Strategies and performance norms for efficient utilization of vector pipeline computers as illustrated by the classical mechanical simulation of rotationally inelastic collisions

David L. Cochrane; Donald G. Truhlar

doi:10.1016/0167-8191(88)90006-3

Strategies and performance norms for efficient utilization of vector pipeline computers as illustrated by the classical mechanical simulation of rotationally inelastic collisions

David L. Cochrane, Donald G. Truhlar

Chemistry (Twin Cities)

Research output: Contribution to journal › Article › peer-review

10 Scopus citations

Abstract

We discuss the vectorization of a classical mechanical trajectory code which simulated the interaction of a rotationally excited rigid rotator with a colliding atom. This code was optimized in FORTRAN 77 and can be run on either a VAX 11/780 minicomputer or a CRAY-1 vector pipeline supercomputer. The article presents a global strategy for vectorizing a classical mechanical trajectory code, a set of performance criteria for characterizing the vectorization of a computer code, and an analysis of the four major subroutines of the vectorized trajectory code in terms of this strategy and these criteria.

Original language	English (US)
Pages (from-to)	63-85
Number of pages	23
Journal	Parallel Computing
Volume	6
Issue number	1
DOIs	https://doi.org/10.1016/0167-8191(88)90006-3
State	Published - Jan 1988

Bibliographical note

Funding Information:
We acknowledge the University of Minnesota Supercomputer Institute for a grant of time on the University of Minnesota Supercomputer Institute CRAY-1 computer. This work was also supported in part by the National Science Foundation under grant no. CHE83-17944.

Keywords

CRAY-1
Simulation of rotationally inelastic collisions
implementation features
timing results
vectorization

Publisher link

10.1016/0167-8191(88)90006-3

Find It

Find It at U of M Libraries

Cite this

@article{03155dcbf7134633a5c95feb223dbf14,

title = "Strategies and performance norms for efficient utilization of vector pipeline computers as illustrated by the classical mechanical simulation of rotationally inelastic collisions",

abstract = "We discuss the vectorization of a classical mechanical trajectory code which simulated the interaction of a rotationally excited rigid rotator with a colliding atom. This code was optimized in FORTRAN 77 and can be run on either a VAX 11/780 minicomputer or a CRAY-1 vector pipeline supercomputer. The article presents a global strategy for vectorizing a classical mechanical trajectory code, a set of performance criteria for characterizing the vectorization of a computer code, and an analysis of the four major subroutines of the vectorized trajectory code in terms of this strategy and these criteria.",

keywords = "CRAY-1, Simulation of rotationally inelastic collisions, implementation features, timing results, vectorization",

author = "Cochrane, {David L.} and Truhlar, {Donald G.}",

note = "Funding Information: We acknowledge the University of Minnesota Supercomputer Institute for a grant of time on the University of Minnesota Supercomputer Institute CRAY-1 computer. This work was also supported in part by the National Science Foundation under grant no. CHE83-17944.",

year = "1988",

month = jan,

doi = "10.1016/0167-8191(88)90006-3",

language = "English (US)",

volume = "6",

pages = "63--85",

journal = "Parallel Computing",

issn = "0167-8191",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Strategies and performance norms for efficient utilization of vector pipeline computers as illustrated by the classical mechanical simulation of rotationally inelastic collisions

AU - Cochrane, David L.

AU - Truhlar, Donald G.

N1 - Funding Information: We acknowledge the University of Minnesota Supercomputer Institute for a grant of time on the University of Minnesota Supercomputer Institute CRAY-1 computer. This work was also supported in part by the National Science Foundation under grant no. CHE83-17944.

PY - 1988/1

Y1 - 1988/1

N2 - We discuss the vectorization of a classical mechanical trajectory code which simulated the interaction of a rotationally excited rigid rotator with a colliding atom. This code was optimized in FORTRAN 77 and can be run on either a VAX 11/780 minicomputer or a CRAY-1 vector pipeline supercomputer. The article presents a global strategy for vectorizing a classical mechanical trajectory code, a set of performance criteria for characterizing the vectorization of a computer code, and an analysis of the four major subroutines of the vectorized trajectory code in terms of this strategy and these criteria.

AB - We discuss the vectorization of a classical mechanical trajectory code which simulated the interaction of a rotationally excited rigid rotator with a colliding atom. This code was optimized in FORTRAN 77 and can be run on either a VAX 11/780 minicomputer or a CRAY-1 vector pipeline supercomputer. The article presents a global strategy for vectorizing a classical mechanical trajectory code, a set of performance criteria for characterizing the vectorization of a computer code, and an analysis of the four major subroutines of the vectorized trajectory code in terms of this strategy and these criteria.

KW - CRAY-1

KW - Simulation of rotationally inelastic collisions

KW - implementation features

KW - timing results

KW - vectorization

UR - http://www.scopus.com/inward/record.url?scp=45549116601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45549116601&partnerID=8YFLogxK

U2 - 10.1016/0167-8191(88)90006-3

DO - 10.1016/0167-8191(88)90006-3

M3 - Article

AN - SCOPUS:45549116601

SN - 0167-8191

VL - 6

SP - 63

EP - 85

JO - Parallel Computing

JF - Parallel Computing

IS - 1

ER -

Strategies and performance norms for efficient utilization of vector pipeline computers as illustrated by the classical mechanical simulation of rotationally inelastic collisions

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this