{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:33:26Z","timestamp":1772724806288,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/iiswc.2017.8167781","type":"proceedings-article","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T23:28:15Z","timestamp":1512689295000},"page":"239-249","source":"Crossref","is-referenced-by-count":16,"title":["HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs"],"prefix":"10.1109","author":[{"given":"Matthew D.","family":"Sinclair","sequence":"first","affiliation":[]},{"given":"Johnathan","family":"Alsop","sequence":"additional","affiliation":[]},{"given":"Sarita V.","family":"Adve","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1105734.1105747"},{"key":"ref33","author":"sinclair","year":"2017","journal-title":"Efficient Coherence and Consistency for Specialized Memory Hierarchies"},{"key":"ref32","article-title":"NVIDIA","year":"0","journal-title":"CUDA SDK 3 1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908114"},{"key":"ref30","article-title":"Atomic Weapons: The C++ Memory Model and Modern Hardware","author":"sutter","year":"2012","journal-title":"C++ COM and Beyond"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750374"},{"key":"ref36","article-title":"Some Examples of Kernel-Hacker Informal Correctness Reasoning","author":"mckenney","year":"2015","journal-title":"Proceedings of the Dagstuhl Workshop on Compositional Verification Methods for Next-Generation Concurrency"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2247684.2247688"},{"key":"ref34","author":"podlozhnyuk","year":"2007","journal-title":"Histogram calculation in CUDA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541981"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694350"},{"key":"ref15","article-title":"Efficient Synchronization Primitives for GPUs","volume":"abs 1110 4623","author":"stuart","year":"2011","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783729"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2889488"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2701618"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1787234.1787255"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830821"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581262"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835930"},{"key":"ref6","article-title":"GPU concurrency Weak behaviours and programming assumptions","author":"alglave","year":"2015","journal-title":"Proc Int Conf Architectural Support for Programming Languages and Operating Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2837614.2837637"},{"key":"ref7","first-page":"489","article-title":"ICS: U: Towards Shared Memory Consistency Models for GPUs","author":"sorensen","year":"2013","journal-title":"Towards Shared Memory Consistency Models for GPUs"},{"key":"ref2","article-title":"IntelPR","year":"2014","journal-title":"Intel Discloses Newest Microarchitecture and 14 Nanometer Manufacturing Process Technical Details"},{"key":"ref9","year":"2017","journal-title":"SPEC ACCEL"},{"key":"ref1","article-title":"HSA Foundation","year":"2017","journal-title":"HSA Platform System Architecture Specification 1 0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_87"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155655"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2903150.2903155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688501"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540743"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975269"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751232"}],"event":{"name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","location":"Seattle, WA","start":{"date-parts":[[2017,10,1]]},"end":{"date-parts":[[2017,10,3]]}},"container-title":["2017 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8122074\/8167743\/08167781.pdf?arnumber=8167781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T22:46:48Z","timestamp":1516056408000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8167781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iiswc.2017.8167781","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}