Approaches for Task Affinity in OpenMP

被引：7

作者：

Terboven, Christian ^{[1
]}

Hahnfeld, Jonas ^{[1
]}

Teruel, Xavier ^{[2
]}

Mateo, Sergi ^{[2
]}

Duran, Alejandro ^{[3
]}

Klemm, Michael ^{[3
]}

Olivier, Stephen L. ^{[4
]}

de Supinski, Bronis R. ^{[5
]}

机构：

[1] Rhein Westfal TH Aachen, IT Ctr, Chair High Performance Comp, Aachen, Germany

[2] Barcelona Supercomp Ctr, Barcelona, Spain

[3] Intel, Santa Clara, CA USA

[4] Sandia Natl Labs, Ctr Res Comp, Albuquerque, NM 87185 USA

[5] LLNL, Livermore, CA USA

来源：

OPENMP: MEMORY, DEVICES, AND TASKS | 2016年 / 9903卷

关键词：

D O I：

10.1007/978-3-319-45550-1_8

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

OpenMP tasking supports parallelization of irregular algorithms. Recent OpenMP specifications extended tasking to increase functionality and to support optimizations, for instance with the taskloop construct. However, task scheduling remains opaque, which leads to inconsistent performance on NUMA architectures. We assess design issues for task affinity and explore several approaches to enable it. We evaluate these proposals with implementations in the Nanos++ and LLVM OpenMP runtimes that improve performance up to 40% and significantly reduce execution time variation.

引用

页码：102 / 115

页数：14

共 50 条

[41] Evaluation of OpenMP Task Scheduling Algorithms for Large NUMA Architectures
Clet-Ortega, Jerome
Carribault, Patrick
Perache, Marc
EURO-PAR 2014 PARALLEL PROCESSING, 2014, 8632 : 596 - 607
[42] OpenMP Target Task: Tasking and Target Offloading on Heterogeneous Systems
Valero-Lara, Pedro
Kim, Jungwon
Hernandez, Oscar
Vetter, Jeffrey
EURO-PAR 2021: PARALLEL PROCESSING WORKSHOPS, 2022, 13098 : 445 - 455
[43] Exploiting Thread-Data Affinity in OpenMP with Data Access Patterns
Di Biagio, Andrea
Speziale, Ettore
Agosta, Giovanni
EURO-PAR 2011 PARALLEL PROCESSING, PT 1, 2011, 6852 : 230 - 241
[44] sOMP: Simulating OpenMP Task-Based Applications with NUMA Effects
Daoudi, Idriss
Virouleau, Philippe
Gautier, Thierry
Thibault, Samuel
Aumage, Olivier
OPENMP: PORTABLE MULTI-LEVEL PARALLELISM ON MODERN SYSTEMS, 2020, 12295 : 197 - 211
[45] Symmetric Indefinite Linear Solver Using OpenMP Task on Multicore Architectures
Yamazaki, Ichitaro
Kurzak, Jakub
Wu, Panruo
Zounon, Mawussi
Dongarra, Jack
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2018, 29 (08) : 1879 - 1892
[46] Static Coarse Grain Task Scheduling with Cache Optimization Using OpenMP
Hirofumi Nakano
Kazuhisa Ishizaka
Motoki Obata
Keiji Kimura
Hironori Kasahara
International Journal of Parallel Programming, 2003, 31 : 211 - 223
[47] Algorithms for Computing the WCRT Bound of OpenMP Task Systems With Conditional Branches
Sun, Jinghao
Guan, Nan
Sun, Jingchang
Zhang, Xi
Chi, Yaoyao
Li, Feng
IEEE TRANSACTIONS ON COMPUTERS, 2021, 70 (01) : 57 - 71
[48] Task-Based Cholesky Decomposition on Knights Corner Using OpenMP
Dorris, Joseph
Kurzak, Jakub
Luszczek, Piotr
YarKhan, Asim
Dongarra, Jack
HIGH PERFORMANCE COMPUTING, ISC HIGH PERFORMANCE 2016 INTERNATIONAL WORKSHOPS, 2016, 9945 : 544 - 562
[49] Characterizing the Performance of Task Reductions in OpenMP 5.X Implementations
Ciesko, Jan
Olivier, Stephen L.
OPENMP IN A MODERN WORLD: FROM MULTI-DEVICE SUPPORT TO META PROGRAMMING, 2022, 13527 : 35 - 49
[50] Partitioning-Based Scheduling of OpenMP Task Systems With Tied Tasks
Wang, Yang
Jiang, Xu
Guan, Nan
Guo, Zhishan
Liu, Xue
Yi, Wang
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2021, 32 (06) : 1322 - 1339

← 1 2 3 4 5 →