FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118337360> ?p ?o ?g. }

• W3118337360 endingPage "460" @default.
• W3118337360 startingPage "447" @default.
• W3118337360 abstract "Traditional convolutional neural network (CNN) architectures suffer from two bottlenecks: computational complexity and memory access cost. In this study, an efficient in-memory convolution accelerator (IMCA) is proposed based on associative in-memory processing to alleviate these two problems directly. In the IMCA, the convolution operations are directly performed inside the memory as in-place operations. The proposed memory computational structure allows for a significant improvement in computational metrics, namely, TOPS/W. Furthermore, due to its unconventional computation style, the IMCA can take advantage of many potential opportunities, such as constant multiplication, bit-level sparsity, and dynamic approximate computing, which, while supported by traditional architectures, require extra overhead to exploit, thus reducing any potential gains. The proposed accelerator architecture exhibits a significant efficiency in terms of area and performance, achieving around 0.65 GOPS and 1.64 TOPS/W at 16-bit fixed-point precision with an area less than 0.25 mm <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> ." @default.
• W3118337360 created "2021-01-18" @default.
• W3118337360 creator A5012920132 @default.
• W3118337360 creator A5013660772 @default.
• W3118337360 creator A5068089858 @default.
• W3118337360 date "2021-03-01" @default.
• W3118337360 modified "2023-09-26" @default.
• W3118337360 title "IMCA: An Efficient In-Memory Convolution Accelerator" @default.
• W3118337360 cites W1677182931 @default.
• W3118337360 cites W1801710398 @default.
• W3118337360 cites W1977030506 @default.
• W3118337360 cites W1989831790 @default.
• W3118337360 cites W2019459561 @default.
• W3118337360 cites W2019947514 @default.
• W3118337360 cites W2021383442 @default.
• W3118337360 cites W2029403235 @default.
• W3118337360 cites W2031342191 @default.
• W3118337360 cites W2039875226 @default.
• W3118337360 cites W2044535169 @default.
• W3118337360 cites W2062395401 @default.
• W3118337360 cites W2067523571 @default.
• W3118337360 cites W2074084814 @default.
• W3118337360 cites W2096029841 @default.
• W3118337360 cites W2099911327 @default.
• W3118337360 cites W2105102111 @default.
• W3118337360 cites W2114094169 @default.
• W3118337360 cites W2144289559 @default.
• W3118337360 cites W2152839228 @default.
• W3118337360 cites W2290132443 @default.
• W3118337360 cites W2518281301 @default.
• W3118337360 cites W2577617591 @default.
• W3118337360 cites W2591922920 @default.
• W3118337360 cites W2604319603 @default.
• W3118337360 cites W2606722458 @default.
• W3118337360 cites W2757647500 @default.
• W3118337360 cites W2789901355 @default.
• W3118337360 cites W2794141774 @default.
• W3118337360 cites W2798447999 @default.
• W3118337360 cites W2801748224 @default.
• W3118337360 cites W2801795932 @default.
• W3118337360 cites W2807127337 @default.
• W3118337360 cites W2877207791 @default.
• W3118337360 cites W2888687637 @default.
• W3118337360 cites W2897083155 @default.
• W3118337360 cites W2920326572 @default.
• W3118337360 cites W2945146780 @default.
• W3118337360 cites W2946185430 @default.
• W3118337360 cites W2950865323 @default.
• W3118337360 cites W2964081807 @default.
• W3118337360 cites W2964988320 @default.
• W3118337360 cites W2966602607 @default.
• W3118337360 cites W2979706619 @default.
• W3118337360 cites W2981240739 @default.
• W3118337360 cites W3003821665 @default.
• W3118337360 cites W3024621361 @default.
• W3118337360 cites W3037261029 @default.
• W3118337360 cites W3038325958 @default.
• W3118337360 cites W4255133361 @default.
• W3118337360 doi "https://doi.org/10.1109/tvlsi.2020.3047641" @default.
• W3118337360 hasPublicationYear "2021" @default.
• W3118337360 type Work @default.
• W3118337360 sameAs 3118337360 @default.
• W3118337360 citedByCount "5" @default.
• W3118337360 countsByYear W31183373602022 @default.
• W3118337360 countsByYear W31183373602023 @default.
• W3118337360 crossrefType "journal-article" @default.
• W3118337360 hasAuthorship W3118337360A5012920132 @default.
• W3118337360 hasAuthorship W3118337360A5013660772 @default.
• W3118337360 hasAuthorship W3118337360A5068089858 @default.
• W3118337360 hasBestOaLocation W31183373602 @default.
• W3118337360 hasConcept C111919701 @default.
• W3118337360 hasConcept C113775141 @default.
• W3118337360 hasConcept C11413529 @default.
• W3118337360 hasConcept C114614502 @default.
• W3118337360 hasConcept C123593499 @default.
• W3118337360 hasConcept C154945302 @default.
• W3118337360 hasConcept C159423971 @default.
• W3118337360 hasConcept C164120249 @default.
• W3118337360 hasConcept C173608175 @default.
• W3118337360 hasConcept C176649486 @default.
• W3118337360 hasConcept C179799912 @default.
• W3118337360 hasConcept C194222762 @default.
• W3118337360 hasConcept C202444582 @default.
• W3118337360 hasConcept C23123220 @default.
• W3118337360 hasConcept C2779960059 @default.
• W3118337360 hasConcept C2780595030 @default.
• W3118337360 hasConcept C33923547 @default.
• W3118337360 hasConcept C41008148 @default.
• W3118337360 hasConcept C45347329 @default.
• W3118337360 hasConcept C45374587 @default.
• W3118337360 hasConcept C459310 @default.
• W3118337360 hasConcept C50644808 @default.
• W3118337360 hasConcept C80444323 @default.
• W3118337360 hasConcept C81363708 @default.
• W3118337360 hasConcept C9390403 @default.
• W3118337360 hasConcept C94375191 @default.
• W3118337360 hasConcept C97854310 @default.
• W3118337360 hasConcept C98986596 @default.

• next