A taxonomy of task-based parallel programming technologies for high-performance computing

被引：79

作者：

Thoman, Peter ^{[1
]}

Dichev, Kiril ^{[2
]}

Heller, Thomas ^{[3
]}

Iakymchuk, Roman ^{[4
]}

Aguilar, Xavier ^{[4
]}

Hasanov, Khalid ^{[5
]}

Gschwandtner, Philipp ^{[1
]}

Lemarinier, Pierre ^{[5
]}

Markidis, Stefano ^{[4
]}

Jordan, Herbert ^{[1
]}

Fahringer, Thomas ^{[1
]}

Katrinis, Kostas ^{[5
]}

Laure, Erwin ^{[4
]}

Nikolopoulos, Dimitrios S. ^{[2
]}

机构：

[1] Univ Innsbruck, A-6020 Innsbruck, Austria

[2] Queens Univ Belfast, Belfast BT7 1NN, Antrim, North Ireland

[3] Univ Erlangen Nurnberg, D-91058 Erlangen, Germany

[4] KTH Royal Inst Technol, S-10044 Stockholm, Sweden

[5] IBM Ireland, Dublin 15, Ireland

来源：

JOURNAL OF SUPERCOMPUTING | 2018年 / 74卷 / 04期

基金：

英国工程与自然科学研究理事会;

关键词：

High-performance computing; Task-based parallelism; Taxonomy; API; Runtime system; Scheduler; Monitoring framework; Fault tolerance; CILK;

D O I：

10.1007/s11227-018-2238-4

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Task-based programming models for shared memory-such as Cilk Plus and OpenMP 3-are well established and documented. However, with the increase in parallel, many-core, and heterogeneous systems, a number of research-driven projects have developed more diversified task-based support, employing various programming and runtime features. Unfortunately, despite the fact that dozens of different task-based systems exist today and are actively used for parallel and high-performance computing (HPC), no comprehensive overview or classification of task-based technologies for HPC exists. In this paper, we provide an initial task-focused taxonomy for HPC technologies, which covers both programming interfaces and runtime mechanisms. We demonstrate the usefulness of our taxonomy by classifying state-of-the-art task-based environments in use today.

引用

页码：1422 / 1434

页数：13

共 50 条

[21] Managing Failures in Task-Based Parallel Workflows in Distributed Computing Environments
Ejarque, Jorge
Bertran, Marta
Cid-Fuentes, Javier Alvarez
Conejero, Javier
Badia, Rosa M.
[J]. EURO-PAR 2020: PARALLEL PROCESSING, 2020, 12247 : 411 - 425
[22] High-performance parallel computing in industry
Eldredge, M
Hughes, TJR
Ferencz, RM
Rifai, SM
Raefsky, A
Herndon, B
[J]. PARALLEL COMPUTING, 1997, 23 (09) : 1217 - 1233
[23] Adaptive Task-Based Intermittent Computing System With Parallel State Backup
Zhang, Wei
Zhang, Qianling
Lv, Mingsong
Liu, Songran
Zhou, Zimeng
Chen, Qiulin
Guan, Nan
Ju, Lei
[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 42 (06) : 1798 - 1809
[24] Assessing Saiph, a task-based DSL for high-performance computational fluid dynamics
Macia, Sandra
Martinez-Ferrer, Pedro J.
Ayguade, Eduard
Beltran, Vicenc
[J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2023, 147 : 235 - 250
[25] A high-productivity task-based programming model for clusters
Tejedor, Enric
Farreras, Montse
Grove, David
Badia, Rosa M.
Almasi, Gheorghe
Labarta, Jesus
[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2012, 24 (18): : 2421 - 2448
[26] Survey of Methodologies, Approaches, and Challenges in Parallel Programming Using High-Performance Computing Systems
Czarnul, Pawel
Proficz, Jerzy
Drypczewski, Krzysztof
[J]. SCIENTIFIC PROGRAMMING, 2020, 2020
[27] Programming for High-Performance Computing on Edge Accelerators
Kang, Pilsung
[J]. MATHEMATICS, 2023, 11 (04)
[28] A task-based taxonomy of erroneous human behavior
Bolton, Matthew L.
[J]. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES, 2017, 108 : 105 - 121
[29] High-performance task distribution for volunteer computing
Anderson, DP
Korpela, E
Walton, R
[J]. First International Conference on e-Science and Grid Computing, Proceedings, 2005, : 196 - 203
[30] HIERARCHICAL TASK-BASED PROGRAMMING WITH STARSS
Planas, Judit
Badia, Rosa M.
Ayguade, Eduard
Labarta, Jesus
[J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2009, 23 (03): : 284 - 299

← 1 2 3 4 5 →