{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T05:26:25Z","timestamp":1783833985115,"version":"3.55.0"},"reference-count":66,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/micro.2016.7783738","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T22:11:05Z","timestamp":1482185465000},"page":"1-13","source":"Crossref","is-referenced-by-count":12,"title":["CANDY: Enabling coherent DRAM caches for multi-node systems"],"prefix":"10.1109","author":[{"given":"Chiachen","family":"Chou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aamer","family":"Jaleel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moinuddin K.","family":"Qureshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/125826.125925"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2629677"},{"key":"ref32","year":"2010","journal-title":"Introduction to Magny-Cours AMD"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835928"},{"key":"ref30","article-title":"Sed: A scalable coherence directory with flexible sharer set encoding","author":"sanchez","year":"2012","journal-title":"Proceedings of the 2012 IEEE 18th International Symposium on High-Performance Computer Architecture ser HPCA '12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1995.524546"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/800015.808204"},{"key":"ref35","year":"2001","journal-title":"AMD Hyper Transport AMD"},{"key":"ref34","year":"2009","journal-title":"Intel QuickPath Interconnect Intel"},{"key":"ref60","year":"2013","journal-title":"OpenSPARC T2 Overview Oracle"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72905-1_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749726"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1332-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2200\/S00346ED1V01Y201104CAC016"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1302981"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2005.30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000076"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-11515-8_3","article-title":"Remote store programming: A memory model for embedded multicore","author":"hoffmann","year":"2010","journal-title":"Proceedings of the 5th International Conference on High Performance Embedded Architectures and Compilers ser HiPEAC'10 Springer-Verlag"},{"key":"ref2","article-title":"JEDEC","year":"2013","journal-title":"High Bandwidth Memory (HBM) DRAM (JESD235) JEDEC"},{"key":"ref1","volume":"1 0","year":"2013","journal-title":"HMC Specification"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628089"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750387"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.36"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1988.5238"},{"key":"ref23","first-page":"312","article-title":"Reducing memory and traffic requirements for scalable directory-based cache coherence schemes","author":"gupta","year":"1990","journal-title":"International Conference on Parallel Processing"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1990.134520"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/2.769448"},{"key":"ref51","year":"2013","journal-title":"Linux 3 8 Automatic NUMA balancing Linux"},{"key":"ref59","first-page":"282","article-title":"Piranha: a scalable architecture based on single-chip multiprocessing","author":"barroso","year":"2000","journal-title":"Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat No RS00201) ISCA"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669166"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2008.4658623"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.31"},{"key":"ref55","first-page":"234","article-title":"Regionscout: exploiting coarse grain sharing in snoop-based coherence","author":"moshovos","year":"2005","journal-title":"ISCA '05 Proceedings of the 2005 International Symposium on Computer Architecture"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2209249.2209269"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2814328"},{"key":"ref52","year":"0","journal-title":"Microsoft Windows NUMA Support Microsoft"},{"key":"ref10","year":"2015","journal-title":"Nvidia updates GPU Roadmap Announces Pascal"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155673"},{"key":"ref40","article-title":"Nu-minebench 2.0","author":"pisharath","year":"2005","journal-title":"Center for Ultra-Scale Computing and Information Security Northwestern University"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2012.2"},{"key":"ref13","article-title":"Challenges in heterogeneous die-stacked and off-chip memory systems","author":"loh","year":"2012","journal-title":"3rd Workshop on SoCs Heterogeneous Architectures and Workloads"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.51"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.63"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.56"},{"key":"ref4","article-title":"JEDEC","year":"2011","journal-title":"I\/O SINGLE DATA RATE (WIDE I\/O SDR) JEDEC"},{"key":"ref3","year":"2014","journal-title":"Micron HMC Gen2 Micron"},{"key":"ref6","year":"2013","journal-title":"DDR4 SPEC (JESD79-4)"},{"key":"ref5","article-title":"1 Gb\\_DDR3\\_SDRAM","year":"2010","journal-title":"Micron"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2016.25"},{"key":"ref7","article-title":"Intel Xeon Phi","year":"2014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264205"},{"key":"ref9","year":"2015","journal-title":"AMD Radeon R9 AMD"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.1989.47168"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830774"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1145\/146628.139705","article-title":"Comparative performance evaluation of cache-coherent numa and coma architectures","author":"stenstr\u00f6m","year":"1992","journal-title":"Proceedings of the 19th Annual International Symposium on Computer Architecture Ser ISCA '92"},{"key":"ref47","first-page":"78:1","article-title":"Allarm: Optimizing sparse directories for thread-local data","author":"roy","year":"2014","journal-title":"Proceedings of the Conference Design Automation & Test in Europe ser DATE ’ 14 European Design and Automation Association"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/361268.361281"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/2370816.2370820","article-title":"Power-Aware Multi-Core Simulation for Early Design Stage Hardware\/Software Co-Optimization","author":"wim heirman","year":"2012","journal-title":"In International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.59"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1997.645797"}],"event":{"name":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","location":"Taipei, Taiwan","start":{"date-parts":[[2016,10,15]]},"end":{"date-parts":[[2016,10,19]]}},"container-title":["2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7777315\/7783693\/07783738.pdf?arnumber=7783738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T00:32:30Z","timestamp":1658190750000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7783738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/micro.2016.7783738","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}