{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:18:38Z","timestamp":1725754718093},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006235","name":"Lawrence Berkeley National Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006235","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/pmbs51919.2020.00016","type":"proceedings-article","created":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T02:27:50Z","timestamp":1618367270000},"page":"126-137","source":"Crossref","is-referenced-by-count":4,"title":["Performance Trade-offs in GPU Communication: A Study of Host and Device-initiated Approaches"],"prefix":"10.1109","author":[{"given":"Taylor","family":"Groves","sequence":"first","affiliation":[{"name":"Lawrence Berkeley National Lab"}]},{"given":"Ben","family":"Brock","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Yuxin","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California,Davis"}]},{"given":"Khaled Z.","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab"}]},{"given":"Lenny","family":"Oliker","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab"}]},{"given":"Nicholas J.","family":"Wright","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab"}]},{"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab"}]},{"given":"Katherine","family":"Yelick","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab"}]}],"member":"263","reference":[{"journal-title":"OpenSHMEM - Toward a Unified RMA Model","first-page":"1379","year":"2011","author":"poole","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370593"},{"year":"2020","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00037"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"year":"2020","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356157"},{"year":"2020","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374544"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/800133.804339"},{"first-page":"191","article-title":"On the efficacy of gpu-integrated mpi for scientific applications","year":"0","author":"aji","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"journal-title":"NVIDIA GPU Technology Conference","article-title":"S9677 - nvshmem: A partitioned global address space library for nvidia gpu clusters","year":"2019","author":"goswami","key":"ref3"},{"first-page":"133","article-title":"LogGPS: a parallel computational model for synchronization analysis","year":"0","author":"ino","key":"ref6"},{"first-page":"43","article-title":"Characterizing cuda unified memory (um)-aware mpi designs on modern gpu architectures","year":"0","author":"manian","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/263767.263803"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1851476.1851564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639624"},{"year":"2020","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.117"},{"key":"ref1","first-page":"1","article-title":"Logp: Towards a realistic model of parallel computation","author":"culler","year":"1993","journal-title":"Proceedings of the fourth ACM SIGPLAN symposium on Principles and practice of parallel pro-gramming"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.17"},{"article-title":"Gravel: Fine-grain gpu-initiated network messages","year":"0","author":"orr","key":"ref22"},{"article-title":"Gpu triggered networking for intra-kernel communications","year":"0","author":"lebeane","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.51"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2963098"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02966-8"},{"article-title":"Beyond GPU Memory Limits with Unified Memory on Pascal","year":"2017","author":"sakharnykh","key":"ref25"}],"event":{"name":"2020 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","start":{"date-parts":[[2020,11,12]]},"location":"GA, USA","end":{"date-parts":[[2020,11,12]]}},"container-title":["2020 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9307827\/9307835\/09307863.pdf?arnumber=9307863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:52:50Z","timestamp":1656453170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9307863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/pmbs51919.2020.00016","relation":{},"subject":[],"published":{"date-parts":[[2020,11]]}}}