Matches in SemOpenAlex for { <https://semopenalex.org/work/W2944132666> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W2944132666 abstract "Approximate computing allows the introduction of inaccuracy in the computation for cost savings, such as energy consumption, chip-area, and latency. Targeting energy efficiency, approximate designs for multipliers, adders, and multiply-accumulate (MAC) have been extensively investigated in the past decade. However, accelerator designs for relatively bigger architectures have been of less attention yet. The Least Squares (LS) algorithm is widely used in digital signal processing applications, e.g., image reconstruction. This work proposes a novel LS accelerator design based on a heterogeneous architecture, where the heterogeneity is introduced using accurate and approximate processing cores. We have considered a case study of radio astronomy calibration processing that employs a complex-input iterative LS algorithm. Our proposed methodology exploits the intrinsic error-resilience of the aforesaid algorithm, where initial iterations are processed on approximate modules while the later ones on accurate modules. Our energy-quality experiments have shown up to 24% of energy savings as compared to an accurate (optimized) counterpart for biased designs and up to 29% energy savings when unbiasing is introduced. The proposed LS accelerator design does not increase the number of iterations and provides sufficient precision to converge to an acceptable solution." @default.
- W2944132666 created "2019-05-16" @default.
- W2944132666 creator A5034253211 @default.
- W2944132666 creator A5038847230 @default.
- W2944132666 creator A5078037091 @default.
- W2944132666 date "2019-04-30" @default.
- W2944132666 modified "2023-09-27" @default.
- W2944132666 title "Energy-efficient approximate least squares accelerator" @default.
- W2944132666 cites W2001335441 @default.
- W2944132666 cites W2026005150 @default.
- W2944132666 cites W2099198033 @default.
- W2944132666 cites W2099512056 @default.
- W2944132666 cites W2121069160 @default.
- W2944132666 cites W2147626801 @default.
- W2944132666 cites W2399535694 @default.
- W2944132666 cites W2623908577 @default.
- W2944132666 cites W2742536119 @default.
- W2944132666 cites W2765405778 @default.
- W2944132666 cites W2790332193 @default.
- W2944132666 cites W2889366309 @default.
- W2944132666 cites W2899084402 @default.
- W2944132666 cites W3101657927 @default.
- W2944132666 cites W4288660548 @default.
- W2944132666 doi "https://doi.org/10.1145/3310273.3323161" @default.
- W2944132666 hasPublicationYear "2019" @default.
- W2944132666 type Work @default.
- W2944132666 sameAs 2944132666 @default.
- W2944132666 citedByCount "1" @default.
- W2944132666 countsByYear W29441326662019 @default.
- W2944132666 crossrefType "proceedings-article" @default.
- W2944132666 hasAuthorship W2944132666A5034253211 @default.
- W2944132666 hasAuthorship W2944132666A5038847230 @default.
- W2944132666 hasAuthorship W2944132666A5078037091 @default.
- W2944132666 hasConcept C105795698 @default.
- W2944132666 hasConcept C185429906 @default.
- W2944132666 hasConcept C186370098 @default.
- W2944132666 hasConcept C33923547 @default.
- W2944132666 hasConcept C41008148 @default.
- W2944132666 hasConcept C9936470 @default.
- W2944132666 hasConceptScore W2944132666C105795698 @default.
- W2944132666 hasConceptScore W2944132666C185429906 @default.
- W2944132666 hasConceptScore W2944132666C186370098 @default.
- W2944132666 hasConceptScore W2944132666C33923547 @default.
- W2944132666 hasConceptScore W2944132666C41008148 @default.
- W2944132666 hasConceptScore W2944132666C9936470 @default.
- W2944132666 hasFunder F4320321800 @default.
- W2944132666 hasLocation W29441326661 @default.
- W2944132666 hasOpenAccess W2944132666 @default.
- W2944132666 hasPrimaryLocation W29441326661 @default.
- W2944132666 hasRelatedWork W1601330515 @default.
- W2944132666 hasRelatedWork W1987634297 @default.
- W2944132666 hasRelatedWork W2027259134 @default.
- W2944132666 hasRelatedWork W2058090705 @default.
- W2944132666 hasRelatedWork W2067694842 @default.
- W2944132666 hasRelatedWork W2088720623 @default.
- W2944132666 hasRelatedWork W2128399668 @default.
- W2944132666 hasRelatedWork W2132777649 @default.
- W2944132666 hasRelatedWork W2133428308 @default.
- W2944132666 hasRelatedWork W2374965391 @default.
- W2944132666 isParatext "false" @default.
- W2944132666 isRetracted "false" @default.
- W2944132666 magId "2944132666" @default.
- W2944132666 workType "article" @default.