Cost-directed refactoring for parallel Erlang programs

Christopher Mark Brown; Marco Danelutto; Kevin Hammond; Peter Kilpatrick; Archibald Elliot

doi:10.1007/s10766-013-0266-5

Cost-directed refactoring for parallel Erlang programs

Christopher Mark Brown, Marco Danelutto, Kevin Hammond, Peter Kilpatrick, Archibald Elliot

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

Abstract

This paper introduces a new programming methodology for intro- ducing and tuning parallelism in Erlang programs, using source-level code refactoring from sequential source programs to parallel programs written us- ing our new skeleton library, Skel. High-level cost models allow us to predict with reasonable accuracy the parallel performance of the refactored program, enabling programmers to make informed decisions about which refactorings to apply. Using our approach, we are able to easily obtain significant and scal- able speedups of up to 21.39 on a 24-core machine over the original sequential code.

Original language	English
Title of host publication	Proc. International Symposium on High-level Parallel Programming and Applications
Publisher	Springer
Number of pages	17
DOIs	https://doi.org/10.1007/s10766-013-0266-5
Publication status	Published - Jun 2013

Publication series

Name	Lecture Notes in Computer Science

Keywords

Parallel Programming
Erlang
Software Refactoring
Skeletons
Cost Modelling

Access to Document

10.1007/s10766-013-0266-5

Cite this

@inproceedings{ae6b9bc0888945fe9b70011d77607042,

title = "Cost-directed refactoring for parallel Erlang programs",

abstract = "This paper introduces a new programming methodology for intro- ducing and tuning parallelism in Erlang programs, using source-level code refactoring from sequential source programs to parallel programs written us- ing our new skeleton library, Skel. High-level cost models allow us to predict with reasonable accuracy the parallel performance of the refactored program, enabling programmers to make informed decisions about which refactorings to apply. Using our approach, we are able to easily obtain significant and scal- able speedups of up to 21.39 on a 24-core machine over the original sequential code.",

keywords = "Parallel Programming, Erlang, Software Refactoring, Skeletons, Cost Modelling",

author = "Brown, \{Christopher Mark\} and Marco Danelutto and Kevin Hammond and Peter Kilpatrick and Archibald Elliot",

year = "2013",

month = jun,

doi = "10.1007/s10766-013-0266-5",

language = "English",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

booktitle = "Proc. International Symposium on High-level Parallel Programming and Applications",

address = "Netherlands",

}

TY - GEN

T1 - Cost-directed refactoring for parallel Erlang programs

AU - Brown, Christopher Mark

AU - Danelutto, Marco

AU - Hammond, Kevin

AU - Kilpatrick, Peter

AU - Elliot, Archibald

PY - 2013/6

Y1 - 2013/6

N2 - This paper introduces a new programming methodology for intro- ducing and tuning parallelism in Erlang programs, using source-level code refactoring from sequential source programs to parallel programs written us- ing our new skeleton library, Skel. High-level cost models allow us to predict with reasonable accuracy the parallel performance of the refactored program, enabling programmers to make informed decisions about which refactorings to apply. Using our approach, we are able to easily obtain significant and scal- able speedups of up to 21.39 on a 24-core machine over the original sequential code.

AB - This paper introduces a new programming methodology for intro- ducing and tuning parallelism in Erlang programs, using source-level code refactoring from sequential source programs to parallel programs written us- ing our new skeleton library, Skel. High-level cost models allow us to predict with reasonable accuracy the parallel performance of the refactored program, enabling programmers to make informed decisions about which refactorings to apply. Using our approach, we are able to easily obtain significant and scal- able speedups of up to 21.39 on a 24-core machine over the original sequential code.

KW - Parallel Programming

KW - Erlang

KW - Software Refactoring

KW - Skeletons

KW - Cost Modelling

UR - https://www.scopus.com/pages/publications/84902246590

U2 - 10.1007/s10766-013-0266-5

DO - 10.1007/s10766-013-0266-5

M3 - Conference contribution

T3 - Lecture Notes in Computer Science

BT - Proc. International Symposium on High-level Parallel Programming and Applications

PB - Springer

ER -

Cost-directed refactoring for parallel Erlang programs

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

ParaPhrase FP7-ICT-2011-7: EU FP7 'ParaPhrase'

FP7 ADVANCE: EU FP7 'Asynchronous and Dynamic Virtualisation through performance Analysis to support Concurrency Engineering 'ADVANCE'

EP/F030657/1 Adaptive Hardware Systems: Copy of Adaptive Hardware Systems with Novel Algorithmic Design and Guaranteed Resource Bounds

Cite this

Cost-directed refactoring for parallel Erlang programs

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ParaPhrase FP7-ICT-2011-7: EU FP7 'ParaPhrase'

FP7 ADVANCE: EU FP7 'Asynchronous and Dynamic Virtualisation through performance Analysis to support Concurrency Engineering 'ADVANCE'

EP/F030657/1 Adaptive Hardware Systems: Copy of Adaptive Hardware Systems with Novel Algorithmic Design and Guaranteed Resource Bounds

Cite this