Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120792801> ?p ?o ?g. }
- W3120792801 abstract "A mass of data transfer between the processing and storage units has been the leading bottleneck in modern Von-Neuman computing systems, especially when used for Artificial Intelligence (AI) tasks. Computing-in-Memory (CIM) has shown great potential to reduce both latency and power consumption. However, the conventional analog CIM schemes are suffering from reliability issues, which may significantly degenerate the accuracy of the computation. Recently, CIM schemes with digitized input data and weights have been proposed for high reliable computing. However, the properties of the digital memory and input data are not fully utilized. This paper presents a novel low power CIM scheme to further reduce the power consumption by using a Modified Radix-4 (M-RD4) booth algorithm at the input and a Modified Canonical Signed Digit (M-CSD) for the network weights. The simulation results show that M-Rd4 and M-CSD reduce the ratio of $1times1$ by 78.5% on LeNet and 80.2% on AlexNet, and improve the computing efficiency by 41.6% in average. The computing-power rate at the fixed-point 8-bit is 60.68 TOPS/s/W." @default.
- W3120792801 created "2021-01-18" @default.
- W3120792801 creator A5029202186 @default.
- W3120792801 creator A5040507818 @default.
- W3120792801 creator A5088701762 @default.
- W3120792801 creator A5091073331 @default.
- W3120792801 date "2021-01-07" @default.
- W3120792801 modified "2023-10-18" @default.
- W3120792801 title "A Low Power In-Memory Multiplication andAccumulation Array with Modified Radix-4 Inputand Canonical Signed Digit Weights" @default.
- W3120792801 cites W1937359183 @default.
- W3120792801 cites W2026445983 @default.
- W3120792801 cites W2076613578 @default.
- W3120792801 cites W2112796928 @default.
- W3120792801 cites W2131256658 @default.
- W3120792801 cites W2138913040 @default.
- W3120792801 cites W2157061035 @default.
- W3120792801 cites W2194775991 @default.
- W3120792801 cites W2300242332 @default.
- W3120792801 cites W2319920447 @default.
- W3120792801 cites W2329040051 @default.
- W3120792801 cites W2404581299 @default.
- W3120792801 cites W2508602506 @default.
- W3120792801 cites W2518281301 @default.
- W3120792801 cites W2560615381 @default.
- W3120792801 cites W2565516711 @default.
- W3120792801 cites W2618530766 @default.
- W3120792801 cites W2747891096 @default.
- W3120792801 cites W2782791387 @default.
- W3120792801 cites W2783525259 @default.
- W3120792801 cites W2798010625 @default.
- W3120792801 cites W2800653266 @default.
- W3120792801 cites W2803914619 @default.
- W3120792801 cites W2809171749 @default.
- W3120792801 cites W2897004326 @default.
- W3120792801 cites W2898994846 @default.
- W3120792801 cites W2919115771 @default.
- W3120792801 cites W2923010225 @default.
- W3120792801 cites W2960778947 @default.
- W3120792801 cites W2964348643 @default.
- W3120792801 cites W3003821665 @default.
- W3120792801 cites W3005729543 @default.
- W3120792801 cites W3015432327 @default.
- W3120792801 cites W3015980402 @default.
- W3120792801 cites W3015982917 @default.
- W3120792801 cites W3017574963 @default.
- W3120792801 cites W3101272433 @default.
- W3120792801 cites W2617093514 @default.
- W3120792801 doi "https://doi.org/10.48550/arxiv.2101.02419" @default.
- W3120792801 hasPublicationYear "2021" @default.
- W3120792801 type Work @default.
- W3120792801 sameAs 3120792801 @default.
- W3120792801 citedByCount "0" @default.
- W3120792801 crossrefType "posted-content" @default.
- W3120792801 hasAuthorship W3120792801A5029202186 @default.
- W3120792801 hasAuthorship W3120792801A5040507818 @default.
- W3120792801 hasAuthorship W3120792801A5088701762 @default.
- W3120792801 hasAuthorship W3120792801A5091073331 @default.
- W3120792801 hasBestOaLocation W31207928011 @default.
- W3120792801 hasConcept C11413529 @default.
- W3120792801 hasConcept C114614502 @default.
- W3120792801 hasConcept C121332964 @default.
- W3120792801 hasConcept C149635348 @default.
- W3120792801 hasConcept C154945302 @default.
- W3120792801 hasConcept C163258240 @default.
- W3120792801 hasConcept C173608175 @default.
- W3120792801 hasConcept C2779091547 @default.
- W3120792801 hasConcept C2780513914 @default.
- W3120792801 hasConcept C2780595030 @default.
- W3120792801 hasConcept C2984118289 @default.
- W3120792801 hasConcept C33923547 @default.
- W3120792801 hasConcept C41008148 @default.
- W3120792801 hasConcept C45374587 @default.
- W3120792801 hasConcept C50644808 @default.
- W3120792801 hasConcept C53442348 @default.
- W3120792801 hasConcept C59822182 @default.
- W3120792801 hasConcept C62520636 @default.
- W3120792801 hasConcept C76155785 @default.
- W3120792801 hasConcept C82876162 @default.
- W3120792801 hasConcept C86803240 @default.
- W3120792801 hasConcept C9390403 @default.
- W3120792801 hasConcept C94375191 @default.
- W3120792801 hasConceptScore W3120792801C11413529 @default.
- W3120792801 hasConceptScore W3120792801C114614502 @default.
- W3120792801 hasConceptScore W3120792801C121332964 @default.
- W3120792801 hasConceptScore W3120792801C149635348 @default.
- W3120792801 hasConceptScore W3120792801C154945302 @default.
- W3120792801 hasConceptScore W3120792801C163258240 @default.
- W3120792801 hasConceptScore W3120792801C173608175 @default.
- W3120792801 hasConceptScore W3120792801C2779091547 @default.
- W3120792801 hasConceptScore W3120792801C2780513914 @default.
- W3120792801 hasConceptScore W3120792801C2780595030 @default.
- W3120792801 hasConceptScore W3120792801C2984118289 @default.
- W3120792801 hasConceptScore W3120792801C33923547 @default.
- W3120792801 hasConceptScore W3120792801C41008148 @default.
- W3120792801 hasConceptScore W3120792801C45374587 @default.
- W3120792801 hasConceptScore W3120792801C50644808 @default.
- W3120792801 hasConceptScore W3120792801C53442348 @default.
- W3120792801 hasConceptScore W3120792801C59822182 @default.
- W3120792801 hasConceptScore W3120792801C62520636 @default.
- W3120792801 hasConceptScore W3120792801C76155785 @default.