Bringing high performance computing to big data algorithms

H. Anzt; J. Dongarra; M. Gates; J. Kurzak; P. Luszczek; S. Tomov; I. Yamazaki

doi:10.1007/978-3-319-49340-4_23

Bringing high performance computing to big data algorithms

H. Anzt
, J. Dongarra
, M. Gates
, J. Kurzak
, P. Luszczek
, S. Tomov
, I. Yamazaki

Computer Science and Mathematics Div

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

5 Scopus citations

Abstract

Many ideas of High Performance Computing are applicable to Big Data problems. The more so now, that hybrid, GPU computing gains traction in mainstream computing applications. This work discusses the differences between the High Performance Computing software stack and the Big Data software stack and then focuses on two popular computing workloads, the Alternating Least Squares algorithm and the Singular Value Decomposition, and shows how their performance can be maximized using hybrid computing techniques.

Original language	English
Title of host publication	Handbook of Big Data Technologies
Publisher	Springer International Publishing
Pages	777-806
Number of pages	30
ISBN (Electronic)	9783319493404
ISBN (Print)	9783319493398
DOIs	https://doi.org/10.1007/978-3-319-49340-4_23
State	Published - Feb 25 2017

Access to Document

10.1007/978-3-319-49340-4_23

Cite this

@inbook{5204969f266d4b9e8fcad338e1cd8817,

title = "Bringing high performance computing to big data algorithms",

abstract = "Many ideas of High Performance Computing are applicable to Big Data problems. The more so now, that hybrid, GPU computing gains traction in mainstream computing applications. This work discusses the differences between the High Performance Computing software stack and the Big Data software stack and then focuses on two popular computing workloads, the Alternating Least Squares algorithm and the Singular Value Decomposition, and shows how their performance can be maximized using hybrid computing techniques.",

author = "H. Anzt and J. Dongarra and M. Gates and J. Kurzak and P. Luszczek and S. Tomov and I. Yamazaki",

year = "2017",

month = feb,

day = "25",

doi = "10.1007/978-3-319-49340-4\_23",

language = "English",

isbn = "9783319493398",

pages = "777--806",

booktitle = "Handbook of Big Data Technologies",

publisher = "Springer International Publishing",

}

TY - CHAP

T1 - Bringing high performance computing to big data algorithms

AU - Anzt, H.

AU - Dongarra, J.

AU - Gates, M.

AU - Kurzak, J.

AU - Luszczek, P.

AU - Tomov, S.

AU - Yamazaki, I.

PY - 2017/2/25

Y1 - 2017/2/25

N2 - Many ideas of High Performance Computing are applicable to Big Data problems. The more so now, that hybrid, GPU computing gains traction in mainstream computing applications. This work discusses the differences between the High Performance Computing software stack and the Big Data software stack and then focuses on two popular computing workloads, the Alternating Least Squares algorithm and the Singular Value Decomposition, and shows how their performance can be maximized using hybrid computing techniques.

AB - Many ideas of High Performance Computing are applicable to Big Data problems. The more so now, that hybrid, GPU computing gains traction in mainstream computing applications. This work discusses the differences between the High Performance Computing software stack and the Big Data software stack and then focuses on two popular computing workloads, the Alternating Least Squares algorithm and the Singular Value Decomposition, and shows how their performance can be maximized using hybrid computing techniques.

UR - https://www.scopus.com/pages/publications/85019958670

U2 - 10.1007/978-3-319-49340-4_23

DO - 10.1007/978-3-319-49340-4_23

M3 - Chapter

AN - SCOPUS:85019958670

SN - 9783319493398

SP - 777

EP - 806

BT - Handbook of Big Data Technologies

PB - Springer International Publishing

ER -

Bringing high performance computing to big data algorithms

Abstract

Access to Document

Other files and links

Fingerprint

Cite this