KIT | KIT-Bibliothek | Impressum | Datenschutz

Cross-Layer Automated Hardware Design for Accuracy-Configurable Approximate Computing

Alan, Tanfer

Abstract:
Approximate Computing trades off computation accuracy against performance or energy efficiency. It is a design paradigm that arose in the last decade as an answer to diminishing returns from Dennard's scaling and a shift in the prominent workloads. A range of modern workloads, categorized mainly as recognition, mining, and synthesis, features an inherent tolerance to approximations. Their characteristics, such as redundancies in their input data and robust-to-noise algorithms, allow them to produce outputs of acceptable quality, despite an approximation in some of their computations. Approximate Computing leverages the application tolerance by relaxing the exactness in computation towards primary design goals of increasing performance or improving energy efficiency. Existing techniques span across the abstraction layers of computer systems where cross-layer techniques are shown to offer a larger design space and yield higher savings. Currently, the majority of the existing work aims at meeting a single accuracy. The extent of approximation tolerance, however, significantly varies with a change in input characteristics and applications.
... mehr


Volltext §
DOI: 10.5445/IR/1000138832
Veröffentlicht am 15.10.2021
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Technische Informatik (ITEC)
Publikationstyp Hochschulschrift
Publikationsdatum 15.10.2021
Sprache Englisch
Identifikator KITopen-ID: 1000138832
Verlag Karlsruher Institut für Technologie (KIT)
Umfang x, 91 S.
Art der Arbeit Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Technische Informatik (ITEC)
Prüfungsdatum 22.07.2021
Referent/Betreuer Prof. J. Henkel
Schlagwörter Approximate Computing, Quality Configurable, Design Space Exploration, Design Automation, Logic synthesis
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page