A convex programming approach for exploiting data and functional parallelism on distributed memory multicomputers

S. Ramaswamy; S. Sapatnekar; P. Banerjee

doi:10.1109/ICPP.1994.21

A convex programming approach for exploiting data and functional parallelism on distributed memory multicomputers

S. Ramaswamy, S. Sapatnekar, P. Banerjee

Electrical and Computer Engineering

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

16 Scopus citations

Abstract

Compilers have focused on the exploitation of one of functional or data parallelism in the past. The PARADIGM compiler project at the University of Illinois is among the first to incorporate techniques for simultaneous exploitation of both. The work in this paper describes the techniques used in the PARADIGM compiler and analyzes the optimality of these techniques. It is the first of its kind to use realistic cost models and includes data transfer costs which all previous researchers have neglected. Preliminary results on the CM-5 show the efficacy of our methods and the significant advantages of using functional and data parallelism together for execution of real applications.

Original language	English (US)
Article number	5727772
Pages (from-to)	II116-II125
Journal	Proceedings of the International Conference on Parallel Processing
Volume	2
DOIs	https://doi.org/10.1109/ICPP.1994.21
State	Published - 1994
Event	23rd International Conference on Parallel Processing, ICPP 1994 - Raleigh, NC, United States Duration: Aug 15 1994 → Aug 19 1994

Publisher link

10.1109/ICPP.1994.21

Find It

Find It at U of M Libraries

Cite this

@article{5f6e12a886b642bfa07697450d3ee601,

title = "A convex programming approach for exploiting data and functional parallelism on distributed memory multicomputers",

abstract = "Compilers have focused on the exploitation of one of functional or data parallelism in the past. The PARADIGM compiler project at the University of Illinois is among the first to incorporate techniques for simultaneous exploitation of both. The work in this paper describes the techniques used in the PARADIGM compiler and analyzes the optimality of these techniques. It is the first of its kind to use realistic cost models and includes data transfer costs which all previous researchers have neglected. Preliminary results on the CM-5 show the efficacy of our methods and the significant advantages of using functional and data parallelism together for execution of real applications.",

author = "S. Ramaswamy and S. Sapatnekar and P. Banerjee",

year = "1994",

doi = "10.1109/ICPP.1994.21",

language = "English (US)",

volume = "2",

pages = "II116--II125",

journal = "Proceedings of the International Conference on Parallel Processing",

issn = "0190-3918",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "23rd International Conference on Parallel Processing, ICPP 1994 ; Conference date: 15-08-1994 Through 19-08-1994",

}

TY - JOUR

T1 - A convex programming approach for exploiting data and functional parallelism on distributed memory multicomputers

AU - Ramaswamy, S.

AU - Sapatnekar, S.

AU - Banerjee, P.

PY - 1994

Y1 - 1994

N2 - Compilers have focused on the exploitation of one of functional or data parallelism in the past. The PARADIGM compiler project at the University of Illinois is among the first to incorporate techniques for simultaneous exploitation of both. The work in this paper describes the techniques used in the PARADIGM compiler and analyzes the optimality of these techniques. It is the first of its kind to use realistic cost models and includes data transfer costs which all previous researchers have neglected. Preliminary results on the CM-5 show the efficacy of our methods and the significant advantages of using functional and data parallelism together for execution of real applications.

AB - Compilers have focused on the exploitation of one of functional or data parallelism in the past. The PARADIGM compiler project at the University of Illinois is among the first to incorporate techniques for simultaneous exploitation of both. The work in this paper describes the techniques used in the PARADIGM compiler and analyzes the optimality of these techniques. It is the first of its kind to use realistic cost models and includes data transfer costs which all previous researchers have neglected. Preliminary results on the CM-5 show the efficacy of our methods and the significant advantages of using functional and data parallelism together for execution of real applications.

UR - http://www.scopus.com/inward/record.url?scp=84904357426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904357426&partnerID=8YFLogxK

U2 - 10.1109/ICPP.1994.21

DO - 10.1109/ICPP.1994.21

M3 - Conference article

AN - SCOPUS:84904357426

SN - 0190-3918

VL - 2

SP - II116-II125

JO - Proceedings of the International Conference on Parallel Processing

JF - Proceedings of the International Conference on Parallel Processing

M1 - 5727772

T2 - 23rd International Conference on Parallel Processing, ICPP 1994

Y2 - 15 August 1994 through 19 August 1994

ER -

A convex programming approach for exploiting data and functional parallelism on distributed memory multicomputers

Abstract

Publisher link

Find It

Other files and links

Fingerprint

Cite this