Multimedia vectorization of floating-point MIN/MAX reductions

Carole Goble; A. J C Bik; Xinmin Tian; Milind B. Girkar

doi:10.1002/cpe.1009

Multimedia vectorization of floating-point MIN/MAX reductions

Carole Goble, A. J C Bik, Xinmin Tian, Milind B. Girkar

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

Abstract

Finding the minimum or maximum value in an array forms an important step in a variety of applications. This paper discusses vectorization schemes that take advantage of the streaming-SIMD-extensions in commonly used floating-point MIN and MAX reductions. Performance advantages are demonstrated with experimental results. Copyright © 2006 John Wiley & Sons, Ltd.

Original language	English
Title of host publication	Concurrency Computation Practice and Experience\|Concurrency Comput. Pract. Exper.
Publisher	John Wiley & Sons Ltd
Pages	997-1007
Number of pages	10
Volume	18
DOIs	https://doi.org/10.1002/cpe.1009
Publication status	Published - 10 Aug 2006
Event	2nd International Workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2005) - Linkoping, SWEDEN Duration: 1 Jan 2007 → 1 Jan 2007

Conference

Conference	2nd International Workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2005)
City	Linkoping, SWEDEN
Period	1/01/07 → 1/01/07

Keywords

Compilers
Multimedia extensions
Optimization
SIMD
Vectorization

Access to Document

10.1002/cpe.1009

Cite this

@inproceedings{22b92c1eca5c4e3e942d07ff0256d256,

title = "Multimedia vectorization of floating-point MIN/MAX reductions",

abstract = "Finding the minimum or maximum value in an array forms an important step in a variety of applications. This paper discusses vectorization schemes that take advantage of the streaming-SIMD-extensions in commonly used floating-point MIN and MAX reductions. Performance advantages are demonstrated with experimental results. Copyright {\textcopyright} 2006 John Wiley & Sons, Ltd.",

keywords = "Compilers, Multimedia extensions, Optimization, SIMD, Vectorization",

author = "Carole Goble and Bik, {A. J C} and Xinmin Tian and Girkar, {Milind B.}",

note = "Zhang, N. Yao, L. Nenadic, A. Chin, J. Goble, C. Rector, A. Chadwick, D. Otenko, S. Shi, Q. 23 CHICHESTER 9 Sp. Iss. SI 194VD; 2nd International Workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2005) ; Conference date: 01-01-2007 Through 01-01-2007",

year = "2006",

month = aug,

day = "10",

doi = "10.1002/cpe.1009",

language = "English",

volume = "18",

pages = "997--1007",

booktitle = "Concurrency Computation Practice and Experience|Concurrency Comput. Pract. Exper.",

publisher = "John Wiley & Sons Ltd",

address = "United Kingdom",

}

Goble, C, Bik, AJC, Tian, X & Girkar, MB 2006, Multimedia vectorization of floating-point MIN/MAX reductions. in Concurrency Computation Practice and Experience|Concurrency Comput. Pract. Exper.. vol. 18, John Wiley & Sons Ltd, pp. 997-1007, 2nd International Workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2005), Linkoping, SWEDEN, 1/01/07. https://doi.org/10.1002/cpe.1009

TY - GEN

T1 - Multimedia vectorization of floating-point MIN/MAX reductions

AU - Goble, Carole

AU - Bik, A. J C

AU - Tian, Xinmin

AU - Girkar, Milind B.

N1 - Zhang, N. Yao, L. Nenadic, A. Chin, J. Goble, C. Rector, A. Chadwick, D. Otenko, S. Shi, Q. 23 CHICHESTER 9 Sp. Iss. SI 194VD

PY - 2006/8/10

Y1 - 2006/8/10

N2 - Finding the minimum or maximum value in an array forms an important step in a variety of applications. This paper discusses vectorization schemes that take advantage of the streaming-SIMD-extensions in commonly used floating-point MIN and MAX reductions. Performance advantages are demonstrated with experimental results. Copyright © 2006 John Wiley & Sons, Ltd.

AB - Finding the minimum or maximum value in an array forms an important step in a variety of applications. This paper discusses vectorization schemes that take advantage of the streaming-SIMD-extensions in commonly used floating-point MIN and MAX reductions. Performance advantages are demonstrated with experimental results. Copyright © 2006 John Wiley & Sons, Ltd.

KW - Compilers

KW - Multimedia extensions

KW - Optimization

KW - SIMD

KW - Vectorization

U2 - 10.1002/cpe.1009

DO - 10.1002/cpe.1009

M3 - Conference contribution

VL - 18

SP - 997

EP - 1007

BT - Concurrency Computation Practice and Experience|Concurrency Comput. Pract. Exper.

PB - John Wiley & Sons Ltd

T2 - 2nd International Workshop on Emerging Technologies for Next-Generation GRID (ETNGRID 2005)

Y2 - 1 January 2007 through 1 January 2007

ER -

Multimedia vectorization of floating-point MIN/MAX reductions

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this