Generalized framework for global communication optimization

M. Kandemir; P. Banerjee; A. Choudhary; J. Ramanujam; N. Shenoy

doi:10.1109/IPPS.1998.669892

Generalized framework for global communication optimization

M. Kandemir^*, P. Banerjee, A. Choudhary, J. Ramanujam, N. Shenoy

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In distributed-memory message-passing architectures reducing communication cost is extremely important. In this paper, we present a technique to optimize communication globally. Our approach is based on a combination of linear algebra framework and dataflow analysis, and can take arbitrary control flow into account. The distinctive features of the algorithm are its accuracy in keeping communication set information and its support for general alignments and distributions including block-cyclic distributions. The method is currently being implemented in the PARADIGM compiler. The preliminary results show that the technique is effective in reducing both number as well as volume of the communication.

Original language	English (US)
Title of host publication	Proceedings of the International Parallel Processing Symposium, IPPS
Publisher	IEEE Comp Soc
Pages	69-73
Number of pages	5
ISBN (Print)	0818684046
DOIs	https://doi.org/10.1109/IPPS.1998.669892
State	Published - 1998
Event	Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing - Orlando, FL, USA Duration: Mar 30 1998 → Apr 3 1998

Other

Other	Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing
City	Orlando, FL, USA
Period	3/30/98 → 4/3/98

ASJC Scopus subject areas

Hardware and Architecture

Access to Document

10.1109/IPPS.1998.669892

Cite this

@inproceedings{01899d12649e466a81d0bc56a7c50d43,

title = "Generalized framework for global communication optimization",

abstract = "In distributed-memory message-passing architectures reducing communication cost is extremely important. In this paper, we present a technique to optimize communication globally. Our approach is based on a combination of linear algebra framework and dataflow analysis, and can take arbitrary control flow into account. The distinctive features of the algorithm are its accuracy in keeping communication set information and its support for general alignments and distributions including block-cyclic distributions. The method is currently being implemented in the PARADIGM compiler. The preliminary results show that the technique is effective in reducing both number as well as volume of the communication.",

author = "M. Kandemir and P. Banerjee and A. Choudhary and J. Ramanujam and N. Shenoy",

year = "1998",

doi = "10.1109/IPPS.1998.669892",

language = "English (US)",

isbn = "0818684046",

pages = "69--73",

booktitle = "Proceedings of the International Parallel Processing Symposium, IPPS",

publisher = "IEEE Comp Soc",

note = "Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing ; Conference date: 30-03-1998 Through 03-04-1998",

}

Kandemir, M, Banerjee, P, Choudhary, A, Ramanujam, J & Shenoy, N 1998, Generalized framework for global communication optimization. in Proceedings of the International Parallel Processing Symposium, IPPS. IEEE Comp Soc, pp. 69-73, Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing, Orlando, FL, USA, 3/30/98. https://doi.org/10.1109/IPPS.1998.669892

TY - GEN

T1 - Generalized framework for global communication optimization

AU - Kandemir, M.

AU - Banerjee, P.

AU - Choudhary, A.

AU - Ramanujam, J.

AU - Shenoy, N.

PY - 1998

Y1 - 1998

N2 - In distributed-memory message-passing architectures reducing communication cost is extremely important. In this paper, we present a technique to optimize communication globally. Our approach is based on a combination of linear algebra framework and dataflow analysis, and can take arbitrary control flow into account. The distinctive features of the algorithm are its accuracy in keeping communication set information and its support for general alignments and distributions including block-cyclic distributions. The method is currently being implemented in the PARADIGM compiler. The preliminary results show that the technique is effective in reducing both number as well as volume of the communication.

AB - In distributed-memory message-passing architectures reducing communication cost is extremely important. In this paper, we present a technique to optimize communication globally. Our approach is based on a combination of linear algebra framework and dataflow analysis, and can take arbitrary control flow into account. The distinctive features of the algorithm are its accuracy in keeping communication set information and its support for general alignments and distributions including block-cyclic distributions. The method is currently being implemented in the PARADIGM compiler. The preliminary results show that the technique is effective in reducing both number as well as volume of the communication.

UR - http://www.scopus.com/inward/record.url?scp=0031678508&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031678508&partnerID=8YFLogxK

U2 - 10.1109/IPPS.1998.669892

DO - 10.1109/IPPS.1998.669892

M3 - Conference contribution

AN - SCOPUS:85044974247

SN - 0818684046

SP - 69

EP - 73

BT - Proceedings of the International Parallel Processing Symposium, IPPS

PB - IEEE Comp Soc

T2 - Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing

Y2 - 30 March 1998 through 3 April 1998

ER -

Generalized framework for global communication optimization

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this