Publication Details

Editorial: Special issue on Advancing on Approximate Computing: Methodologies, Architectures and Algorithms

BARBARESCHI Mario, BOSIO Alberto, SEKANINA Lukáš and BRAUN Claus. Editorial: Special issue on Advancing on Approximate Computing: Methodologies, Architectures and Algorithms. Future Generation Computer Systems, vol. 124, no. 1, 2021. ISSN 0167-739X.
Czech title
Editorial: Speciální číslo o pokrocích v aproximativním počítání: Metody, architektury a algoritmy
Type
editorial
Language
english
Authors
Barbareschi Mario, Dr. (UNINA)
Bosio Alberto (LIRMM)
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY FIT BUT)
Braun Claus, Dr. (Bosch)
Keywords

approximate circuit, approximate computing, error modeling and propagation, inherent error resiliency

Abstract

In the modern computing era, characterized by saturated performance and high production costs, Approximate Computing has been representing the most attractive breakthrough for efficient system design. Such an innovative paradigm leverages the intrinsic error resilience of applications to inaccuracy in their inner calculations, in order to trade output result quality, under a certain maximum acceptable error threshold, off for system performance gain, such as calculation time and power demanding. In particular, for audio, image and video processing, data mining and information retrieval, approximate results turn out hard to distinguish from perfect ones, while their computation is less expensive. In recent years, Approximate Computing applicability is broadening in many scientific areas since suitable solutions come from approximate arithmetic operators, implemented both at hardware and software level, but from unreliable memory architectures, integrated circuit test, compilers and many others too. This special issue is dedicated to original research results and achievements by researcher community working on challenges and issues related to Approximate Computing

Published
2021
Pages
54-55
Journal
Future Generation Computer Systems, vol. 124, no. 1, ISSN 0167-739X
Publisher
Elsevier Science
DOI
UT WoS
000685542700007
EID Scopus
Back to top