Hierarchically tiled arrays for parallelism and locality

Guo Jia; Ganesh Bikshandi; Daniel Hoeflinger; Gheorghe Almasi; Basilio Fraguela; María Jesús Garzarán; David Padua; Christoph Von Praunt

doi:10.1109/IPDPS.2006.1639573

Hierarchically tiled arrays for parallelism and locality

Guo Jia, Ganesh Bikshandi, Daniel Hoeflinger, Gheorghe Almasi, Basilio Fraguela, María Jesús Garzarán, David Padua, Christoph Von Praunt

Computer Science

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

Abstract

Parallel programming is facilitated by constructs which, unlike the widely used SPMD paradigm, provide programmers with a global view of the code and data structures. These constructs could be compiler directives containing information about data and task distribution, language extensions specifically designed for parallel computation, or classes that encapsulate parallelism. In this paper, we describe a class developed at Illinois and its MATLAB implementation. This class can be used to conveniently express both parallelism and locality. A C++ implementation is now underway. Its characteristics will be reported in a future paper. We have implemented most of the NAS benchmarks using our HTA MATLAB extensions and found during that HTAs enable the fast prototyping of parallel algorithms and produce programs that are easy to understand and maintain.

Original language	English (US)
Title of host publication	20th International Parallel and Distributed Processing Symposium, IPDPS 2006
Publisher	IEEE Computer Society
ISBN (Print)	1424400546, 9781424400546
DOIs	https://doi.org/10.1109/IPDPS.2006.1639573
State	Published - Jan 1 2006
Event	20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006 - Rhodes Island, Greece Duration: Apr 25 2006 → Apr 29 2006

Publication series

Name	20th International Parallel and Distributed Processing Symposium, IPDPS 2006
Volume	2006

Other

Other	20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006
Country	Greece
City	Rhodes Island
Period	4/25/06 → 4/29/06

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/IPDPS.2006.1639573

Fingerprint Dive into the research topics of 'Hierarchically tiled arrays for parallelism and locality'. Together they form a unique fingerprint.

Cite this

Jia, G., Bikshandi, G., Hoeflinger, D., Almasi, G., Fraguela, B., Garzarán, M. J., Padua, D., & Von Praunt, C. (2006). Hierarchically tiled arrays for parallelism and locality. In 20th International Parallel and Distributed Processing Symposium, IPDPS 2006 [1639573] (20th International Parallel and Distributed Processing Symposium, IPDPS 2006; Vol. 2006). IEEE Computer Society. https://doi.org/10.1109/IPDPS.2006.1639573

Hierarchically tiled arrays for parallelism and locality. / Jia, Guo; Bikshandi, Ganesh; Hoeflinger, Daniel; Almasi, Gheorghe; Fraguela, Basilio; Garzarán, María Jesús ; Padua, David; Von Praunt, Christoph.

20th International Parallel and Distributed Processing Symposium, IPDPS 2006. IEEE Computer Society, 2006. 1639573 (20th International Parallel and Distributed Processing Symposium, IPDPS 2006; Vol. 2006).

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

Jia, G, Bikshandi, G, Hoeflinger, D, Almasi, G, Fraguela, B, Garzarán, MJ , Padua, D & Von Praunt, C 2006, Hierarchically tiled arrays for parallelism and locality. in 20th International Parallel and Distributed Processing Symposium, IPDPS 2006., 1639573, 20th International Parallel and Distributed Processing Symposium, IPDPS 2006, vol. 2006, IEEE Computer Society, 20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006, Rhodes Island, Greece, 4/25/06. https://doi.org/10.1109/IPDPS.2006.1639573

Jia G, Bikshandi G, Hoeflinger D, Almasi G, Fraguela B, Garzarán MJ et al. Hierarchically tiled arrays for parallelism and locality. In 20th International Parallel and Distributed Processing Symposium, IPDPS 2006. IEEE Computer Society. 2006. 1639573. (20th International Parallel and Distributed Processing Symposium, IPDPS 2006). https://doi.org/10.1109/IPDPS.2006.1639573

Jia, Guo ; Bikshandi, Ganesh ; Hoeflinger, Daniel ; Almasi, Gheorghe ; Fraguela, Basilio ; Garzarán, María Jesús ; Padua, David ; Von Praunt, Christoph. / Hierarchically tiled arrays for parallelism and locality. 20th International Parallel and Distributed Processing Symposium, IPDPS 2006. IEEE Computer Society, 2006. (20th International Parallel and Distributed Processing Symposium, IPDPS 2006).

