{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:42:44Z","timestamp":1755801764624,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/mlhpc49564.2019.00006","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:01:43Z","timestamp":1578603703000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Understanding Scalability and Fine-Grain Parallelism of Synchronous Data Parallel Training"],"prefix":"10.1109","author":[{"given":"Jiali","family":"Li","sequence":"first","affiliation":[{"name":"University of Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Nicolae","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Wozniak","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[{"name":"University of Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"journal-title":"TORCH A Scientific Computing Framework for Luajit","year":"0","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref13","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Microsoft Corporation Tech Rep MSR-TR-2014-112"},{"journal-title":"Machine learning toolkit for extreme scale (matex)","year":"0","key":"ref14"},{"journal-title":"Distributed deep learning on hadoop and spark clusters","year":"0","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"journal-title":"Keras","year":"2015","author":"chollet","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337905"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00099"},{"journal-title":"Horovod repository","year":"0","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref3","first-page":"258","author":"bruha","year":"2001","journal-title":"Pre- and Post-processing in Machine Learning and Data Mining"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","first-page":"1","article-title":"To-wards portable online prediction of network utilization using mpi-level monitoring","author":"tseng","year":"2019","journal-title":"EuroPar'19 25th International European Conference on Parallel and Distributed Systems"},{"key":"ref8","first-page":"3049","article-title":"Asynchronous decentralized parallel stochastic gradient descent","author":"lian","year":"0","journal-title":"ICML'18 The 35th International Conference on Machine Learning"},{"key":"ref7","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"NIPS'14 Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/RTEICT.2016.7808140"},{"journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems","year":"0","author":"abadi","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp.2018.00136"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00064"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2508-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337902"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Candle benchmarks","year":"0","key":"ref25"}],"event":{"name":"2019 IEEE\/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC)","start":{"date-parts":[[2019,11,18]]},"location":"Denver, CO, USA","end":{"date-parts":[[2019,11,18]]}},"container-title":["2019 IEEE\/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8945041\/8950671\/08950683.pdf?arnumber=8950683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:34:13Z","timestamp":1755714853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8950683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/mlhpc49564.2019.00006","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}