Distributed Memory Programming on Many-Cores: A Case Study Using Eden Divide-&-Conquer Skeletons

Jost Berthold; Mischa Dieterle; Oleg Lobachev; Rita Loogen

Distributed Memory Programming on Many-Cores: A Case Study Using Eden Divide-&-Conquer Skeletons

Jost Berthold, Mischa Dieterle, Oleg Lobachev, Rita Loogen

Department of Computer Science

Abstract

Eden is a parallel extension of the lazy functional language Haskell providing dynamic process creation and automatic data exchange. As a Haskell extension, Eden takes a high-level approach to parallel programming and thereby simplifies parallel program development. The current implementation is tailored to networks of workstations. Recent work has shown that this implementation shows surprisingly competitive performance on many-core machines, compared to dedicated shared-memory implementations of parallel Haskell. In the paper we describe a case study with different Eden divide-and-conquer skeletons. We analyse their performance comparing example applications implemented using these Eden skeletons against parallel Haskell implementations using shared memory on many-core machines

Original language	English
Title of host publication	ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Workshop proceedings
Editors	K.E. Großpitsch, A. Henkersdorf, T. Ungerer, J. Hähner
Number of pages	9
Publisher	VDE Verlag
Publication date	2009
Pages	47-56
ISBN (Print)	978-3-8007-3133-6
Publication status	Published - 2009
Event	ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Delft, Netherlands Duration: 10 Mar 2009 → 13 Mar 2009 Conference number: 22

Conference

Conference	ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009
Number	22
Country/Territory	Netherlands
City	Delft
Period	10/03/2009 → 13/03/2009

Cite this

Distributed Memory Programming on Many-Cores : A Case Study Using Eden Divide-&-Conquer Skeletons. / Berthold, Jost; Dieterle, Mischa; Lobachev, Oleg et al.

ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Workshop proceedings. ed. / K.E. Großpitsch; A. Henkersdorf; T. Ungerer; J. Hähner. VDE Verlag, 2009. p. 47-56.

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

Berthold, J, Dieterle, M, Lobachev, O & Loogen, R 2009, Distributed Memory Programming on Many-Cores: A Case Study Using Eden Divide-&-Conquer Skeletons. in KE Großpitsch, A Henkersdorf, T Ungerer & J Hähner (eds), ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Workshop proceedings. VDE Verlag, pp. 47-56, ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009, Delft, Netherlands, 10/03/2009.

@inproceedings{3e1080d0fae411de825d000ea68e967b,

title = "Distributed Memory Programming on Many-Cores: A Case Study Using Eden Divide-&-Conquer Skeletons",

abstract = "Eden is a parallel extension of the lazy functional language Haskell providing dynamic process creation and automatic data exchange. As a Haskell extension, Eden takes a high-level approach to parallel programming and thereby simplifies parallel program development. The current implementation is tailored to networks of workstations. Recent work has shown that this implementation shows surprisingly competitive performance on many-core machines, compared to dedicated shared-memory implementations of parallel Haskell. In the paper we describe a case study with different Eden divide-and-conquer skeletons. We analyse their performance comparing example applications implemented using these Eden skeletons against parallel Haskell implementations using shared memory on many-core machines",

author = "Jost Berthold and Mischa Dieterle and Oleg Lobachev and Rita Loogen",

year = "2009",

language = "English",

isbn = "978-3-8007-3133-6",

pages = "47--56",

editor = "K.E. Gro{\ss}pitsch and A. Henkersdorf and T. Ungerer and J. H{\"a}hner",

booktitle = "ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Workshop proceedings",

publisher = "VDE Verlag",

note = "ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 ; Conference date: 10-03-2009 Through 13-03-2009",

}

TY - GEN

T1 - Distributed Memory Programming on Many-Cores

T2 - ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009

AU - Berthold, Jost

AU - Dieterle, Mischa

AU - Lobachev, Oleg

AU - Loogen, Rita

N1 - Conference code: 22

PY - 2009

Y1 - 2009

N2 - Eden is a parallel extension of the lazy functional language Haskell providing dynamic process creation and automatic data exchange. As a Haskell extension, Eden takes a high-level approach to parallel programming and thereby simplifies parallel program development. The current implementation is tailored to networks of workstations. Recent work has shown that this implementation shows surprisingly competitive performance on many-core machines, compared to dedicated shared-memory implementations of parallel Haskell. In the paper we describe a case study with different Eden divide-and-conquer skeletons. We analyse their performance comparing example applications implemented using these Eden skeletons against parallel Haskell implementations using shared memory on many-core machines

AB - Eden is a parallel extension of the lazy functional language Haskell providing dynamic process creation and automatic data exchange. As a Haskell extension, Eden takes a high-level approach to parallel programming and thereby simplifies parallel program development. The current implementation is tailored to networks of workstations. Recent work has shown that this implementation shows surprisingly competitive performance on many-core machines, compared to dedicated shared-memory implementations of parallel Haskell. In the paper we describe a case study with different Eden divide-and-conquer skeletons. We analyse their performance comparing example applications implemented using these Eden skeletons against parallel Haskell implementations using shared memory on many-core machines

M3 - Article in proceedings

SN - 978-3-8007-3133-6

SP - 47

EP - 56

BT - ARCS '09 - 22th International Conference on Architecture of Computing Systems 2009 - Workshop proceedings

A2 - Großpitsch, K.E.

A2 - Henkersdorf, A.

A2 - Ungerer, T.

A2 - Hähner, J.

PB - VDE Verlag

Y2 - 10 March 2009 through 13 March 2009

ER -

Distributed Memory Programming on Many-Cores: A Case Study Using Eden Divide-&-Conquer Skeletons

Abstract

Conference

Fingerprint

Cite this