Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang

Vladimir Janjic; Christopher Mark Brown; Kevin Hammond

doi:10.3233/978-1-61499-621-7-185

Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang

Vladimir Janjic, Christopher Mark Brown, Kevin Hammond

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

Abstract

We describe Lapedo, a novel library of hybrid parallel skeletons for programming heterogeneous multi-core/many-core CPU/GPU sys- tems in Erlang. Lapedo’s hybrid skeletons comprise a mixture of CPU and GPU components, allowing skeletons to be flexibly and dynamically mapped to available resources. We also describe a model for deriving near-optimal division of work between CPUs and GPUs, ensuring load balancing between resources. Finally, we evaluate the effectiveness of Lapedo on three realistic use cases from different domains, demonstrating significant speedups compared to executing the same application on only CPU cores or a GPU.

Original language	English
Title of host publication	Parallel Computing
Subtitle of host publication	On the Road to Exascale
Editors	Gerhard R Joubert, Hugh Leather, Mark Parsons, Frans Peters, Mark Sawyer
Publisher	IOS Press
Pages	185-195
ISBN (Print)	9781614996200, 9781614996217
DOIs	https://doi.org/10.3233/978-1-61499-621-7-185
Publication status	Published - Apr 2016
Event	International Conference on Parallel Computing (ParCo) 2015 - University of Edinburgh, Informatics Forum, Edinburgh, United Kingdom Duration: 1 Sept 2015 → 4 Sept 2015 http://www.parco2015.org/home

Publication series

Name	Advances in Parallel Computing
Volume	27

Conference

Conference	International Conference on Parallel Computing (ParCo) 2015
Country/Territory	United Kingdom
City	Edinburgh
Period	1/09/15 → 4/09/15
Internet address	http://www.parco2015.org/home

Keywords

Parallel skeletons
Heterogeneous systems
GPU Offloading

Access to Document

10.3233/978-1-61499-621-7-185

parco2015
© 2016, Publisher / the Author(s). This work is made available online in accordance with the publisher’s policies. This is the author created, accepted version manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at ebooks.iospress.nl / https://dx.doi.org/ 10.3233/978-1-61499-621-7-185
Accepted author manuscript, 312 KB

H2020 Collaboration REPHRASE: H2020 Collaboration 2014 - RePhrase
Hammond, K. (PI)
European Commission
1/04/15 → 31/03/18
Project: Standard
ParaPhrase 100% - FP7-ICT-2011-7: ParaPhrase 100%
Hammond, K. (PI)
European Commission
1/10/11 → 31/03/15
Project: Standard

Christopher Mark Brown
- cmb21st-andrews.acuk
- School of Computer Science - Lecturer
Person: Academic

Lapedo: Hybrid Skeletons for Programming Heterogeneous Multicore Machines in Erlang
Janjic, V. (Creator), Brown, C. M. (Contributor) & Hammond, K. (Contributor), Zenodo, 30 Sept 2015
DOI: 10.5281/zenodo.33204
Dataset

Cite this

@inproceedings{404f205a13364132abc576ef186d146c,

title = "Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang",

abstract = "We describe Lapedo, a novel library of hybrid parallel skeletons for programming heterogeneous multi-core/many-core CPU/GPU sys- tems in Erlang. Lapedo{\textquoteright}s hybrid skeletons comprise a mixture of CPU and GPU components, allowing skeletons to be flexibly and dynamically mapped to available resources. We also describe a model for deriving near-optimal division of work between CPUs and GPUs, ensuring load balancing between resources. Finally, we evaluate the effectiveness of Lapedo on three realistic use cases from different domains, demonstrating significant speedups compared to executing the same application on only CPU cores or a GPU.",

