{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:32:50Z","timestamp":1767339170886,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672526"],"award-info":[{"award-number":["61672526"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,2,1]]},"DOI":"10.23919\/date51398.2021.9474145","type":"proceedings-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T22:11:46Z","timestamp":1629843106000},"page":"657-662","source":"Crossref","is-referenced-by-count":20,"title":["HeSA: Heterogeneous Systolic Array Architecture for Compact CNNs Hardware Accelerators"],"prefix":"10.23919","author":[{"given":"Rui","family":"Xu","sequence":"first","affiliation":[]},{"given":"Sheng","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Yaohua","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Guo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures","author":"hasan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Addressing the issue of processing element under-utilization in general-purpose systolic deep learning accelerators","author":"bosheng","year":"0","journal-title":"Proc Asia and South Pacific Design Automation Conference"},{"key":"ref12","article-title":"Google supercharges machine learning tasks with TPU custom chip","volume":"18","author":"norm","year":"2016","journal-title":"Google Blog"},{"key":"ref13","article-title":"DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator","author":"nandan kumar","year":"0","journal-title":"2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"},{"key":"ref14","article-title":"Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization","author":"kung","year":"2018","journal-title":"arXiv Learning"},{"key":"ref15","article-title":"Sparse-TPU: Adapting Systolic Arrays for Sparse Matrices","author":"xin","year":"0","journal-title":"International Conference on Supercomputing (ICS 2010)"},{"key":"ref16","article-title":"Imagenet classification with deep convolutional neural networks","author":"alex","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Deep residual learning for image recognition","author":"kaiming","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref4","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"mingxing","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Mixconv: Mixed depthwise convolutional kernels","author":"mingxing","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Scale-sim: Systolic cnn accelerator simulator","author":"ananda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training","author":"sangkug","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"127","article-title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks","volume":"52","author":"yu-hsin","year":"2016","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1109\/JETCAS.2019.2910232","article-title":"Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices","volume":"9","author":"yu-hsin","year":"2019","journal-title":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems"},{"key":"ref2","article-title":"Searching for mobi1enetv3","author":"andrew","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref1","first-page":"485","article-title":"Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey","volume":"108","author":"lei","year":"0","journal-title":"Proceedings of the IEEE"},{"key":"ref9","article-title":"ShiDianNao: Shifting vision processing closer to the sensor","author":"zidong","year":"0","journal-title":"Proceedings of the 42Nd Annual International Symposium on Computer Architecture"}],"event":{"name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","start":{"date-parts":[[2021,2,1]]},"location":"Grenoble, France","end":{"date-parts":[[2021,2,5]]}},"container-title":["2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9473901\/9473226\/09474145.pdf?arnumber=9474145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T21:41:20Z","timestamp":1643319680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9474145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,1]]},"references-count":17,"URL":"https:\/\/doi.org\/10.23919\/date51398.2021.9474145","relation":{},"subject":[],"published":{"date-parts":[[2021,2,1]]}}}