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
N1 - Publisher Copyright:
© 2018 ACM.
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
SN - 0360-0300
VL - 51
JO - ACM Computing Surveys
JF - ACM Computing Surveys
IS - 1
M1 - 1
ER -