Dynamic task discovery in PaRSEC- A data-flow task-based runtime

Reazul Hoque; Thomas Herault; George Bosilca; Jack Dongarra

doi:10.1145/3148226.3148233

Dynamic task discovery in PaRSEC- A data-flow task-based runtime

Reazul Hoque, Thomas Herault, George Bosilca, Jack Dongarra

Computer Science and Mathematics Div

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

49 Scopus citations

Abstract

Successfully exploiting distributed collections of heterogeneous many-cores architectures with complex memory hierarchy through a portable programming model is a challenge for application developers. The literature is not short of proposals addressing this problem, including many evolutionary solutions that seek to extend the capabilities of current message passing paradigms with intranode features (MPI+X). A different, more revolutionary, solution explores data-flow task-based runtime systems as a substitute to both local and distributed data dependencies management. The solution explored in this paper, PaRSEC, is based on such a programming paradigm, supported by a highly efficient task-based runtime. This paper compares two programming paradigms present in PaRSEC, Parameterized Task Graph (PTG) and Dynamic Task Discovery (DTD) in terms of capabilities, overhead and potential benefits.

Original language	English
Title of host publication	Proceedings of ScalA 2017
Subtitle of host publication	8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Association for Computing Machinery, Inc
ISBN (Print)	9781450351256
DOIs	https://doi.org/10.1145/3148226.3148233
State	Published - Nov 12 2017
Event	8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017 - Denver, United States Duration: Nov 12 2017 → Nov 17 2017

Publication series

Name	Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017
Country/Territory	United States
City	Denver
Period	11/12/17 → 11/17/17

Funding

This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the U.S. Department of Energy Office of Science and the National Nuclear Security Administration.

Funders	Funder number
U.S. Department of Energy Office of Science
National Nuclear Security Administration

Keywords

Data-flow
Dynamic task-graph
PaRSEC
Task-based runtime

Access to Document

10.1145/3148226.3148233

Cite this

Hoque, R., Herault, T., Bosilca, G., & Dongarra, J. (2017). Dynamic task discovery in PaRSEC- A data-flow task-based runtime. In Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis Article 3148233 (Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis). Association for Computing Machinery, Inc. https://doi.org/10.1145/3148226.3148233

Hoque, Reazul ; Herault, Thomas ; Bosilca, George et al. / Dynamic task discovery in PaRSEC- A data-flow task-based runtime. Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, Inc, 2017. (Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{75375a87ffe9414fb67e18c00cb776e3,

title = "Dynamic task discovery in PaRSEC- A data-flow task-based runtime",

abstract = "Successfully exploiting distributed collections of heterogeneous many-cores architectures with complex memory hierarchy through a portable programming model is a challenge for application developers. The literature is not short of proposals addressing this problem, including many evolutionary solutions that seek to extend the capabilities of current message passing paradigms with intranode features (MPI+X). A different, more revolutionary, solution explores data-flow task-based runtime systems as a substitute to both local and distributed data dependencies management. The solution explored in this paper, PaRSEC, is based on such a programming paradigm, supported by a highly efficient task-based runtime. This paper compares two programming paradigms present in PaRSEC, Parameterized Task Graph (PTG) and Dynamic Task Discovery (DTD) in terms of capabilities, overhead and potential benefits.",

keywords = "Data-flow, Dynamic task-graph, PaRSEC, Task-based runtime",

author = "Reazul Hoque and Thomas Herault and George Bosilca and Jack Dongarra",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017 ; Conference date: 12-11-2017 Through 17-11-2017",

year = "2017",

month = nov,

day = "12",

doi = "10.1145/3148226.3148233",

language = "English",

isbn = "9781450351256",

series = "Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of ScalA 2017",

}

Hoque, R, Herault, T, Bosilca, G & Dongarra, J 2017, Dynamic task discovery in PaRSEC- A data-flow task-based runtime. in Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis., 3148233, Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis, Association for Computing Machinery, Inc, 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017, Denver, United States, 11/12/17. https://doi.org/10.1145/3148226.3148233

Dynamic task discovery in PaRSEC- A data-flow task-based runtime. / Hoque, Reazul; Herault, Thomas; Bosilca, George et al.
Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, Inc, 2017. 3148233 (Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dynamic task discovery in PaRSEC- A data-flow task-based runtime

AU - Hoque, Reazul

AU - Herault, Thomas

AU - Bosilca, George

AU - Dongarra, Jack

PY - 2017/11/12

Y1 - 2017/11/12

N2 - Successfully exploiting distributed collections of heterogeneous many-cores architectures with complex memory hierarchy through a portable programming model is a challenge for application developers. The literature is not short of proposals addressing this problem, including many evolutionary solutions that seek to extend the capabilities of current message passing paradigms with intranode features (MPI+X). A different, more revolutionary, solution explores data-flow task-based runtime systems as a substitute to both local and distributed data dependencies management. The solution explored in this paper, PaRSEC, is based on such a programming paradigm, supported by a highly efficient task-based runtime. This paper compares two programming paradigms present in PaRSEC, Parameterized Task Graph (PTG) and Dynamic Task Discovery (DTD) in terms of capabilities, overhead and potential benefits.

AB - Successfully exploiting distributed collections of heterogeneous many-cores architectures with complex memory hierarchy through a portable programming model is a challenge for application developers. The literature is not short of proposals addressing this problem, including many evolutionary solutions that seek to extend the capabilities of current message passing paradigms with intranode features (MPI+X). A different, more revolutionary, solution explores data-flow task-based runtime systems as a substitute to both local and distributed data dependencies management. The solution explored in this paper, PaRSEC, is based on such a programming paradigm, supported by a highly efficient task-based runtime. This paper compares two programming paradigms present in PaRSEC, Parameterized Task Graph (PTG) and Dynamic Task Discovery (DTD) in terms of capabilities, overhead and potential benefits.

KW - Data-flow

KW - Dynamic task-graph

KW - PaRSEC

KW - Task-based runtime

UR - http://www.scopus.com/inward/record.url?scp=85044437718&partnerID=8YFLogxK

U2 - 10.1145/3148226.3148233

DO - 10.1145/3148226.3148233

M3 - Conference contribution

AN - SCOPUS:85044437718

SN - 9781450351256

T3 - Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis

BT - Proceedings of ScalA 2017

PB - Association for Computing Machinery, Inc

T2 - 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017

Y2 - 12 November 2017 through 17 November 2017

ER -

Hoque R, Herault T, Bosilca G, Dongarra J. Dynamic task discovery in PaRSEC- A data-flow task-based runtime. In Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, Inc. 2017. 3148233. (Proceedings of ScalA 2017: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1145/3148226.3148233

Dynamic task discovery in PaRSEC- A data-flow task-based runtime

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this