@inproceedings{7a8c5beccda442a2b8819552f9579db6,

title = "Hierarchically tiled arrays for parallelism and locality",

abstract = "Parallel programming is facilitated by constructs which, unlike the widely used SPMD paradigm, provide programmers with a global view of the code and data structures. These constructs could be compiler directives containing information about data and task distribution, language extensions specifically designed for parallel computation, or classes that encapsulate parallelism. In this paper, we describe a class developed at Illinois and its MATLAB implementation. This class can be used to conveniently express both parallelism and locality. A C++ implementation is now underway. Its characteristics will be reported in a future paper. We have implemented most of the NAS benchmarks using our HTA MATLAB extensions and found during that HTAs enable the fast prototyping of parallel algorithms and produce programs that are easy to understand and maintain.",

author = "Guo Jia and Ganesh Bikshandi and Daniel Hoeflinger and Gheorghe Almasi and Basilio Fraguela and Garzar{\'a}n, {Mar{\'i}a Jes{\'u}s} and David Padua and {Von Praunt}, Christoph",

year = "2006",

month = jan,

day = "1",

doi = "10.1109/IPDPS.2006.1639573",

language = "English (US)",

isbn = "1424400546",

series = "20th International Parallel and Distributed Processing Symposium, IPDPS 2006",

publisher = "IEEE Computer Society",

booktitle = "20th International Parallel and Distributed Processing Symposium, IPDPS 2006",

note = "20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006 ; Conference date: 25-04-2006 Through 29-04-2006",

}

TY - GEN

T1 - Hierarchically tiled arrays for parallelism and locality

AU - Jia, Guo

AU - Bikshandi, Ganesh

AU - Hoeflinger, Daniel

AU - Almasi, Gheorghe

AU - Fraguela, Basilio

AU - Garzarán, María Jesús

AU - Padua, David

AU - Von Praunt, Christoph

PY - 2006/1/1

Y1 - 2006/1/1

N2 - Parallel programming is facilitated by constructs which, unlike the widely used SPMD paradigm, provide programmers with a global view of the code and data structures. These constructs could be compiler directives containing information about data and task distribution, language extensions specifically designed for parallel computation, or classes that encapsulate parallelism. In this paper, we describe a class developed at Illinois and its MATLAB implementation. This class can be used to conveniently express both parallelism and locality. A C++ implementation is now underway. Its characteristics will be reported in a future paper. We have implemented most of the NAS benchmarks using our HTA MATLAB extensions and found during that HTAs enable the fast prototyping of parallel algorithms and produce programs that are easy to understand and maintain.

AB - Parallel programming is facilitated by constructs which, unlike the widely used SPMD paradigm, provide programmers with a global view of the code and data structures. These constructs could be compiler directives containing information about data and task distribution, language extensions specifically designed for parallel computation, or classes that encapsulate parallelism. In this paper, we describe a class developed at Illinois and its MATLAB implementation. This class can be used to conveniently express both parallelism and locality. A C++ implementation is now underway. Its characteristics will be reported in a future paper. We have implemented most of the NAS benchmarks using our HTA MATLAB extensions and found during that HTAs enable the fast prototyping of parallel algorithms and produce programs that are easy to understand and maintain.

UR - http://www.scopus.com/inward/record.url?scp=33847108581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847108581&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2006.1639573

DO - 10.1109/IPDPS.2006.1639573

M3 - Conference contribution

AN - SCOPUS:33847108581

SN - 1424400546

SN - 9781424400546

T3 - 20th International Parallel and Distributed Processing Symposium, IPDPS 2006

BT - 20th International Parallel and Distributed Processing Symposium, IPDPS 2006

PB - IEEE Computer Society

T2 - 20th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2006

Y2 - 25 April 2006 through 29 April 2006

ER -