Multi-core portability abstraction

Martti Forsell, Mikko Hiivala

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

Application portability between different multicore architecture-parallel programming paradigm/tool pairs is a big problem nowadays leading often to a complete rewrite of an application when switching from an architecture-paradigm pair to another. This is caused by a wide variety of architectural properties requiring different optimization techniques for different architectures, typically hiding the essence of (parallel) computation defined by the application. In this paper, we introduce the Multi-Core Portability Abstraction (MCPA) simplifying portability and implementation of parallel applications making use of shared memory. It abstracts away typical architecture dependent effects caused by latency, synchronization, and partitioning and acts as an executable intermediate abstraction/reference implementation as well as a tool for analyzing the intrinsic parallelism of the application and relative goodness of architectures in executing it. We give a short application example with performance measurements
Original languageEnglish
Title of host publicationProceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages778-785
ISBN (Print)978-1-4673-0974-5
DOIs
Publication statusPublished - 2012
MoE publication typeNot Eligible
Event26th International Parallel and Distributed Processing Symposium, IPDPSW 2012 - Shanghai, China
Duration: 21 May 201225 May 2012
Conference number: 26

Conference

Conference26th International Parallel and Distributed Processing Symposium, IPDPSW 2012
Abbreviated titleIPDPSW 2012
CountryChina
CityShanghai
Period21/05/1225/05/12

Fingerprint

Parallel programming
Synchronization
Data storage equipment

Keywords

  • Application portability
  • model of computation
  • multicore architectures
  • parallel computing
  • parallel programming

Cite this

Forsell, M., & Hiivala, M. (2012). Multi-core portability abstraction. In Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012 (pp. 778-785). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IPDPSW.2012.96
Forsell, Martti ; Hiivala, Mikko. / Multi-core portability abstraction. Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. Institute of Electrical and Electronic Engineers IEEE, 2012. pp. 778-785
@inproceedings{153b7a0b136a4d2a83ce0cd4bef433fe,
title = "Multi-core portability abstraction",
abstract = "Application portability between different multicore architecture-parallel programming paradigm/tool pairs is a big problem nowadays leading often to a complete rewrite of an application when switching from an architecture-paradigm pair to another. This is caused by a wide variety of architectural properties requiring different optimization techniques for different architectures, typically hiding the essence of (parallel) computation defined by the application. In this paper, we introduce the Multi-Core Portability Abstraction (MCPA) simplifying portability and implementation of parallel applications making use of shared memory. It abstracts away typical architecture dependent effects caused by latency, synchronization, and partitioning and acts as an executable intermediate abstraction/reference implementation as well as a tool for analyzing the intrinsic parallelism of the application and relative goodness of architectures in executing it. We give a short application example with performance measurements",
keywords = "Application portability, model of computation, multicore architectures, parallel computing, parallel programming",
author = "Martti Forsell and Mikko Hiivala",
year = "2012",
doi = "10.1109/IPDPSW.2012.96",
language = "English",
isbn = "978-1-4673-0974-5",
pages = "778--785",
booktitle = "Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Forsell, M & Hiivala, M 2012, Multi-core portability abstraction. in Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. Institute of Electrical and Electronic Engineers IEEE, pp. 778-785, 26th International Parallel and Distributed Processing Symposium, IPDPSW 2012, Shanghai, China, 21/05/12. https://doi.org/10.1109/IPDPSW.2012.96

Multi-core portability abstraction. / Forsell, Martti; Hiivala, Mikko.

Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. Institute of Electrical and Electronic Engineers IEEE, 2012. p. 778-785.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Multi-core portability abstraction

AU - Forsell, Martti

AU - Hiivala, Mikko

PY - 2012

Y1 - 2012

N2 - Application portability between different multicore architecture-parallel programming paradigm/tool pairs is a big problem nowadays leading often to a complete rewrite of an application when switching from an architecture-paradigm pair to another. This is caused by a wide variety of architectural properties requiring different optimization techniques for different architectures, typically hiding the essence of (parallel) computation defined by the application. In this paper, we introduce the Multi-Core Portability Abstraction (MCPA) simplifying portability and implementation of parallel applications making use of shared memory. It abstracts away typical architecture dependent effects caused by latency, synchronization, and partitioning and acts as an executable intermediate abstraction/reference implementation as well as a tool for analyzing the intrinsic parallelism of the application and relative goodness of architectures in executing it. We give a short application example with performance measurements

AB - Application portability between different multicore architecture-parallel programming paradigm/tool pairs is a big problem nowadays leading often to a complete rewrite of an application when switching from an architecture-paradigm pair to another. This is caused by a wide variety of architectural properties requiring different optimization techniques for different architectures, typically hiding the essence of (parallel) computation defined by the application. In this paper, we introduce the Multi-Core Portability Abstraction (MCPA) simplifying portability and implementation of parallel applications making use of shared memory. It abstracts away typical architecture dependent effects caused by latency, synchronization, and partitioning and acts as an executable intermediate abstraction/reference implementation as well as a tool for analyzing the intrinsic parallelism of the application and relative goodness of architectures in executing it. We give a short application example with performance measurements

KW - Application portability

KW - model of computation

KW - multicore architectures

KW - parallel computing

KW - parallel programming

U2 - 10.1109/IPDPSW.2012.96

DO - 10.1109/IPDPSW.2012.96

M3 - Conference article in proceedings

SN - 978-1-4673-0974-5

SP - 778

EP - 785

BT - Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Forsell M, Hiivala M. Multi-core portability abstraction. In Proceedings of the IEEE 26th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2012. Institute of Electrical and Electronic Engineers IEEE. 2012. p. 778-785 https://doi.org/10.1109/IPDPSW.2012.96