 1148 - 1157
  • [5] Communication in task-parallel ILU-preconditioned CG solvers using MPI plus OmpSs
    Aliaga, Jose I.
    Barreda, Maria
    Flegar, Goran
    Bollhoefer, Matthias
    Quintana-Orti, Enrique S.
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2017, 29 (21):
  • [6] CHAMELEON: Reactive Load Balancing for Hybrid MPI plus OpenMP Task-Parallel Applications
    Klinkenberg, Jannis
    Samfass, Philipp
    Bader, Michael
    Terboven, Christian
    Mueller, Matthias S.
    [J]. JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2020, 138 : 55 - 64
  • [7] Towards Unifying OpenMP Under the Task-Parallel Paradigm Implementation and Performance of the taskloop Construct
    Podobas, Artur
    Karlsson, Sven
    [J]. OpenMP: Memory, Devices, and Tasks, 2016, 9903 : 116 - 129
  • [8] Supporting Adaptive Privatization Techniques for Irregular Array Reductions in Task-Parallel Programming Models
    Ciesko, Jan
    Mateo, Sergi
    Teruel, Xavier
    Martorell, Xavier
    Ayguade, Eduard
    Labarta, Jesus
    [J]. OpenMP: Memory, Devices, and Tasks, 2016, 9903 : 336 - 349
  • [9] Performance modelling for task-parallel programs
    Kühnemann, M
    Rauber, T
    Rünger, G
    [J]. PERFORMANCE ANALYSIS AND GRID COMPUTING, 2004, : 77 - 91
  • [10] Task-Parallel Programming on NUMA Architectures
    Terboven, Christian
    Schmidl, Dirk
    Cramer, Tim
    Mey, Dieter An
    [J]. EURO-PAR 2012 PARALLEL PROCESSING, 2012, 7484 : 638 - 649
12345