{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:22:55Z","timestamp":1774120975695,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/hpcc\/smartcity\/dss.2019.00101","type":"proceedings-article","created":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T01:12:28Z","timestamp":1570151548000},"page":"670-677","source":"Crossref","is-referenced-by-count":11,"title":["Auto-Tuning MPI Collective Operations on Large-Scale Parallel Systems"],"prefix":"10.1109","author":[{"given":"Wenxu","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Juan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feihao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaole","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2677036"},{"key":"ref38","article-title":"Multi-core aware optimization for mpi collectives","author":"tu","year":"2008","journal-title":"IEEE Cluster"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3281411.3281422"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057087"},{"key":"ref31","author":"rabenseifner","year":"1997","journal-title":"A new optimized MPI reduce algorithm"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-007-0012-0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542496"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3211332.3211336"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3078633.3081040"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6495010"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54807-9_9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.288"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.46"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1944862.1944881"},{"key":"ref15","article-title":"Opencl task partitioning in the presence of gpu contention","author":"grewe","year":"2013","journal-title":"LCPC &#x2019;13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494993"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2015.03.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1779-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2016.44"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03770-2_26"},{"key":"ref4","year":"2019","journal-title":"MVAPICH Ohio State University Micro benchmark"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-014-3500-9"},{"key":"ref3","year":"2019","journal-title":"MPICH-A Portable Implementation of MPI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87475-1_30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ClusterW.2012.15"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/71.642949"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00033"},{"key":"ref7","article-title":"Optimizing sparse matrix&#x2013;vector multiplications on an armv8-based many-core architecture","author":"chen","year":"2018","journal-title":"International Journal of Parallel Programming"},{"key":"ref2","year":"2019","journal-title":"MPI Forum"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.24"},{"key":"ref1","year":"2019","journal-title":"Integrated Performance Monitoring"},{"key":"ref46","article-title":"Tianhe-1a interconnect and message-passing services","author":"xie","year":"2012","journal-title":"IEEE Micro"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213166"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2512436"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2768413"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00061"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1145\/966049.781514","article-title":"Cc&#x2013;mpi: a compiled communication capable mpi prototype for ethernet switched clusters","author":"karwande","year":"2003","journal-title":"ACM SIGPLAN Notices"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135984"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2579561"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-015-1520-7"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1145\/1854273.1854313","article-title":"Partitioning streaming parallelism for multi-cores: A machine learning based approach","author":"wang","year":"2010","journal-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2017.7863744"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1594835.1504189"},{"key":"ref25","article-title":"Fast automatic heuristic construction using active learning","author":"ogilvie","year":"2014","journal-title":"LCPC &#x2019;14"}],"event":{"name":"2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS)","location":"Zhangjiajie, China","start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,12]]}},"container-title":["2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8831117\/8855328\/08855601.pdf?arnumber=8855601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T22:34:20Z","timestamp":1664577260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8855601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/hpcc\/smartcity\/dss.2019.00101","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}