Targeting heterogeneous architectures via macro data flow

M. Aldinucci; M. Danelutto; P. Kilpatrick; M. Torquati

doi:10.1142/S0129626412400063

Targeting heterogeneous architectures via macro data flow

M. Aldinucci, M. Danelutto, P. Kilpatrick, M. Torquati

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more "domain specific" programming models. Experimental results demonstrating the feasibility of the approach are presented. © 2012 World Scientific Publishing Company.

Original language	English
Article number	1240006
Pages (from-to)	1-12
Number of pages	12
Journal	Parallel Processing Letters
Volume	22
Issue number	2
DOIs	https://doi.org/10.1142/S0129626412400063
Publication status	Published - 01 Jun 2012

ASJC Scopus subject areas

Hardware and Architecture
Software
Theoretical Computer Science

Access to Document

10.1142/S0129626412400063

Cite this

@article{12523f14038c4c90be8042856502f4b5,

title = "Targeting heterogeneous architectures via macro data flow",

abstract = "We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more {"}domain specific{"} programming models. Experimental results demonstrating the feasibility of the approach are presented. {\textcopyright} 2012 World Scientific Publishing Company.",

author = "M. Aldinucci and M. Danelutto and P. Kilpatrick and M. Torquati",

year = "2012",

month = jun,

day = "1",

doi = "10.1142/S0129626412400063",

language = "English",

volume = "22",

pages = "1--12",

journal = "Parallel Processing Letters",

publisher = "World Scientific",

number = "2",

}

TY - JOUR

T1 - Targeting heterogeneous architectures via macro data flow

AU - Aldinucci, M.

AU - Danelutto, M.

AU - Kilpatrick, P.

AU - Torquati, M.

PY - 2012/6/1

Y1 - 2012/6/1

N2 - We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more "domain specific" programming models. Experimental results demonstrating the feasibility of the approach are presented. © 2012 World Scientific Publishing Company.

AB - We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more "domain specific" programming models. Experimental results demonstrating the feasibility of the approach are presented. © 2012 World Scientific Publishing Company.

UR - http://www.scopus.com/inward/record.url?partnerID=yv4JPVwI&eid=2-s2.0-84862059433&md5=018b7b0acf423a275d68cdf204c7c501

U2 - 10.1142/S0129626412400063

DO - 10.1142/S0129626412400063

M3 - Article

VL - 22

SP - 1

EP - 12

JO - Parallel Processing Letters

JF - Parallel Processing Letters

IS - 2

M1 - 1240006

ER -

Targeting heterogeneous architectures via macro data flow

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this