Back to Results
First PageMeta Content
Numerical linear algebra / HPC Challenge Benchmark / LU decomposition / Cholesky decomposition / LAPACK / Basic Linear Algebra Subprograms / Matrix decomposition / Matrix / Rank / Algebra / Linear algebra / Mathematics


1 Reducing the time to tune parallel dense linear algebra routines with partial execution and performance modelling ∗ Oak
Add to Reading List

Document Date: 2010-10-09 11:32:30


Open Document

File Size: 287,87 KB

Share Result on Facebook

City

Philadelphia / Rennes / Seattle / Baltimore / New York / Washington / DC / Berlin / London / /

Company

Johns Hopkins University Press / Elsevier Inc. / Oxford University Press / AMD / IBM / Pergamon Press / Oak Ridge National Laboratory / Top20 Systems / Pearson / Imperial College Press / Intel / John Wiley & Sons / /

Country

France / United States / /

Currency

pence / /

Facility

University of Manchester / University of Tennessee Abstract / Piotr Luszczek§ Ridge National Laboratory / University of Tennessee / Oak Ridge National Laboratory / Prentice Hall / Rice University / /

IndustryTerm

performance computing / parallel algorithms / software misconfiguration / shared memory multicore systems / dual-processor / parallel applications / row swapping algorithm / interconnect network / Self-adapting software / parallel computing influence / linear equations software / computing / software libraries / large dense linear systems / final solution / boundary integral solution / important tool / dense linear systems / stealth technology / large dense systems / linear algebra algorithms / /

MarketIndex

HPCC / HPL / HPC Challenge / LINPACK / /

OperatingSystem

Cross-platform / Linux / /

Organization

Core2 Duo / The Johns Hopkins University / Piotr Luszczek§ Ridge National Laboratory / Rice University / Society for Industrial and Applied Mathematics / IEEE Computer Society Washington / University of Manchester / Oxford University / University of Tennessee Abstract / University of Tennessee / Knoxville / /

Person

R. Clint Whaley / Jonathan Weinberg / Javier Cuenca / James W. Demmel / Erich Strohmaier / L. Suzan Blackford / Iain S. Duff / Kenneth J. Roche / Fred G. Gustavson / S. Hammarling / Leo T. Yang / Greg Wilson / Danny C. Sorensen / Alan Edelman / Adolfy Hoisie / Frank Mueller / Sven Hammarling / Zizhong Chen / Robert W. Numerich / Gene H. Golub / Patrick Worley / Warren Smith / Xiasong Ma / Henk A. van der Vorst / Suzan L. Blackford / Ken Stanley / A. Karp / A. Greenbaum / Andy Oram / A. McKenney / Andy Cleary / Emmanuel Jeannot / Julien Langou / Antoine Petitet / J. Choi / J. Du Croz / Allan Snavely / Domingo Gim´enez / Progress / Michael O. McCracken / Valerie Taylor / Luis-Pedro Garc´ıa / Susan Ostrouchov / Jack J. Dongarra / Kenneth Roche / David W. Walker / Piotr Luszczek / Harvey J. Wasserman / Ian Foster / Jeremy Kepner / Darren J. Kerbyson / Greg Henry / /

/

Position

designer / Statistician / editor / model external influences / /

Product

Instanbul 2.8 GHz 6 / Vizio L32 Television / /

ProgrammingLanguage

DC / /

ProvinceOrState

New Brunswick / New York / Washington / Tennessee / /

PublishedMedium

The American Statistician / Lecture Notes in Computer Science / /

Technology

1345 processor / Linux / fluid dynamics / operating system / shared memory / linear algebra algorithms / 416 processors / Parallel Matrix Algorithms / underlying algorithm / stealth technology / Matrix algorithms / row swapping algorithm / Parallel Processing / Gigabit Ethernet / /

URL

http /

SocialTag