FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2068710123> ?p ?o ?g. }

• W2068710123 abstract "Owing to a growing desire to reduce energy consumption and widely anticipated hurdles to the continued technology scaling promised by Moore's law, techniques and technologies such as inexact circuits and probabilistic CMOS (PCMOS) have gained prominence. These radical approaches trade accuracy at the hardware level for significant gains in energy consumption, area, and speed. While holding great promise, their ability to influence the broader milieu of computing is limited due to two shortcomings. First, they were mostly based on ad-hoc hand designs and did not consider algorithmically well-characterized automated design methodologies. Also, existing design approaches were limited to particular layers of abstraction such as physical, architectural and algorithmic or more broadly software. However, it is well-known that significant gains can be achieved by optimizing across the layers. To respond to this need, in this paper, we present an algorithmically well-founded cross-layer co-design framework (CCF) for automatically designing inexact hardware in the form of datapath elements. Specifically adders and multipliers, and show that significant associated gains can be achieved in terms of energy, area, and delay or speed. Our algorithms can achieve these gains with adding any additional hardware overhead. The proposed CCF framework embodies a symbiotic relationship between architecture and logic-layer design through the technique of probabilistic pruning combined with the novel confined voltage scaling technique introduced in this paper, applied at the physical layer. A second drawback of the state of the art with inexact design is the lack of physical evidence established through measuring fabricated ICs that the gains and other benefits that can be achieved are valid. Again, in this paper, we have addressed this shortcoming by using CCF to fabricate a prototype chip implementing inexact data-path elements; a range of 64-bit integer adders whose outputs can be erroneous. Through physical measurements of our prototype chip wherein the inexact adders admit expected relative error magnitudes of 10% or less, we have found that cumulative gains over comparable and fully accurate chips, quantified through the area-delay-energy product, can be a multiplicative factor of 15 or more. As evidence of the utility of these results, we demonstrate that despite admitting error while achieving gains, images processed using the FFT algorithm implemented using our inexact adders are visually discernible." @default.
• W2068710123 created "2016-06-24" @default.
• W2068710123 creator A5031043122 @default.
• W2068710123 creator A5044663943 @default.
• W2068710123 creator A5061421817 @default.
• W2068710123 creator A5064286485 @default.
• W2068710123 creator A5068875104 @default.
• W2068710123 creator A5069058393 @default.
• W2068710123 date "2012-05-15" @default.
• W2068710123 modified "2023-10-10" @default.
• W2068710123 title "Algorithmic methodologies for ultra-efficient inexact architectures for sustaining technology scaling" @default.
• W2068710123 cites W1533950919 @default.
• W2068710123 cites W1582324226 @default.
• W2068710123 cites W1990173890 @default.
• W2068710123 cites W2010468809 @default.
• W2068710123 cites W2016806092 @default.
• W2068710123 cites W2025715885 @default.
• W2068710123 cites W2030020312 @default.
• W2068710123 cites W2073359066 @default.
• W2068710123 cites W2097193789 @default.
• W2068710123 cites W2100098458 @default.
• W2068710123 cites W2104677471 @default.
• W2068710123 cites W2109489315 @default.
• W2068710123 cites W2109946919 @default.
• W2068710123 cites W2118331018 @default.
• W2068710123 cites W2125169487 @default.
• W2068710123 cites W2128065014 @default.
• W2068710123 cites W2129655902 @default.
• W2068710123 cites W2148042901 @default.
• W2068710123 cites W2151503471 @default.
• W2068710123 cites W2152977845 @default.
• W2068710123 cites W2155664816 @default.
• W2068710123 cites W2156425544 @default.
• W2068710123 doi "https://doi.org/10.1145/2212908.2212912" @default.
• W2068710123 hasPublicationYear "2012" @default.
• W2068710123 type Work @default.
• W2068710123 sameAs 2068710123 @default.
• W2068710123 citedByCount "34" @default.
• W2068710123 countsByYear W20687101232012 @default.
• W2068710123 countsByYear W20687101232013 @default.
• W2068710123 countsByYear W20687101232014 @default.
• W2068710123 countsByYear W20687101232015 @default.
• W2068710123 countsByYear W20687101232016 @default.
• W2068710123 countsByYear W20687101232017 @default.
• W2068710123 countsByYear W20687101232021 @default.
• W2068710123 crossrefType "proceedings-article" @default.
• W2068710123 hasAuthorship W2068710123A5031043122 @default.
• W2068710123 hasAuthorship W2068710123A5044663943 @default.
• W2068710123 hasAuthorship W2068710123A5061421817 @default.
• W2068710123 hasAuthorship W2068710123A5064286485 @default.
• W2068710123 hasAuthorship W2068710123A5068875104 @default.
• W2068710123 hasAuthorship W2068710123A5069058393 @default.
• W2068710123 hasConcept C108010975 @default.
• W2068710123 hasConcept C111472728 @default.
• W2068710123 hasConcept C111919701 @default.
• W2068710123 hasConcept C113775141 @default.
• W2068710123 hasConcept C118524514 @default.
• W2068710123 hasConcept C119599485 @default.
• W2068710123 hasConcept C124304363 @default.
• W2068710123 hasConcept C127413603 @default.
• W2068710123 hasConcept C127879752 @default.
• W2068710123 hasConcept C138885662 @default.
• W2068710123 hasConcept C147358964 @default.
• W2068710123 hasConcept C149635348 @default.
• W2068710123 hasConcept C154945302 @default.
• W2068710123 hasConcept C164620267 @default.
• W2068710123 hasConcept C177650935 @default.
• W2068710123 hasConcept C188817802 @default.
• W2068710123 hasConcept C190560348 @default.
• W2068710123 hasConcept C199360897 @default.
• W2068710123 hasConcept C24326235 @default.
• W2068710123 hasConcept C2742236 @default.
• W2068710123 hasConcept C2777904410 @default.
• W2068710123 hasConcept C2779960059 @default.
• W2068710123 hasConcept C2780165032 @default.
• W2068710123 hasConcept C2781198647 @default.
• W2068710123 hasConcept C37135326 @default.
• W2068710123 hasConcept C41008148 @default.
• W2068710123 hasConcept C46362747 @default.
• W2068710123 hasConcept C49937458 @default.
• W2068710123 hasConcept C6557445 @default.
• W2068710123 hasConcept C74172769 @default.
• W2068710123 hasConcept C76155785 @default.
• W2068710123 hasConcept C82876162 @default.
• W2068710123 hasConcept C86803240 @default.
• W2068710123 hasConceptScore W2068710123C108010975 @default.
• W2068710123 hasConceptScore W2068710123C111472728 @default.
• W2068710123 hasConceptScore W2068710123C111919701 @default.
• W2068710123 hasConceptScore W2068710123C113775141 @default.
• W2068710123 hasConceptScore W2068710123C118524514 @default.
• W2068710123 hasConceptScore W2068710123C119599485 @default.
• W2068710123 hasConceptScore W2068710123C124304363 @default.
• W2068710123 hasConceptScore W2068710123C127413603 @default.
• W2068710123 hasConceptScore W2068710123C127879752 @default.
• W2068710123 hasConceptScore W2068710123C138885662 @default.
• W2068710123 hasConceptScore W2068710123C147358964 @default.
• W2068710123 hasConceptScore W2068710123C149635348 @default.
• W2068710123 hasConceptScore W2068710123C154945302 @default.
• W2068710123 hasConceptScore W2068710123C164620267 @default.
• W2068710123 hasConceptScore W2068710123C177650935 @default.

• next