{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T18:22:57Z","timestamp":1758824577748,"version":"3.37.3"},"reference-count":12,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#CNS-1513120","#ACI-1450440","#CCF-1565414","#ACI-1664137"],"award-info":[{"award-number":["#CNS-1513120","#ACI-1450440","#CCF-1565414","#ACI-1664137"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Micro"],"published-print":{"date-parts":[[2020,1,1]]},"DOI":"10.1109\/mm.2019.2949986","type":"journal-article","created":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T20:28:09Z","timestamp":1572467289000},"page":"35-43","source":"Crossref","is-referenced-by-count":10,"title":["Communication Profiling and Characterization of Deep-Learning Workloads on Clusters With High-Performance Interconnects"],"prefix":"10.1109","volume":"40","author":[{"given":"Ammar Ahmad","family":"Awan","sequence":"first","affiliation":[]},{"given":"Arpan","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Ching-Hsiang","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[]},{"given":"Dhableswar K.","family":"Panda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146356"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02465-9_32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-CSS-ICESS.2015.45"},{"year":"2016","key":"ref6","article-title":"Benchmarking deep learning operations on different hardware"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2018.8638634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34356-9_28"},{"article-title":"Best practices for scaling deep learning training and inference with Tensorflow on Intel Xeon processor-based HPC infrastructures","year":"2019","author":"bhandare","key":"ref12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00064"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2949986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","year":"2018","author":"sergeev","key":"ref1"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/40\/8959236\/08887216.pdf?arnumber=8887216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:47Z","timestamp":1642003427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8887216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,1]]},"references-count":12,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mm.2019.2949986","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"type":"print","value":"0272-1732"},{"type":"electronic","value":"1937-4143"}],"subject":[],"published":{"date-parts":[[2020,1,1]]}}}