Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905996924> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2905996924 endingPage "789" @default.
- W2905996924 startingPage "778" @default.
- W2905996924 abstract "Many applications show tolerance to inaccuracies. These can be exploited to build faster circuits with smaller area and lower power. This is particularly true for the hardware accelerators in heterogeneous computing systems. A major problem with approximate computing is that the resulting approximated circuit is highly dependent on the training data. Previous works often rely on static training results. If the workload is dynamic in nature or changes over time, output errors may reach unacceptable levels. Therefore, dynamic control methods are needed to solve this problem. To address this issue, in this paper, we propose an approximate self-adaptive architecture that autotunes itself at runtime based on the workload. Two different control mechanisms are proposed, one based on a regular heartbeat (HB), which resets the approximate circuits at regular intervals and the other based on internal lightweight checkers (LWCs). These checkers detect a change in the workload and reset the approximations. Experimental results show that our proposed methods work well leading to very good results compared to other approximation methods while keeping the output error within the given maximum error threshold at relatively low-area overheads, on average 8% and 8.5% for HB and LWC method, respectively, and delay overheads 5.9% and 8.1%." @default.
- W2905996924 created "2019-01-01" @default.
- W2905996924 creator A5004538765 @default.
- W2905996924 creator A5061580251 @default.
- W2905996924 date "2019-04-01" @default.
- W2905996924 modified "2023-09-27" @default.
- W2905996924 title "Toward Self-Tunable Approximate Computing" @default.
- W2905996924 cites W1533950919 @default.
- W2905996924 cites W1856540154 @default.
- W2905996924 cites W1986192284 @default.
- W2905996924 cites W1998824039 @default.
- W2905996924 cites W2010966003 @default.
- W2905996924 cites W2020217519 @default.
- W2905996924 cites W2030922317 @default.
- W2905996924 cites W2034270503 @default.
- W2905996924 cites W2035378788 @default.
- W2905996924 cites W2044235194 @default.
- W2905996924 cites W2107376597 @default.
- W2905996924 cites W2113592437 @default.
- W2905996924 cites W2121662690 @default.
- W2905996924 cites W2142883190 @default.
- W2905996924 cites W2143556363 @default.
- W2905996924 cites W2187230075 @default.
- W2905996924 cites W2244005500 @default.
- W2905996924 cites W2244803248 @default.
- W2905996924 cites W2265166184 @default.
- W2905996924 cites W2293636967 @default.
- W2905996924 cites W2399535694 @default.
- W2905996924 cites W2404305894 @default.
- W2905996924 cites W2405102949 @default.
- W2905996924 cites W2466529450 @default.
- W2905996924 cites W2499900168 @default.
- W2905996924 cites W2509971597 @default.
- W2905996924 cites W2588565458 @default.
- W2905996924 cites W2742536119 @default.
- W2905996924 cites W2746351350 @default.
- W2905996924 cites W2768781341 @default.
- W2905996924 cites W2770370002 @default.
- W2905996924 cites W2798414599 @default.
- W2905996924 cites W2884390179 @default.
- W2905996924 cites W3005460357 @default.
- W2905996924 cites W4231563577 @default.
- W2905996924 cites W4234974086 @default.
- W2905996924 cites W634728970 @default.
- W2905996924 doi "https://doi.org/10.1109/tvlsi.2018.2884848" @default.
- W2905996924 hasPublicationYear "2019" @default.
- W2905996924 type Work @default.
- W2905996924 sameAs 2905996924 @default.
- W2905996924 citedByCount "12" @default.
- W2905996924 countsByYear W29059969242020 @default.
- W2905996924 countsByYear W29059969242021 @default.
- W2905996924 countsByYear W29059969242022 @default.
- W2905996924 countsByYear W29059969242023 @default.
- W2905996924 crossrefType "journal-article" @default.
- W2905996924 hasAuthorship W2905996924A5004538765 @default.
- W2905996924 hasAuthorship W2905996924A5061580251 @default.
- W2905996924 hasConcept C173608175 @default.
- W2905996924 hasConcept C41008148 @default.
- W2905996924 hasConceptScore W2905996924C173608175 @default.
- W2905996924 hasConceptScore W2905996924C41008148 @default.
- W2905996924 hasIssue "4" @default.
- W2905996924 hasLocation W29059969241 @default.
- W2905996924 hasOpenAccess W2905996924 @default.
- W2905996924 hasPrimaryLocation W29059969241 @default.
- W2905996924 hasRelatedWork W1491899005 @default.
- W2905996924 hasRelatedWork W1502414128 @default.
- W2905996924 hasRelatedWork W1558545464 @default.
- W2905996924 hasRelatedWork W1604898313 @default.
- W2905996924 hasRelatedWork W1984303163 @default.
- W2905996924 hasRelatedWork W2074301136 @default.
- W2905996924 hasRelatedWork W2117014006 @default.
- W2905996924 hasRelatedWork W2172791042 @default.
- W2905996924 hasRelatedWork W2372170743 @default.
- W2905996924 hasRelatedWork W4233815414 @default.
- W2905996924 hasVolume "27" @default.
- W2905996924 isParatext "false" @default.
- W2905996924 isRetracted "false" @default.
- W2905996924 magId "2905996924" @default.
- W2905996924 workType "article" @default.