{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:14:43Z","timestamp":1776122083088,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":["61672526"],"award-info":[{"award-number":["61672526"]}],"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":["61572508"],"award-info":[{"award-number":["61572508"]}],"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":["61872374"],"award-info":[{"award-number":["61872374"]}],"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":["61572025"],"award-info":[{"award-number":["61572025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project of NUDT","award":["ZK17-03-06"],"award-info":[{"award-number":["ZK17-03-06"]}]},{"name":"Science and Technology Innovation project of Hunan Province","award":["2018RS3083"],"award-info":[{"award-number":["2018RS3083"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2019,10,1]]},"DOI":"10.1109\/tpds.2019.2906891","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T22:20:52Z","timestamp":1553552452000},"page":"2148-2164","source":"Crossref","is-referenced-by-count":15,"title":["Coordinated DMA: Improving the DRAM Access Efficiency for Matrix Multiplication"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-4060","authenticated-orcid":false,"given":"Sheng","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenggang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meidi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"34","article-title":"Complexity effective memory access scheduling for many-core accelerator architectures","author":"yuan","year":"2010","journal-title":"Proc 42nd Annu IEEE\/ACM Int Symp Microarchit"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2012.6378661"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835945"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1128022.1128027"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2006.38"},{"key":"ref74","first-page":"684","article-title":"Model-driven level 3 BLAS performance optimization on Loongson 3A processor","author":"zhang","year":"2012","journal-title":"Proc IEEE Int Conf Parallel Distrib Syst"},{"key":"ref39","article-title":"Parallel and scalable sparse basic linear algebra subprograms","author":"liu","year":"2015"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3093172.3093228"},{"key":"ref32","article-title":"Sequoia summary","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155630"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750374"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-014-3501-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263591"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.51"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555758"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2851553.2851575"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2016.25"},{"key":"ref63","article-title":"Intel I350 ethernet controller and DMA coalescing","author":"stabley","year":"2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.51"},{"key":"ref64","article-title":"GPU specs database","year":"2018"},{"key":"ref27","first-page":"1","article-title":"ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers","author":"kim","year":"2010","journal-title":"Proc Int Symp High-Perform Comput Arch"},{"key":"ref65","article-title":"TMS320C6678 multicore fixed and floating-point digital signal processor","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2847255"},{"key":"ref29","article-title":"Roadrunner: Hardware and software overview","author":"komornicki","year":"2009","journal-title":"IBM International Technical Support Org"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/NOCS.2009.5071446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063400"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.386.0673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.51"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2002.1106783"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1147\/rd.494.0589"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.37"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-015-1613-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-013-0916-9"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2086696.2086716"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/DSD.2012.99"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339668"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2006.1598120"},{"key":"ref55","article-title":"Titan user guide","year":"2018"},{"key":"ref54","article-title":"Summit user guide","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.24"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/100788926"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2017.19"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cl.2017.06.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2200\/S00647ED1V01Y201505CAC032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.109"},{"key":"ref17","article-title":"Intel Xeon Phi Coprocessor 5110P product specifications","year":"2018"},{"key":"ref18","article-title":"Intel Xeon Phi Processor 7290 product specifications","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628072"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2013.129"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.1999.744334"},{"key":"ref6","first-page":"314","article-title":"Optimizing the use of static buffers for DMA on a CELL Chip","author":"chen","year":"2006","journal-title":"Proc 19th Int Conf Languages Compilers Parallel Comput"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1965-0178586-1"},{"key":"ref49","first-page":"302","article-title":"Overview of the K computer system","volume":"48","author":"miyazaki","year":"2012","journal-title":"FUJITSU Sci Tech J"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-016-5588-7"},{"key":"ref46","article-title":"4Gb: x4, x8, x16 DDR3 SDRAM Features","year":"2011"},{"key":"ref45","article-title":"Calculating Memory System Power for DDR3","year":"0"},{"key":"ref48","first-page":"1","article-title":"Balancing DRAM locality and parallelism in shared memory CMP systems","author":"min","year":"2012","journal-title":"Proc IEEE Int Symp High-Perform Comput Archit"},{"key":"ref47","article-title":"DDR3 SDRAM Verilog model","year":"0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168953"},{"key":"ref41","article-title":"Achieve 10X DRAM bandwidth improvement with a DDR controller read reorder buffer","author":"greenberg","year":"2013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00018"},{"key":"ref43","first-page":"748","article-title":"Toward scalable matrix multiply on multithreaded architectures","author":"marker","year":"2007","journal-title":"Proc Int Euro-Par Conf Parallel Process"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8830308\/08673652.pdf?arnumber=8673652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:14:23Z","timestamp":1657746863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":76,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2019.2906891","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,1]]}}}