Imperial College London
Alternate

ProfessorPaulKelly

Faculty of Engineering, Department of Computing

Professor of Software Technology
 
 
 
//

Contact

 

+44 (0)20 7594 8332p.kelly Website

 
 
//

Location

 

Level 3 (upstairs), William Penney Building, room 304William Penney LaboratorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Unat:2017:10.1109/TPDS.2017.2703149,
author = {Unat, D and Dubey, A and Hoefler, T and Shalf, J and Abraham, M and Bianco, M and Chamberlain, BL and Cledat, R and Edwards, HC and Finkel, H and Fuerlinger, K and Hannig, F and Jeannot, E and Kamil, A and Keasler, J and Kelly, PHJ and Leung, V and Ltaief, H and Maruyama, N and Newburn, CJ and Pericas, M},
doi = {10.1109/TPDS.2017.2703149},
journal = {IEEE Transactions on Parallel and Distributed Systems},
pages = {3007--3020},
title = {Trends in Data Locality Abstractions for HPC Systems},
url = {http://dx.doi.org/10.1109/TPDS.2017.2703149},
volume = {28},
year = {2017}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The cost of data movement has always been an important concern in high performance computing (HPC) systems. It has now become the dominant factor in terms of both energy consumption and performance. Support for expression of data locality has been explored in the past, but those efforts have had only modest success in being adopted in HPC applications for various reasons. them However, with the increasing complexity of the memory hierarchy and higher parallelism in emerging HPC systems, locality management has acquired a new urgency. Developers can no longer limit themselves to low-level solutions and ignore the potential for productivity and performance portability obtained by using locality abstractions. Fortunately, the trend emerging in recent literature on the topic alleviates many of the concerns that got in the way of their adoption by application developers. Data locality abstractions are available in the forms of libraries, data structures, languages and runtime systems; a common theme is increasing productivity without sacrificing performance. This paper examines these trends and identifies commonalities that can combine various locality concepts to develop a comprehensive approach to expressing and managing data locality on future large-scale high-performance computing systems.
AU  - Unat,D
AU  - Dubey,A
AU  - Hoefler,T
AU  - Shalf,J
AU  - Abraham,M
AU  - Bianco,M
AU  - Chamberlain,BL
AU  - Cledat,R
AU  - Edwards,HC
AU  - Finkel,H
AU  - Fuerlinger,K
AU  - Hannig,F
AU  - Jeannot,E
AU  - Kamil,A
AU  - Keasler,J
AU  - Kelly,PHJ
AU  - Leung,V
AU  - Ltaief,H
AU  - Maruyama,N
AU  - Newburn,CJ
AU  - Pericas,M
DO  - 10.1109/TPDS.2017.2703149
EP  - 3020
PY  - 2017///
SN  - 1045-9219
SP  - 3007
TI  - Trends in Data Locality Abstractions for HPC Systems
T2  - IEEE Transactions on Parallel and Distributed Systems
UR  - http://dx.doi.org/10.1109/TPDS.2017.2703149
UR  - http://hdl.handle.net/10044/1/52117
VL  - 28
ER  -
Download