{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:36Z","timestamp":1750219836892,"version":"3.41.0"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T00:00:00Z","timestamp":1694217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100013061","name":"Jilin Scientific and Technological Development Program","doi-asserted-by":"crossref","award":["20220201139GX"],"award-info":[{"award-number":["20220201139GX"]}],"id":[{"id":"10.13039\/501100013061","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2023,9,30]]},"abstract":"<jats:p>Convolutional neural network (CNN) accelerators are popular specialized platforms for efficient CNN processing. As semiconductor manufacturing technology scales down to nano scale, process variation dramatically affects the chip\u2019s quality. Process variation causes delay variation within the chip due to transistor parameter differences. CNN accelerators adopt a large number of processing elements (PEs) for parallel computing, which are highly susceptible to process variation effects. Fast CNN processing desires consistent performance among PEs; otherwise the processing speed is limited by the slowest PE within the chip. In this work, we first quantitatively model and analyze the impact of process variation on CNN accelerators\u2019 operating frequency. We further analyze the utilization of CNN accelerators and the characteristics of CNN models. We then leverage the PE underutilization to propose a sub-matrix reformation mechanism and leverage the pixel similarity of images to propose a weight transfer technique. Both techniques are able to tolerate the low-frequency PEs and achieve performance improvement at chip level. Furthermore, a novel resilience-aware mapping technique that exploits the diversity in the importance of weights is also proposed to improve the performance. Evaluation results show that our techniques are able to achieve significant processing speed improvement with negligible accuracy loss.<\/jats:p>","DOI":"10.1145\/3604236","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T10:50:06Z","timestamp":1686221406000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving the Performance of CNN Accelerator Architecture under the Impact of Process Variations"],"prefix":"10.1145","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8256-7585","authenticated-orcid":false,"given":"Jingweijia","family":"Tan","sequence":"first","affiliation":[{"name":"Jilin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6536-973X","authenticated-orcid":false,"given":"Weiren","family":"Wang","sequence":"additional","affiliation":[{"name":"Jilin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1291-7268","authenticated-orcid":false,"given":"Maodi","family":"Ma","sequence":"additional","affiliation":[{"name":"Jilin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5597-3625","authenticated-orcid":false,"given":"Xiaohui","family":"Wei","sequence":"additional","affiliation":[{"name":"Jilin University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9154-3294","authenticated-orcid":false,"given":"Kaige","family":"Yan","sequence":"additional","affiliation":[{"name":"Jilin University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,9,9]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Cifar-10 CNN. n.d. https:\/\/keras.io\/examples\/cifar10_cnn\/."},{"key":"e_1_3_1_3_2","unstructured":"International Technology Roadmap for Semiconductors. n.d. http:\/\/www.itrs2.net\/."},{"key":"e_1_3_1_4_2","unstructured":"Keras. n.d. https:\/\/keras.io\/."},{"key":"e_1_3_1_5_2","unstructured":"Process integration devices and structures by semiconductor industry association. n.d. https:\/\/www.semiconductors.org\/resources\/2009-international-technology-roadmap-for-semiconductors-itrs\/pids\/. 05 Sep 2018."},{"key":"e_1_3_1_6_2","unstructured":"TensorFlow. n.d. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2014.189"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/12.223671"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/996566.996588"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_1_14_2","unstructured":"Tim Edwards. 2019. Qflow 1.3: An Open-Source Digital Synthesis Flow. http:\/\/opencircuitdesign.com\/qflow\/."},{"key":"e_1_3_1_15_2","volume-title":"International Symposium on Quality of Electronic Design","author":"Friedberg P.","year":"2005","unstructured":"P. Friedberg, Y. Cao, J. Cain, R. Wang, and C. Spanos. 2005. Modeling within-die spatial correlation effects for process-design co-optimization. In International Symposium on Quality of Electronic Design."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2980098"},{"key":"e_1_3_1_17_2","article-title":"Deep residual learning for image recognition","volume":"1512","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). arxiv:1512.03385http:\/\/arxiv.org\/abs\/1512.03385.","journal-title":"CoRR"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196004"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2012.6263951"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/12.21144"},{"key":"e_1_3_1_22_2","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. Citeseer."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.37"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00015"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_1_28_2","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"1409","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014).","journal-title":"CoRR"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSE.2007.44"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.1986.1586118"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.57"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627613"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196129"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/VTS.2018.8368656"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604236","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:42Z","timestamp":1750178802000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,9]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,9,30]]}},"alternative-id":["10.1145\/3604236"],"URL":"https:\/\/doi.org\/10.1145\/3604236","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"type":"print","value":"1084-4309"},{"type":"electronic","value":"1557-7309"}],"subject":[],"published":{"date-parts":[[2023,9,9]]},"assertion":[{"value":"2022-10-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-28","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}