{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:04:21Z","timestamp":1787324661625,"version":"build-2736575974"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":["11875221"],"award-info":[{"award-number":["11875221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,6,1]]},"DOI":"10.1109\/tpds.2021.3115630","type":"journal-article","created":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T20:30:50Z","timestamp":1632774650000},"page":"1451-1463","source":"Crossref","is-referenced-by-count":31,"title":["A Survey of GPU Multitasking Methods Supported by Hardware Architecture"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6044-4752","authenticated-orcid":false,"given":"Chen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0007-0968","authenticated-orcid":false,"given":"Wu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0871-6519","authenticated-orcid":false,"given":"Feiping","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2133-0722","authenticated-orcid":false,"given":"Huiyang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.44"},{"key":"ref38","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"stratton","year":"2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2018.00027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2014.2299539"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"ref34","year":"2019","journal-title":"CUDA Samples Reference Manual"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1145\/2370816.2370865","article-title":"Multi2Sim: A Simulation Framework for CPU-GPU Computing","author":"rafael ubal","year":"2012","journal-title":"In International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref20","article-title":"Multi-Process Service","year":"2020"},{"key":"ref22","article-title":"Whitepaper: NVIDIA Tesla P100","year":"2016"},{"key":"ref21","article-title":"Whitepaper: NVIDIA GeForce GTX 980","year":"2014"},{"key":"ref24","article-title":"NVIDIA A100 Tensor Core GPU Architecture","year":"2020"},{"key":"ref23","article-title":"NVIDIA Turing GPU Architecture","year":"2018"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056024"},{"key":"ref26","article-title":"Whitepaper: Introducing RDNA Architecture","year":"2019"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref25","article-title":"Whitepaper: Dissecting the Polaris Architecture","year":"2016"},{"key":"ref50","first-page":"192","article-title":"Algorithms for preemptive co-scheduling of kernels on GPUs","author":"eyraud-dubois and","year":"2020","journal-title":"Proc IEEE 27th Int Conf High Perform Comput Data Analytics"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2366231.2337168"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3064352"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783718"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2883906"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465929"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2017.7858307"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.76"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"ref40","first-page":"164","article-title":"Balancing thoughput and fairness in SMT processors","author":"luo","year":"2001","journal-title":"Proc IEEE Int Symp Perform Anal Syst Softw"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001161"},{"key":"ref3","first-page":"1","article-title":"ECML: Improving efficiency of machine learning in edge clouds","author":"dhakal","year":"2020","journal-title":"Proc IEEE 9th Int Conf Cloud Netw"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3070710"},{"key":"ref5","article-title":"NVIDIA","year":"2014","journal-title":"NVIDIA's Next Generation CUDA Compute Architecture Kepler GK110"},{"key":"ref8","first-page":"562","article-title":"A power-aware symbiotic scheduling algorithm for concurrent GPU kernels","author":"li","year":"2015","journal-title":"Proc IEEE 21st Int Conf Parallel Distrib Syst"},{"key":"ref49","first-page":"121","article-title":"CTXBack: Enabling low latency GPU context switching via context flashback","author":"ji","year":"2021","journal-title":"Proc IEEE Int Parallel Distrib Process Symp"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2597917.2597925"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4409"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2988251"},{"key":"ref45","first-page":"1","article-title":"GPU-EvR: Run-time event based real-time scheduling framework on GPGPU platform","author":"lee","year":"2014","journal-title":"Proc Des Autom Test Eur Conf Exhib"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037742"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366180"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2011.13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2015.7108420"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ECRTS.2012.15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00041"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2854764"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00074"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.03.009"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2018.2889042"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2018.2851207"},{"key":"ref77","first-page":"1","article-title":"Dynamic optimizations in GPU using roofline model","author":"thomas","year":"2021","journal-title":"Proc IEEE Int Symp Circuits Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3014163"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205311"},{"key":"ref78","first-page":"87","article-title":"Designing GPU architecture for memory bandwidth reservation","author":"marangoz","year":"2021","journal-title":"Proc IEEE Int Symp Perform Anal Syst Softw"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00070"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2019.00011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3047638"},{"key":"ref63","first-page":"1","article-title":"Application-aware memory system for fair and efficient execution of concurrent GPGPU applications","author":"jog","year":"2014","journal-title":"Proc Workshop Gen Purpose Process Using GPUs"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2014.6974717"},{"key":"ref65","first-page":"1","article-title":"Process variation-aware workload partitioning algorithms for GPUs supporting spatial-multitasking","author":"aguilera","year":"2014","journal-title":"Proc Des Autom Test Eur Conf Exhib"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2014.6742976"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.14"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2016.94"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.19"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/379539.379547"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2791442"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155637"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.07.038"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.24"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3295690"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.148"},{"key":"ref105","first-page":"473","article-title":"Accel-Sim: An extensible simulation framework for validated GPU modeling","author":"khairy","year":"2020","journal-title":"Proc ACM\/IEEE 47th Annu Int Symp Comput Architecture"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218711"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.840816"},{"key":"ref102","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2017.7939084"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.37"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2011.5762740"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2016.0122"},{"key":"ref96","first-page":"46","article-title":"Dynamic detection of uniform and affine vectors in GPGPU computations","author":"collange","year":"2009","journal-title":"Proc Int Conf Parallel Process"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2844210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00035"},{"key":"ref12","article-title":"Whitepaper: NVIDIA Tesla V100 GPU Architecture","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3377138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2944602"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451160"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2477405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2015.7054182"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.257"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037707"},{"key":"ref18","article-title":"CUDA C++ Programming Guide","year":"2021"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446078"},{"key":"ref19","article-title":"Whitepaper: NVIDIA's Next Generation CUDA Compute Architecture: Fermi","year":"2009"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657093"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.05.023"},{"key":"ref85","first-page":"9","article-title":"Exploring cache bypassing and partitioning for multitasking on GPUs","author":"liang","year":"2017","journal-title":"Proc IEEE\/ACM Int Conf Comput Aided Des"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080203"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00027"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3326124"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9591458\/09548839.pdf?arnumber=9548839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T17:55:51Z","timestamp":1649440551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9548839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,1]]},"references-count":111,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3115630","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":[[2022,6,1]]}}}