{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T09:01:31Z","timestamp":1768035691566,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["PROMETEO\/2017\/77"],"award-info":[{"award-number":["PROMETEO\/2017\/77"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2018,5,1]]},"DOI":"10.1109\/tpds.2017.2784428","type":"journal-article","created":{"date-parts":[[2017,12,18]],"date-time":"2017-12-18T19:58:20Z","timestamp":1513627100000},"page":"1089-1102","source":"Crossref","is-referenced-by-count":11,"title":["Intra-Node Memory Safe GPU Co-Scheduling"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7871-9152","authenticated-orcid":false,"given":"Carlos","family":"Reano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6435-1200","authenticated-orcid":false,"given":"Federico","family":"Silla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-8307","authenticated-orcid":false,"given":"Dimitrios S.","family":"Nikolopoulos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8392-832X","authenticated-orcid":false,"given":"Blesson","family":"Varghese","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/978-1-4615-0509-9_13","article-title":"PBS Pro:\n Grid computing and scheduling attributes","author":"nitzberg","year":"2004","journal-title":"Grid Resource Management"},{"key":"ref31","author":"bradley","year":"2013","journal-title":"Hyper-Q example"},{"key":"ref30","year":"2015","journal-title":"CUDA Multi-Process Service"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872368"},{"key":"ref34","year":"2016","journal-title":"Tesla P100"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.50"},{"key":"ref11","first-page":"1","article-title":"Towards multi-tenant GPGPU: Event-driven\n programming model for system-wide scheduling on shared GPUs","author":"suzuki","year":"2016","journal-title":"Proc Workshop Multicore Rack-Scale Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2013.12"},{"key":"ref13","first-page":"17","article-title":"TimeGraph: GPU scheduling for\n real-time multi-tasking environments","author":"kato","year":"2011","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref14","first-page":"535","article-title":"Improving application concurrency on GPUs by managing implicit and explicit synchronisations","author":"butler","year":"2015","journal-title":"Proc 21st IEEE Int Conf Parallel Distrib Syst"},{"key":"ref15","article-title":"Improving GPU utilisation with multi-process service (MPS)","author":"sah","year":"2015","journal-title":"Proc GPU Technology Conf"},{"key":"ref16","first-page":"1","article-title":"Multi-threaded Kernel offloading to GPGPU using hyper-Q on Kepler architecture","author":"wende","year":"2014","journal-title":"Proc Zuse Inst Berlin Rep"},{"key":"ref17","year":"2016","journal-title":"CUDA C Programming Guide 8 0"},{"key":"ref18","author":"howes","year":"2015","journal-title":"The OpenCL Specification 1 2"},{"key":"ref19","first-page":"993","article-title":"schedGPU: Fine-grain dynamic and adaptive scheduling for GPUs","author":"rea\u00f1o","year":"2016","journal-title":"Proc Int Conf High Perform Comput Simul"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2011.5999803"},{"key":"ref4","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq644"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/10968987_3","article-title":"SLURM:\n Simple Linux utility for resource management","author":"yoo","year":"2003","journal-title":"Proc Int Workshop Job Scheduling Strategies Parallel Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2636342"},{"key":"ref29","first-page":"10","article-title":"Fine-grained resource sharing for\n concurrent GPGPU kernels","author":"gregg","year":"2012","journal-title":"Proc 1st Usenix Workshop Hot Topics in Parallelism"},{"key":"ref5","first-page":"1","article-title":"QP: A heterogeneous multi-accelerator cluster","author":"showerman","year":"2009","journal-title":"Proc 10th LCI Int Conf High-Perform Clustered Comput"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2012.78"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2015.15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2013.0319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.90"},{"key":"ref1","first-page":"47","article-title":"GPU cluster for high performance computing","author":"fan","year":"2004","journal-title":"Proc IEEE\/ACM Supercomp"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0164-1212(02)00134-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/107972.107985"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/169627.169848"},{"key":"ref24","article-title":"Parboil: A revised benchmark suite for\n scientific and commercial throughput computing","author":"stratton","year":"2012","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2009.05.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SC.Companion.2012.142"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8334163\/08219713.pdf?arnumber=8219713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:24:16Z","timestamp":1643185456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8219713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,1]]},"references-count":35,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2017.2784428","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":[[2018,5,1]]}}}