{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T08:10:23Z","timestamp":1778746223582,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T00:00:00Z","timestamp":1504224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572250"],"award-info":[{"award-number":["61572250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602194"],"award-info":[{"award-number":["61602194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Industry Support Program","award":["BE2014131"],"award-info":[{"award-number":["BE2014131"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,9,1]]},"DOI":"10.1109\/tpds.2017.2686384","type":"journal-article","created":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T00:12:11Z","timestamp":1490227931000},"page":"2539-2552","source":"Crossref","is-referenced-by-count":23,"title":["Improving Execution Concurrency of Large-Scale Matrix Multiplication on Distributed Data-Parallel Platforms"],"prefix":"10.1109","volume":"28","author":[{"given":"Rong","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hucheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanru","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2015.11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2453970"},{"key":"ref33","first-page":"1","article-title":"Spartan: A distributed array framework with\n smart tiling","author":"huang","year":"2015","journal-title":"Proc 2015 Usenix Ann Technical Conf"},{"key":"ref32","article-title":"SparkR (R on Spark)","year":"2016"},{"key":"ref31","article-title":"Rhadoop: A collection of five R packages that allow users to\n manage and analyze data with Hadoop","author":"analytics","year":"2012"},{"key":"ref30","first-page":"599","article-title":"Graphx: Graph processing in a distributed dataflow framework","author":"gonzalez","year":"2014","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168857"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807275"},{"key":"ref34","article-title":"Distarray documents","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767930"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939675"},{"key":"ref11","article-title":"Learning semantic image representations at a large scale","author":"jia","year":"2014"},{"key":"ref12","article-title":"Apache Flink","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749432"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2013.19"},{"key":"ref16","article-title":"The\n MNIST Ddatabaase of handwritten digits","author":"lecun","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2010.17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.80"},{"key":"ref19","article-title":"Automatically Tuned Linear Algebra Software (ATLAS)","year":"2016"},{"key":"ref28","article-title":"Graphlab: A new framework for parallel machine learning","author":"low","year":"2014"},{"key":"ref4","first-page":"1","article-title":"Resilient distributed datasets: A\n fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc 9th USENIX Conf Netw Syst Des Implementation"},{"key":"ref27","first-page":"1","article-title":"Piccolo: Building fast, distributed programs with partitioned tables","author":"power","year":"2010","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref3","article-title":"Apache Spark","year":"2016"},{"key":"ref6","article-title":"Apache Mahout","year":"2016"},{"key":"ref29","first-page":"17","article-title":"Powergraph: Distributed graph-parallel computation on natural\n graphs","author":"gonzalez","year":"2012","journal-title":"Presented as part 10th USENIX Symp Operating Syst Des Implementation"},{"key":"ref5","article-title":"Apache Spark MLlib","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.158"},{"key":"ref7","article-title":"SystemML Documents","year":"2016"},{"key":"ref2","article-title":"Apache Hadoop","year":"2011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465371"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref46","first-page":"193","article-title":"Communication-optimal parallel algorithm for strassen&#x2019;s\n matrix multiplication","author":"ballard","year":"2012","journal-title":"Proc 4th Annu ACM Symp Parallel Algorithms Archit"},{"key":"ref20","article-title":"LAPACK : Linear Algebra PACKage","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.80"},{"key":"ref22","article-title":"Optimizing shuffle performance in spark","author":"davidson","year":"0"},{"key":"ref21","article-title":"Intel Math Kernel Library (Intel MKL)","year":"2016"},{"key":"ref42","first-page":"1","article-title":"Bidmach: Large-scale learning with zero memory allocation","author":"canny","year":"2013","journal-title":"NIPS Workshop BigLearn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FMPC.1992.234898"},{"key":"ref41","article-title":"cuBLAS","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38718-0_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/PL00008264"},{"key":"ref43","first-page":"347","article-title":"Heterospark: A heterogeneous cpu\/gpu spark platform for\n machine learning algorithms","author":"li","year":"2015","journal-title":"Proc IEEE Int Conf Netw Archit Storage"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723712"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8003561\/07884988.pdf?arnumber=7884988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:31Z","timestamp":1641987631000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7884988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,1]]},"references-count":46,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2017.2686384","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2017,9,1]]}}}