IMPLEMENTATION OF SOME CONCURRENT ALGORITHMS FOR MATRIX FACTORIZATION.

J. J. Dongarra; A. H. Sameh; D. C. Sorensen

IMPLEMENTATION OF SOME CONCURRENT ALGORITHMS FOR MATRIX FACTORIZATION.

J. J. Dongarra, A. H. Sameh, D. C. Sorensen

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper discusses implementations of various forms of the QR factorization on the Denelcor HEP. The motivation for examining these implementations was to investigate performance issues that we might expect to face in developing mathematical software for linear algebra problems on emerging parallel architectures. The Denelcor HEP is particularly well suited for such a study because it offers the possibility of very fine grain parallelism through low overhead synchronization primitives. We point out certain synchronization problems that arise within the more lightly coupled variations of the algorithm and offer a comparison of the performance of these variations.

Original language	English
Pages (from-to)	39-46
Number of pages	8
Journal	Proceedings of the Hawaii International Conference on System Sciences
State	Published - 1985
Externally published	Yes

Funding

* An earlier version of this paper appeared in the proceedings of the Eighteenth Annual Hawaii International Conference on System Sciences in January 1985. ** Work supported in part by the Applied Mathematical Sciences subprogram of the Office of Energy Research, U.S. Department of Energy under Contract g-31-109-Eng-33.

Funders	Funder number
Office of Energy Research
U.S. Department of Energy	g-31-109-Eng-33

Cite this

@article{cf312c0fc2174598b19e9417e0324775,

title = "IMPLEMENTATION OF SOME CONCURRENT ALGORITHMS FOR MATRIX FACTORIZATION.",

abstract = "This paper discusses implementations of various forms of the QR factorization on the Denelcor HEP. The motivation for examining these implementations was to investigate performance issues that we might expect to face in developing mathematical software for linear algebra problems on emerging parallel architectures. The Denelcor HEP is particularly well suited for such a study because it offers the possibility of very fine grain parallelism through low overhead synchronization primitives. We point out certain synchronization problems that arise within the more lightly coupled variations of the algorithm and offer a comparison of the performance of these variations.",

author = "Dongarra, {J. J.} and Sameh, {A. H.} and Sorensen, {D. C.}",

year = "1985",

language = "English",

pages = "39--46",

journal = "Proceedings of the Hawaii International Conference on System Sciences",

issn = "0073-1129",

}

TY - JOUR

T1 - IMPLEMENTATION OF SOME CONCURRENT ALGORITHMS FOR MATRIX FACTORIZATION.

AU - Dongarra, J. J.

AU - Sameh, A. H.

AU - Sorensen, D. C.

PY - 1985

Y1 - 1985

N2 - This paper discusses implementations of various forms of the QR factorization on the Denelcor HEP. The motivation for examining these implementations was to investigate performance issues that we might expect to face in developing mathematical software for linear algebra problems on emerging parallel architectures. The Denelcor HEP is particularly well suited for such a study because it offers the possibility of very fine grain parallelism through low overhead synchronization primitives. We point out certain synchronization problems that arise within the more lightly coupled variations of the algorithm and offer a comparison of the performance of these variations.

AB - This paper discusses implementations of various forms of the QR factorization on the Denelcor HEP. The motivation for examining these implementations was to investigate performance issues that we might expect to face in developing mathematical software for linear algebra problems on emerging parallel architectures. The Denelcor HEP is particularly well suited for such a study because it offers the possibility of very fine grain parallelism through low overhead synchronization primitives. We point out certain synchronization problems that arise within the more lightly coupled variations of the algorithm and offer a comparison of the performance of these variations.

UR - http://www.scopus.com/inward/record.url?scp=0021825979&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0021825979

SN - 0073-1129

SP - 39

EP - 46

JO - Proceedings of the Hawaii International Conference on System Sciences

JF - Proceedings of the Hawaii International Conference on System Sciences

ER -

IMPLEMENTATION OF SOME CONCURRENT ALGORITHMS FOR MATRIX FACTORIZATION.

Abstract

Funding

Other files and links

Fingerprint

Cite this