{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T22:08:32Z","timestamp":1792966112448,"version":"4.5.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/iiswc47752.2019.9042017","type":"proceedings-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T08:55:14Z","timestamp":1584694514000},"page":"257-262","source":"Crossref","is-referenced-by-count":3,"title":["Performance-driven Programming of Multi-TFLOP Deep Learning Accelerators"],"prefix":"10.1109","author":[{"given":"Swagath","family":"Venkataramani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungwook","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijayalakshmi","family":"Srinivasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailash","family":"Gopalakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leland","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2931584"},{"key":"ref32","article-title":"Glow: Graph lowering compiler techniques for neural networks","author":"rotem","year":"2018","journal-title":"CoRR abs\/1805 00907"},{"key":"ref31","article-title":"Intel ngraph: An intermediate representation, compiler, and executor for deep learning","author":"cyphers","year":"2018","journal-title":"CoRR abs\/1801 08058"},{"key":"ref30","first-page":"578","article-title":"TVM: an automated end-to-end optimizing compiler for deep learning","author":"chen","year":"0","journal-title":"Proc OSDI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CoolChips.2019.8721357"},{"key":"ref10","first-page":"1","article-title":"Quality programmable vector processors for approximate computing","author":"chippa","year":"2013","journal-title":"Proceedings of the 46th Annual IEEE\/ACM International Symposium on Microarchitecture MICRO-46"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.21"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.106"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2133382.2133388"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2009.25"},{"key":"ref28","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"CoRR abs\/1512 03385"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR abs\/1409 1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815993"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref29","first-page":"265","article-title":"Tensor-flow: A system for large-scale machine learning","author":"abadi","year":"0","journal-title":"Proc OSDI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001178"},{"key":"ref1","article-title":"A scalable multi-teraops deep learning processor core for ai training and inference","author":"fleischer","year":"0","journal-title":"Proc VLSI Symposium"},{"key":"ref20","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 ACMISIGDA International Symposium on Field-Programmable Gate Arrays"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2016.7428073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC.2015.41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref26","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2015.60"}],"event":{"name":"2019 IEEE International Symposium on Workload Characterization (IISWC)","location":"Orlando, FL, USA","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,5]]}},"container-title":["2019 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9027808\/9041927\/09042017.pdf?arnumber=9042017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:19:25Z","timestamp":1657855165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9042017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iiswc47752.2019.9042017","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}