{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T09:58:32Z","timestamp":1740131912852,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772541","61872376"],"award-info":[{"award-number":["61772541","61872376"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2022,11,1]]},"DOI":"10.1109\/tc.2022.3145164","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T22:17:30Z","timestamp":1643667450000},"page":"3032-3046","source":"Crossref","is-referenced-by-count":1,"title":["ParaX : Bandwidth-Efficient Instance Assignment for DL on Multi-NUMA Many-Core CPUs"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-8485","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"first","affiliation":[{"name":"NICEX Lab, School of Informatics, Xiamen University, Xiamen, Fujian, China"}]},{"given":"Lujia","family":"Yin","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}]},{"given":"Yuxing","family":"Peng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}]},{"given":"Kai","family":"Lu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, Hunan, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Des. Implementation","author":"Abadi"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/2647868.2654889"},{"year":"2015","author":"Chen","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/HPCA.2018.00059"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/HPCA47549.2020.00047"},{"year":"2019","author":"Georganas","article-title":"High-performance deep learning via a single building block","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.5555\/2685048.2685095"},{"year":"2018","author":"Sergeev","article-title":"Horovod: Fast and easy distributed deep learning in tensorflow","key":"ref11"},{"year":"2017","author":"Howard","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","key":"ref12"},{"year":"2015","author":"Ioffe","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1002\/cpe.5547"},{"year":"2016","author":"Keskar","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","key":"ref15"},{"year":"2017","author":"Goyal","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/3225058.3225069"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2018.00647"},{"year":"2014","author":"Krizhevsky","article-title":"One weird trick for parallelizing convolutional neural networks","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1162\/neco.1997.9.8.1735"},{"year":"2016","author":"Wu","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/3038912.3052569"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","first-page":"1","article-title":"SLIDE : In defense of smart algorithms over hardware acceleration for large-scale deep learning systems","volume-title":"Proc. Conf. Mach. Learn. Syst.","author":"Chen"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref28","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Des. Implementation","author":"Chen"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-030-38961-1_4"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.3115\/v1\/W14-3309"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/3037697.3037700"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1145\/2872362.2872368"},{"key":"ref34","first-page":"5","article-title":"Accelerating large scale deep learning inference through deepcpu at microsoft","volume-title":"Proc. USENIX Conf. Oper. Mach. Learn.","author":"Zhang"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.14778\/2732977.2733001"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/CAHPC.2018.8645860"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/MCSoC.2019.00022"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/IPDPS.2019.00113"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/EMPDP.2019.8671552"},{"key":"ref40","article-title":"Ternary weight networks","author":"Li","year":"2016","journal-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop Efficient Methods Deep Neural Networks"},{"key":"ref41","first-page":"107","article-title":"Scalability-based manycore partitioning","volume-title":"Proc. Int. Conf. Parallel Archit. Compilation Techn.","author":"Sasaki"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1145\/2254064.2254082"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1145\/2594291.2594292"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1145\/3243176.3243199"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.14778\/3447689.3447692"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/9913765\/09697417.pdf?arnumber=9697417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:57:06Z","timestamp":1705535826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9697417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,1]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tc.2022.3145164","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"type":"print","value":"0018-9340"},{"type":"electronic","value":"1557-9956"},{"type":"electronic","value":"2326-3814"}],"subject":[],"published":{"date-parts":[[2022,11,1]]}}}