Efficient robust parallel computations.

Zvi Kedem, Krishna V. Palem, Paul G. Spirakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A parallel computing system becomes increasingly prone to failure as the number of processing elements in it increases. In this paper, we describe a completely general strategy that takes an arbitrary step of an ideal CRCW PRAM and automatically translates it to run efficiently and robustly on a PRAM in which processors are prone to failure. The strategy relies on efficient robust algorithms for solving a core problem, the Certified Write-All Problem. This problem characterizes the core of robustness, because, as we show, its complexity is equal to that of any general strategy for realizing robustness in the model. We analyze the expected parallel time and work of various algorithms for solving this problem. Our results are a non-trivial generalization of R.P. Brent's Lemma. We consider the case where the number of the available processors decreases dynamically over time, whereas Brent's Lemma is only applicable in the case where the processor availability pattern is static.

Original languageEnglish (US)
Title of host publicationProc 22nd Annu ACM Symp Theory Comput
PublisherPubl by ACM
Pages138-148
Number of pages11
ISBN (Print)0897913612
StatePublished - 1990
EventProceedings of the 22nd Annual ACM Symposium on Theory of Computing - Baltimore, MD, USA
Duration: May 14 1990May 16 1990

Other

OtherProceedings of the 22nd Annual ACM Symposium on Theory of Computing
CityBaltimore, MD, USA
Period5/14/905/16/90

Fingerprint

Parallel processing systems
Availability
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kedem, Z., Palem, K. V., & Spirakis, P. G. (1990). Efficient robust parallel computations. In Proc 22nd Annu ACM Symp Theory Comput (pp. 138-148). Publ by ACM.

Efficient robust parallel computations. / Kedem, Zvi; Palem, Krishna V.; Spirakis, Paul G.

Proc 22nd Annu ACM Symp Theory Comput. Publ by ACM, 1990. p. 138-148.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kedem, Z, Palem, KV & Spirakis, PG 1990, Efficient robust parallel computations. in Proc 22nd Annu ACM Symp Theory Comput. Publ by ACM, pp. 138-148, Proceedings of the 22nd Annual ACM Symposium on Theory of Computing, Baltimore, MD, USA, 5/14/90.
Kedem Z, Palem KV, Spirakis PG. Efficient robust parallel computations. In Proc 22nd Annu ACM Symp Theory Comput. Publ by ACM. 1990. p. 138-148
Kedem, Zvi ; Palem, Krishna V. ; Spirakis, Paul G. / Efficient robust parallel computations. Proc 22nd Annu ACM Symp Theory Comput. Publ by ACM, 1990. pp. 138-148
@inproceedings{cabb16c54f284da7b0e68dde13c3a7d1,
title = "Efficient robust parallel computations.",
abstract = "A parallel computing system becomes increasingly prone to failure as the number of processing elements in it increases. In this paper, we describe a completely general strategy that takes an arbitrary step of an ideal CRCW PRAM and automatically translates it to run efficiently and robustly on a PRAM in which processors are prone to failure. The strategy relies on efficient robust algorithms for solving a core problem, the Certified Write-All Problem. This problem characterizes the core of robustness, because, as we show, its complexity is equal to that of any general strategy for realizing robustness in the model. We analyze the expected parallel time and work of various algorithms for solving this problem. Our results are a non-trivial generalization of R.P. Brent's Lemma. We consider the case where the number of the available processors decreases dynamically over time, whereas Brent's Lemma is only applicable in the case where the processor availability pattern is static.",
author = "Zvi Kedem and Palem, {Krishna V.} and Spirakis, {Paul G.}",
year = "1990",
language = "English (US)",
isbn = "0897913612",
pages = "138--148",
booktitle = "Proc 22nd Annu ACM Symp Theory Comput",
publisher = "Publ by ACM",

}

TY - GEN

T1 - Efficient robust parallel computations.

AU - Kedem, Zvi

AU - Palem, Krishna V.

AU - Spirakis, Paul G.

PY - 1990

Y1 - 1990

N2 - A parallel computing system becomes increasingly prone to failure as the number of processing elements in it increases. In this paper, we describe a completely general strategy that takes an arbitrary step of an ideal CRCW PRAM and automatically translates it to run efficiently and robustly on a PRAM in which processors are prone to failure. The strategy relies on efficient robust algorithms for solving a core problem, the Certified Write-All Problem. This problem characterizes the core of robustness, because, as we show, its complexity is equal to that of any general strategy for realizing robustness in the model. We analyze the expected parallel time and work of various algorithms for solving this problem. Our results are a non-trivial generalization of R.P. Brent's Lemma. We consider the case where the number of the available processors decreases dynamically over time, whereas Brent's Lemma is only applicable in the case where the processor availability pattern is static.

AB - A parallel computing system becomes increasingly prone to failure as the number of processing elements in it increases. In this paper, we describe a completely general strategy that takes an arbitrary step of an ideal CRCW PRAM and automatically translates it to run efficiently and robustly on a PRAM in which processors are prone to failure. The strategy relies on efficient robust algorithms for solving a core problem, the Certified Write-All Problem. This problem characterizes the core of robustness, because, as we show, its complexity is equal to that of any general strategy for realizing robustness in the model. We analyze the expected parallel time and work of various algorithms for solving this problem. Our results are a non-trivial generalization of R.P. Brent's Lemma. We consider the case where the number of the available processors decreases dynamically over time, whereas Brent's Lemma is only applicable in the case where the processor availability pattern is static.

UR - http://www.scopus.com/inward/record.url?scp=0025028518&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025028518&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0897913612

SP - 138

EP - 148

BT - Proc 22nd Annu ACM Symp Theory Comput

PB - Publ by ACM

ER -