Approximate communication: Techniques for reducing communication bottlenecks in large-scale parallel systems

Filipe Betzel, Karen Khatamifard, Harini Suresh, David J. Lilja, John Sartori, Ulya Karpuzcu

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Approximate computing has gained research attention recently as a way to increase energy efficiency and/or performance by exploiting some applications' intrinsic error resiliency. However, little attention has been given to its potential for tackling the communication bottleneck that remains one of the looming challenges to be tackled for efficient parallelism. This article explores the potential benefits of approximate computing for communication reduction by surveying three promising techniques for approximate communication: compression, relaxed synchronization, and value prediction. The techniques are compared based on an evaluation framework composed of communication cost reduction, performance, energy reduction, applicability, overheads, and output degradation. Comparison results demonstrate that lossy link compression and approximate value prediction show great promise for reducing the communication bottleneck in bandwidth-constrained applications. Meanwhile, relaxed synchronization is found to provide large speedups for select error-Tolerant applications, but suffers from limited general applicability and unreliable output degradation guarantees. Finally, this article concludes with several suggestions for future research on approximate communication techniques.

Original languageEnglish (US)
Article number1
JournalACM Computing Surveys
Volume51
Issue number1
DOIs
StatePublished - Jan 2018

Fingerprint

Parallel Systems
Large-scale Systems
Communication
Degradation
Synchronization
Compression
Resiliency
Computing
Prediction
Output
Communication Cost
Comparison Result
Energy Efficiency
Surveying
Parallelism
Cost reduction
Bandwidth
Energy efficiency
Evaluation
Energy

Keywords

  • Approximate communication
  • Approximate computing
  • Communication reduction
  • Scalability

Cite this

Approximate communication : Techniques for reducing communication bottlenecks in large-scale parallel systems. / Betzel, Filipe; Khatamifard, Karen; Suresh, Harini; Lilja, David J.; Sartori, John; Karpuzcu, Ulya.

In: ACM Computing Surveys, Vol. 51, No. 1, 1, 01.2018.

Research output: Contribution to journalArticle

@article{8decb2b5cec444cb8d1202f26269f44d,
title = "Approximate communication: Techniques for reducing communication bottlenecks in large-scale parallel systems",
abstract = "Approximate computing has gained research attention recently as a way to increase energy efficiency and/or performance by exploiting some applications' intrinsic error resiliency. However, little attention has been given to its potential for tackling the communication bottleneck that remains one of the looming challenges to be tackled for efficient parallelism. This article explores the potential benefits of approximate computing for communication reduction by surveying three promising techniques for approximate communication: compression, relaxed synchronization, and value prediction. The techniques are compared based on an evaluation framework composed of communication cost reduction, performance, energy reduction, applicability, overheads, and output degradation. Comparison results demonstrate that lossy link compression and approximate value prediction show great promise for reducing the communication bottleneck in bandwidth-constrained applications. Meanwhile, relaxed synchronization is found to provide large speedups for select error-Tolerant applications, but suffers from limited general applicability and unreliable output degradation guarantees. Finally, this article concludes with several suggestions for future research on approximate communication techniques.",
keywords = "Approximate communication, Approximate computing, Communication reduction, Scalability",
author = "Filipe Betzel and Karen Khatamifard and Harini Suresh and Lilja, {David J.} and John Sartori and Ulya Karpuzcu",
year = "2018",
month = "1",
doi = "10.1145/3145812",
language = "English (US)",
volume = "51",
journal = "ACM Computing Surveys",
issn = "0360-0300",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - Approximate communication

T2 - Techniques for reducing communication bottlenecks in large-scale parallel systems

AU - Betzel, Filipe

AU - Khatamifard, Karen

AU - Suresh, Harini

AU - Lilja, David J.

AU - Sartori, John

AU - Karpuzcu, Ulya

PY - 2018/1

Y1 - 2018/1

N2 - Approximate computing has gained research attention recently as a way to increase energy efficiency and/or performance by exploiting some applications' intrinsic error resiliency. However, little attention has been given to its potential for tackling the communication bottleneck that remains one of the looming challenges to be tackled for efficient parallelism. This article explores the potential benefits of approximate computing for communication reduction by surveying three promising techniques for approximate communication: compression, relaxed synchronization, and value prediction. The techniques are compared based on an evaluation framework composed of communication cost reduction, performance, energy reduction, applicability, overheads, and output degradation. Comparison results demonstrate that lossy link compression and approximate value prediction show great promise for reducing the communication bottleneck in bandwidth-constrained applications. Meanwhile, relaxed synchronization is found to provide large speedups for select error-Tolerant applications, but suffers from limited general applicability and unreliable output degradation guarantees. Finally, this article concludes with several suggestions for future research on approximate communication techniques.

AB - Approximate computing has gained research attention recently as a way to increase energy efficiency and/or performance by exploiting some applications' intrinsic error resiliency. However, little attention has been given to its potential for tackling the communication bottleneck that remains one of the looming challenges to be tackled for efficient parallelism. This article explores the potential benefits of approximate computing for communication reduction by surveying three promising techniques for approximate communication: compression, relaxed synchronization, and value prediction. The techniques are compared based on an evaluation framework composed of communication cost reduction, performance, energy reduction, applicability, overheads, and output degradation. Comparison results demonstrate that lossy link compression and approximate value prediction show great promise for reducing the communication bottleneck in bandwidth-constrained applications. Meanwhile, relaxed synchronization is found to provide large speedups for select error-Tolerant applications, but suffers from limited general applicability and unreliable output degradation guarantees. Finally, this article concludes with several suggestions for future research on approximate communication techniques.

KW - Approximate communication

KW - Approximate computing

KW - Communication reduction

KW - Scalability

UR - http://www.scopus.com/inward/record.url?scp=85040787531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040787531&partnerID=8YFLogxK

U2 - 10.1145/3145812

DO - 10.1145/3145812

M3 - Article

AN - SCOPUS:85040787531

VL - 51

JO - ACM Computing Surveys

JF - ACM Computing Surveys

SN - 0360-0300

IS - 1

M1 - 1

ER -