keywords = "Parallel skeletons, Heterogeneous systems, GPU Offloading",

author = "Vladimir Janjic and Brown, {Christopher Mark} and Kevin Hammond",

year = "2016",

month = apr,

doi = "10.3233/978-1-61499-621-7-185",

language = "English",

isbn = "9781614996200",

series = "Advances in Parallel Computing",

publisher = "IOS Press",

pages = "185--195",

editor = "Joubert, {Gerhard R} and Hugh Leather and Mark Parsons and Frans Peters and Mark Sawyer",

booktitle = "Parallel Computing",

address = "Netherlands",

note = "International Conference on Parallel Computing (ParCo) 2015 ; Conference date: 01-09-2015 Through 04-09-2015",

url = "http://www.parco2015.org/home",

}

Janjic, V, Brown, CM & Hammond, K 2016, Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang. in GR Joubert, H Leather, M Parsons, F Peters & M Sawyer (eds), Parallel Computing: On the Road to Exascale. Advances in Parallel Computing, vol. 27, IOS Press, pp. 185-195, International Conference on Parallel Computing (ParCo) 2015, Edinburgh, United Kingdom, 1/09/15. https://doi.org/10.3233/978-1-61499-621-7-185

Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang. / Janjic, Vladimir; Brown, Christopher Mark; Hammond, Kevin.
Parallel Computing: On the Road to Exascale. ed. / Gerhard R Joubert; Hugh Leather; Mark Parsons; Frans Peters; Mark Sawyer. IOS Press, 2016. p. 185-195 (Advances in Parallel Computing; Vol. 27).

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

TY - GEN

T1 - Lapedo

T2 - International Conference on Parallel Computing (ParCo) 2015

AU - Janjic, Vladimir

AU - Brown, Christopher Mark

AU - Hammond, Kevin

PY - 2016/4

Y1 - 2016/4

N2 - We describe Lapedo, a novel library of hybrid parallel skeletons for programming heterogeneous multi-core/many-core CPU/GPU sys- tems in Erlang. Lapedo’s hybrid skeletons comprise a mixture of CPU and GPU components, allowing skeletons to be flexibly and dynamically mapped to available resources. We also describe a model for deriving near-optimal division of work between CPUs and GPUs, ensuring load balancing between resources. Finally, we evaluate the effectiveness of Lapedo on three realistic use cases from different domains, demonstrating significant speedups compared to executing the same application on only CPU cores or a GPU.

AB - We describe Lapedo, a novel library of hybrid parallel skeletons for programming heterogeneous multi-core/many-core CPU/GPU sys- tems in Erlang. Lapedo’s hybrid skeletons comprise a mixture of CPU and GPU components, allowing skeletons to be flexibly and dynamically mapped to available resources. We also describe a model for deriving near-optimal division of work between CPUs and GPUs, ensuring load balancing between resources. Finally, we evaluate the effectiveness of Lapedo on three realistic use cases from different domains, demonstrating significant speedups compared to executing the same application on only CPU cores or a GPU.

KW - Parallel skeletons

KW - Heterogeneous systems

KW - GPU Offloading

U2 - 10.3233/978-1-61499-621-7-185

DO - 10.3233/978-1-61499-621-7-185

M3 - Conference contribution

SN - 9781614996200

SN - 9781614996217

T3 - Advances in Parallel Computing

SP - 185

EP - 195

BT - Parallel Computing

A2 - Joubert, Gerhard R

A2 - Leather, Hugh

A2 - Parsons, Mark

A2 - Peters, Frans

A2 - Sawyer, Mark

PB - IOS Press

Y2 - 1 September 2015 through 4 September 2015

ER -

Lapedo: hybrid skeletons for programming heterogeneous multicore machines in Erlang

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

H2020 Collaboration REPHRASE: H2020 Collaboration 2014 - RePhrase

ParaPhrase 100% - FP7-ICT-2011-7: ParaPhrase 100%

Profiles

Christopher Mark Brown

Datasets

Lapedo: Hybrid Skeletons for Programming Heterogeneous Multicore Machines in Erlang

Cite this