{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T05:26:29Z","timestamp":1783833989877,"version":"3.55.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/micro.2016.7783729","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T17:11:05Z","timestamp":1482167465000},"page":"1-14","source":"Crossref","is-referenced-by-count":29,"title":["Lazy release consistency for GPUs"],"prefix":"10.1109","author":[{"given":"Johnathan","family":"Alsop","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc S.","family":"Orr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradford M.","family":"Beckmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David A.","family":"Wood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830778"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694356"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694350"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2012.7476485"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375591"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2814270.2814283"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/146628.139676","article-title":"Lazy release consistency for software distributed shared memory","author":"keleher","year":"1992","journal-title":"Proceedings of the 19th Annual Symposium on Computer Architecture"},{"key":"ref17","article-title":"AMD's GEM5 APU simulator","year":"0","journal-title":"AMD Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"ref19","article-title":"GPU Computing Gems Jade","author":"cederman","year":"0","journal-title":"Dynamic Load-Balancing Using Work Stealing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835930"},{"key":"ref4","article-title":"CUDA C Programming Guide","year":"0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540747"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1990.134502"},{"key":"ref6","article-title":"HSA Programmer's Reference Manual: HSAIL Virtual ISA and Programming Model, Compiler Writer's Guide, and Object Format (BRIG) Version 1.0 Provisional","year":"2013","journal-title":"HSA Foundation Spring"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"key":"ref5","article-title":"The OpenCL Specification (Version 2.0)","author":"munshi","year":"2013","journal-title":"Khronos OpenCL Working Group"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2701618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541981"},{"key":"ref2","article-title":"Working Draft, Standard for Programming Language C++","year":"0","journal-title":"International Organization for Standardization"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908114"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2200\/S00346ED1V01Y201104CAC016"},{"key":"ref20","first-page":"1:1","article-title":"The University of Florida Sparse Matrix Collection, T. A. Davis and Y. Hu","volume":"38","year":"2011","journal-title":"ACM Transactions on Mathematical Software"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370853"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/ISCA.1995.524548","article-title":"Dynamic self-invalidation: reducing coherence overhead in shared-memory multiprocessors","author":"lebeck","year":"1995","journal-title":"Proceedings 22nd Annual International Symposium on Computer Architecture ISCA"},{"key":"ref24","article-title":"RC3: Consistency directed cache coherence for x86-64 with RC extensions","author":"elver","year":"2015","journal-title":"International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835927"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485940"},{"key":"ref25","article-title":"DeNovoND: efficient hardware support for disciplined non-determinism","author":"sung","year":"2014","journal-title":"Proceedings of the 47th International Symposium on Microarchitecture"}],"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\/07783729.pdf?arnumber=7783729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T06:39:07Z","timestamp":1692599947000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7783729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/micro.2016.7783729","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}