{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:31Z","timestamp":1774365571969,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/micro.2016.7783717","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T22:11:05Z","timestamp":1482185465000},"page":"1-12","source":"Crossref","is-referenced-by-count":17,"title":["Cache-emulated register file: An integrated on-chip memory architecture for high performance GPGPUs"],"prefix":"10.1109","author":[{"given":"Naifeng","family":"Jing","sequence":"first","affiliation":[]},{"given":"Jianfei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Fengfeng","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Wenkang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaoyao","family":"Liang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2016604.2016608"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2016.2584623"},{"key":"ref31","first-page":"55","article-title":"Bank stealing for conflict mitigation in GPGPU register file","author":"jing","year":"2015","journal-title":"Proceedings of the International Symposium on Low power Electronics and Design (ISLPED)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2818374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485952"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2611758"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522337"},{"key":"ref16","article-title":"GPGPU register file management by hardware cooperated register reallocation","author":"jeon","year":"2014","journal-title":"Computer Engineering Technical Report Number CENG-2014-05 in University of Southern California"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830784"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2013.6629258"},{"key":"ref19","author":"appel","year":"1997","journal-title":"Modern Compiler Implementation in C Basic Techniques"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000093"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2015.2417545"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.18"},{"key":"ref27","article-title":"Power-performance co-optimization of throughput core architecture using resistive memory","author":"nilanjan goswami","year":"2013","journal-title":"Proceedings of the Annual IEEE International Symposium on High Performance Computer Architecture"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750417"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"key":"ref2","article-title":"Nvidia's next generation CUDA compute architecture: Kepler GK110","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750418"},{"key":"ref1","article-title":"Nvidia's next generation CUDA compute architecture: Fermi","year":"0"},{"key":"ref20","article-title":"Parallel thread execution ISA version 3.0","year":"2012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref21","year":"0","journal-title":"Cuda Sdk"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref26","first-page":"247","article-title":"SRAM-DRAM hybrid memory with applications to efficient register files in fine-grained multi-threading","author":"yu","year":"2011","journal-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA) ISCA"},{"key":"ref25","year":"0","journal-title":"CACTI An Integrated Cache and Memory Access Time Cycle Time Area Leakage and Dynamic Power Model"}],"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\/07783717.pdf?arnumber=7783717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T17:58:36Z","timestamp":1483639116000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7783717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/micro.2016.7783717","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}