{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:20:39Z","timestamp":1730269239811,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/ipdps47924.2020.00057","type":"proceedings-article","created":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T21:18:30Z","timestamp":1594761510000},"page":"483-493","source":"Crossref","is-referenced-by-count":14,"title":["A Study of Single and Multi-device Synchronization Methods in Nvidia GPUs"],"prefix":"10.1109","author":[{"given":"Lingqi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[]},{"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018755"},{"journal-title":"arXiv preprint arXiv 1804 06324","article-title":"Dissecting the nvidia volta gpu architecture via microbenchmarking","year":"2018","author":"jia","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145820"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44917-2_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"ref15","first-page":"16","article-title":"Better performance at lower occupancy","volume":"10","author":"volkov","year":"2010","journal-title":"Proceedings of the GPU Technology Conference GTC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751232"},{"year":"2019","key":"ref17","article-title":"Nvidia cuda runtime api"},{"journal-title":"Parallel Forall","article-title":"Faster parallel reductions on kepler","year":"2014","author":"luitjens","key":"ref18"},{"year":"2019","key":"ref19","article-title":"Nvidia cuda sample"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3022671.2984032"},{"key":"ref3","first-page":"1","article-title":"Chainer: a next-generation open source framework for deep learning","volume":"5","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS)"},{"journal-title":"Ph D Dissertation","article-title":"Efficient synchronization for gpgpu","year":"2018","author":"liu","key":"ref6"},{"key":"ref5","first-page":"1","article-title":"Inter-block gpu communication via fast barrier synchronization","author":"xiao","year":"2010","journal-title":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"year":"2017","key":"ref7","article-title":"V100 gpu architecture"},{"key":"ref2","first-page":"70","article-title":"Optimizing parallel reduction in cuda","volume":"2","author":"harris","year":"2007","journal-title":"NVIDIA Developer Technology"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"year":"2019","key":"ref1","article-title":"Programming guide"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2012.6266966"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661187"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WSCAD.2018.00013"},{"year":"2019","key":"ref24","article-title":"Cub library"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73699-0_5"},{"journal-title":"Introduction to error analysis the study of uncertainties in physical measurements","year":"1997","author":"taylor","key":"ref25"}],"event":{"name":"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","start":{"date-parts":[[2020,5,18]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2020,5,22]]}},"container-title":["2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9136850\/9139768\/09139854.pdf?arnumber=9139854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:55:18Z","timestamp":1656453318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9139854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ipdps47924.2020.00057","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}