{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:19:08Z","timestamp":1729671548313,"version":"3.28.0"},"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":17,"title":["Lazy release consistency for GPUs"],"prefix":"10.1109","author":[{"given":"Johnathan","family":"Alsop","sequence":"first","affiliation":[]},{"given":"Marc S.","family":"Orr","sequence":"additional","affiliation":[]},{"given":"Bradford M.","family":"Beckmann","sequence":"additional","affiliation":[]},{"given":"David A.","family":"Wood","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/2830772.2830778"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1145\/2694344.2694391"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/2830772.2830821"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/2694344.2694356"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/2694344.2694350"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/HOTCHIPS.2012.7476485"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/1375581.1375591"},{"doi-asserted-by":"publisher","key":"ref15","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"},{"year":"0","journal-title":"AMD Research","article-title":"AMD's GEM5 APU simulator","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/IISWC.2013.6704684"},{"year":"0","author":"cederman","journal-title":"Dynamic Load-Balancing Using Work Stealing","article-title":"GPU Computing Gems Jade","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/HPCA.2014.6835930"},{"year":"0","article-title":"CUDA C Programming Guide","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1145\/2540708.2540747"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ISCA.1990.134502"},{"year":"2013","journal-title":"HSA Foundation Spring","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","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/HPCA.2013.6522351"},{"year":"2013","author":"munshi","journal-title":"Khronos OpenCL Working Group","article-title":"The OpenCL Specification (Version 2.0)","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/2701618"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1145\/2541940.2541981"},{"year":"0","journal-title":"International Organization for Standardization","article-title":"Working Draft, Standard for Programming Language C++","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/2908080.2908114"},{"doi-asserted-by":"publisher","key":"ref1","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"},{"doi-asserted-by":"publisher","key":"ref22","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"},{"year":"2015","author":"elver","journal-title":"International Conference on Parallel Architectures and Compilation Techniques (PACT)","article-title":"RC3: Consistency directed cache coherence for x86-64 with RC extensions","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/HPCA.2014.6835927"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/2485922.2485940"},{"year":"2014","author":"sung","journal-title":"Proceedings of the 47th International Symposium on Microarchitecture","article-title":"DeNovoND: efficient hardware support for disciplined non-determinism","key":"ref25"}],"event":{"name":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","start":{"date-parts":[[2016,10,15]]},"location":"Taipei, Taiwan","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":"http:\/\/dx.doi.org\/10.1109\/micro.2016.7783729","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}
