{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:15:19Z","timestamp":1767860119583,"version":"3.49.0"},"reference-count":58,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/hpca.2016.7446050","type":"proceedings-article","created":{"date-parts":[[2016,4,4]],"date-time":"2016-04-04T22:03:56Z","timestamp":1459807436000},"page":"14-26","source":"Crossref","is-referenced-by-count":119,"title":["TABLA: A unified template-based framework for accelerating statistical machine learning"],"prefix":"10.1109","author":[{"given":"Divya","family":"Mahajan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongse","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Amaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hardik","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Yazdanbakhsh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Kyung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadi","family":"Esmaeilzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Hyperspectral images clustering on reconfigurable hardware using the k-means algorithm","author":"gda","year":"2003","journal-title":"SBCCI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.961"},{"key":"ref33","article-title":"GPU acceleration for support vector machines","author":"athanasopoulos","year":"2011","journal-title":"International Workshop on Image Analysis for Multimedia Interactive Services"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"ref31","article-title":"Implementation of a fast artificial neural network library (FANN). Technical report, Department of Computer Science University of Copenhagen (DIKU)","author":"nissen","year":"2003"},{"key":"ref30","first-page":"27:1","article-title":"Libsvm: A library for support vector machines","volume":"2","author":"chih-chung","year":"2011","journal-title":"ACM Trans Intell Syst Technol"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/AHS.2011.5963944"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537602"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2514641.2514649"},{"key":"ref34","article-title":"cudnn: Efficient primitives for deep learning","author":"chetlur","year":"2014","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.97"},{"key":"ref27","first-page":"801","article-title":"MLPACK: A scalable C++ machine learning library","volume":"14","author":"curtin","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"ref2","first-page":"365","article-title":"Dark silicon and the end of multicore scaling","author":"esmaeilzadeh","year":"2011","journal-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA) ISCA"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.77"},{"key":"ref20","article-title":"Second workshop on information heterogeneity and fusion in recommender systems (HetRec)","author":"cantador","year":"2011","journal-title":"Proceedings of the 5th ACM Conference on Recommender Systems RecSys 2011"},{"key":"ref22","first-page":"51","article-title":"Neurocomputing, using the MasPar MP-1","author":"grajski","year":"1993","journal-title":"Parallel Digital Implementations of Neural Networks chapter 2"},{"key":"ref21","article-title":"Grouplens","year":"0","journal-title":"MovieLens dataset"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.48"},{"key":"ref26","first-page":"1871","article-title":"Liblinear: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref25","author":"jetson","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2006.8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2008.54"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2013.6645495"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485945"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950435"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1723112.1723129"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1344671.1344720"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73040-8_52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155623"},{"key":"ref11","article-title":"Sirius: An open end-to-end voice and vision personal assistant and its implications for future warehouse scale computers","author":"johann","year":"2015","journal-title":"ASPLOS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2010.39"},{"key":"ref12","article-title":"Where's the beef? why FPGAs are so fast","author":"sirowy","year":"2008","journal-title":"Technical Report MSR-TR-2008-130 Microsoft Research"},{"key":"ref13","year":"2014","journal-title":"Zynq-7000 All Programmable SoC"},{"key":"ref14","article-title":"Intel Corporation","year":"0","journal-title":"Disrupting the Data Center to Create the Digital Services Economy"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213874"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2117-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref19","author":"lichman","year":"2013","journal-title":"UCI Machine Learning Repository"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.1974.1050511"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736044"},{"key":"ref6","author":"gantz","year":"0","journal-title":"Extracting Value from Chaos"},{"key":"ref5","first-page":"10:10","article-title":"CPU DB: Recording microprocessor history","volume":"10","author":"andrew","year":"2012","journal-title":"ACM Queue"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749755"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853195"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1661438.1661439"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155640"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228465"},{"key":"ref45","article-title":"a small-footprint high-throughput accelerator for ubiquitous machine-learning","author":"chen","year":"0","journal-title":"Asplos 2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2011.5941086"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056066"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2010.2100802"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2009.34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"ref43","first-page":"6:1","article-title":"A massively parallel, energy efficient programmable accelerator for learning and classification","volume":"9","author":"abhinandan","year":"2012","journal-title":"ACM Trans Archit Code Optim"}],"event":{"name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Barcelona, Spain","start":{"date-parts":[[2016,3,12]]},"end":{"date-parts":[[2016,3,16]]}},"container-title":["2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7440961\/7446041\/7446050.pdf?arnumber=7446050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2016,9,30]],"date-time":"2016-09-30T01:20:04Z","timestamp":1475198404000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7446050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/hpca.2016.7446050","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}