{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:56:17Z","timestamp":1763348177976,"version":"3.28.0"},"reference-count":117,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/icrc.2018.8638612","type":"proceedings-article","created":{"date-parts":[[2019,3,8]],"date-time":"2019-03-08T20:46:55Z","timestamp":1552078015000},"page":"1-13","source":"Crossref","is-referenced-by-count":26,"title":["Hardware-Software Co-Design for an Analog-Digital Accelerator for Machine Learning"],"prefix":"10.1109","author":[{"given":"Joao","family":"Ambrosi","sequence":"first","affiliation":[]},{"given":"Aayush","family":"Ankit","sequence":"additional","affiliation":[]},{"given":"Rodrigo","family":"Antunes","sequence":"additional","affiliation":[]},{"given":"Sai Rahul","family":"Chalamalasetti","sequence":"additional","affiliation":[]},{"given":"Soumitra","family":"Chatterjee","sequence":"additional","affiliation":[]},{"given":"Izzat El","family":"Hajj","sequence":"additional","affiliation":[]},{"given":"Guilherme","family":"Fachini","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Faraboschi","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Foltin","sequence":"additional","affiliation":[]},{"given":"Sitao","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Wen-Mei","family":"Hwu","sequence":"additional","affiliation":[]},{"given":"Gustavo","family":"Knuppe","sequence":"additional","affiliation":[]},{"given":"Sunil Vishwanathpur","family":"Lakshminarasimha","sequence":"additional","affiliation":[]},{"given":"Dejan","family":"Milojicic","sequence":"additional","affiliation":[]},{"given":"Mohan","family":"Parthasarathy","sequence":"additional","affiliation":[]},{"given":"Filipe","family":"Ribeiro","sequence":"additional","affiliation":[]},{"given":"Lucas","family":"Rosa","sequence":"additional","affiliation":[]},{"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[]},{"given":"Plinio","family":"Silveira","sequence":"additional","affiliation":[]},{"given":"John Paul","family":"Strachan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Caffe2 a lightweight modular and scalable deep learning framework","year":"0","key":"ref39"},{"journal-title":"CNTK The Microsoft Cognitive Toolkit","year":"0","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nnano.2017.83"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2016.7838429"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2015.2439635"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nature14441","article-title":"Training and operation of an integrated neuromorphic network based on metal-oxide memristors","volume":"521","author":"prezioso","year":"2015","journal-title":"Nature"},{"key":"ref37","article-title":"Coherent accelerator processor interface (CAPI)for POWER8 systems","author":"wile","year":"2014","journal-title":"tech rep IBM"},{"journal-title":"Gen-Z Consortium","article-title":"Gen-Z interconnect","year":"2016","key":"ref36"},{"journal-title":"CCIX Consortium","article-title":"CCIX interconnect","year":"2017","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201705914"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062326"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms3072"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627625"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2700234"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446049"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref101","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1145\/2983990.2984019","article-title":"Makalu: Fast recoverable allocation of non-volatile memory","author":"bhandari","year":"2016","journal-title":"Proceedings of the 2016 ACM SIGPLAN International Conference on Object-Oriented Programming Systems Languages and Applications"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"ref100","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1145\/2660193.2660224","article-title":"Atlas: Leveraging locks for non-volatile memory consistency","author":"chakrabarti","year":"2014","journal-title":"Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages & Applications"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2009.25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2016.7738695"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2017.8123649"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783724"},{"key":"ref54","first-page":"548","article-title":"Scalpel: Customizing dnn pruning to the underlying hardware parallelism","author":"yu","year":"2017","journal-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture ISCA ‘17"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783754"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref40","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IRETELC.1955.5407891"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1109\/EE.1961.6433557","article-title":"Analog computer simulates heart response to nerve stimulation","volume":"80","author":"gardner","year":"1961","journal-title":"Electrical Engineering"},{"key":"ref6","first-page":"230","article-title":"On computable numbers, with an application to the entschei-dungsproblem","volume":"s2 42","year":"1936","journal-title":"Proceedings of the London Mathematical Society"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1986.4788973"},{"journal-title":"Computer Organization and Design Fourth Edition Fourth Edition The Hardware\/Software Interface (The Morgan Kaufmann Series in Computer Architecture and Design)","year":"2008","author":"patterson","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/85.238389"},{"journal-title":"Neural network exchange format","year":"0","author":"group","key":"ref49"},{"journal-title":"Analog and Analog\/hybrid Computer Programming","year":"1971","author":"hausner","key":"ref9"},{"key":"ref46","article-title":"Mixed low-precision deep learning inference using dynamic fixed point","volume":"abs 1701 8978","author":"mellempudi","year":"2017","journal-title":"CoRR"},{"key":"ref45","article-title":"Deep neural network compression with single and multiple level quantization","volume":"abs 1803 3289","author":"xu","year":"2018","journal-title":"CoRR"},{"key":"ref48","first-page":"164","article-title":"Think Locally, Act Globally: Highly Balanced Graph Partitioning","volume":"7933","author":"sanders","year":"2013","journal-title":"Proceedings of the 12th International Symposium on Experimental Algorithms (SEA‘13)"},{"key":"ref47","article-title":"Fixed point quantization of deep convolutional networks","volume":"abs 1511 6393","author":"lin","year":"2015","journal-title":"CoRR"},{"journal-title":"NNEF Neural Network Exchange Format","year":"0","key":"ref42"},{"journal-title":"ONNX Open Neural Network Exchange Format","year":"0","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489341"},{"key":"ref43","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","volume":"abs 1806 8342","author":"krishnamoorthi","year":"2018","journal-title":"CoRR"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2009.5272559"},{"key":"ref72","article-title":"A survey of fpga based neural network accelerator","author":"guo","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080221"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898003"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2682138"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.106"},{"key":"ref62","first-page":"1","article-title":"4.6 al. 93tops\/w scalable deep learning\/inference processor with tetra-parallel mimd architecture for big-data applications","author":"park","year":"2015","journal-title":"Solid-State Circuits Conference-(ISSCC) 2015 IEEE International"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1145\/2742060.2743766","article-title":"Origami: A convolutional network accelerator","author":"cavigelli","year":"2015","journal-title":"Proceedings of the 25th Edition on Great Lakes Symposium on VLSI GLSVLSI ‘15"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref65","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1145\/2684746.2689060","article-title":"Optimizing fpga-based accelerator design for deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/EE.1950.6434088","article-title":"Nonlinear functions in an analog computer","volume":"69","author":"mccann","year":"1950","journal-title":"Electrical Engineering"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2018.8278135"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854329"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.30"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970337"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2016.17"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/QRS-C.2017.27"},{"key":"ref91","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1145\/3173162.3173176","article-title":"Maeri: Enabling flexible dataflow mapping over dnn accelerators via reconfigurable interconnects","author":"kwon","year":"2018","journal-title":"Proceedings of the third international conference on Architectural support for programming languages and operating systems - ASP"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.5220\/0005040101630169"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173205"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124543"},{"key":"ref103","first-page":"45","article-title":"Savi objects: sharing and virtuality incorporated","volume":"1","author":"hajj","year":"2017","journal-title":"Proceedings of the ACM on Programming Languages"},{"key":"ref102","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1145\/2872362.2872366","article-title":"Spacejmp: Programming with multiple virtual address spaces","author":"hajj","year":"2016","journal-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems"},{"key":"ref111","article-title":"Unmodified device driver reuse and improved system dependability via virtual machines","author":"levasseur","year":"2004","journal-title":"Proceedings of the 6th conference on Symposium on Operating Systems Design & Implementation"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW.2015.7107425"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150987"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950379"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950380"},{"key":"ref96","first-page":"1","article-title":"A machine-learning classifier implemented in a standard 6t sram array","author":"zhang","year":"2016","journal-title":"2016 IEEE Symposium on VLSI Circuits (VLSIC)"},{"key":"ref97","first-page":"1","article-title":"Rebooting the data access hierarchy of computing systems","author":"wen-mei","year":"2017","journal-title":"Rebooting Computing (ICRC) 2017 IEEE International Conference"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.1961.6373040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1972.5009043"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.1974.1161436"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537908"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001179"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref117","first-page":"41","article-title":"Qemu, a fast and portable dynamic translator","author":"bellard","year":"2005","journal-title":"Annual Technical Conference FREENIX Track"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228448"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898092"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2013.6575348"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/2524211.2524219"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref116","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1145\/1496909.1496921","article-title":"Cotson: Infrastructure for full system simulation","volume":"43","author":"argollo","year":"2009","journal-title":"SIGOPS Oper Syst Rev"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/244804.244807"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062307"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124552"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898011"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037746"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"}],"event":{"name":"2018 IEEE International Conference on Rebooting Computing (ICRC)","start":{"date-parts":[[2018,11,7]]},"location":"McLean, VA, USA","end":{"date-parts":[[2018,11,9]]}},"container-title":["2018 IEEE International Conference on Rebooting Computing (ICRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8634807\/8638586\/08638612.pdf?arnumber=8638612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T15:37:16Z","timestamp":1663083436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8638612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":117,"URL":"https:\/\/doi.org\/10.1109\/icrc.2018.8638612","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}