{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:00:06Z","timestamp":1740132006127,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T00:00:00Z","timestamp":1443657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61300005"],"award-info":[{"award-number":["61300005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CFAR, one of six centers of STARnet, a Semiconductor Research Corporation program sponsored by MARCO and DARPA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1109\/tcad.2015.2424962","type":"journal-article","created":{"date-parts":[[2015,4,21]],"date-time":"2015-04-21T18:43:25Z","timestamp":1429641805000},"page":"1677-1690","source":"Crossref","is-referenced-by-count":16,"title":["An Efficient Compiler Framework for Cache Bypassing on GPUs"],"prefix":"10.1109","volume":"34","author":[{"given":"Yun","family":"Liang","sequence":"first","affiliation":[]},{"given":"Xiaolong","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Guangyu","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Deming","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"134","article-title":"Compiler managed micro-cache bypassing for high performance EPIC processors","author":"wu","year":"2002","journal-title":"Proc 35th Ann Int Symp Microarch (MICRO)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771793"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"journal-title":"Fermi GPUs","year":"0","key":"ref10"},{"journal-title":"Kepler GPUs","year":"0","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"journal-title":"Introduction to Algorithms","year":"2001","author":"cormen","key":"ref13"},{"journal-title":"Occupancy Calculator","year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","year":"2012","author":"stratton","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"journal-title":"NVIDIA Gpu Computing Sdk","year":"0","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"ref4","first-page":"73","article-title":"Optimization principles and application performance evaluation of a multithreaded GPU using CUDA","author":"ryoo","year":"2008","journal-title":"Proc Symp Principles Program Lang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155671"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2024724.2024754"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"ref2","first-page":"832","article-title":"Real-time implementation and performance optimization of 3D sound localization on GPUs","author":"liang","year":"2012","journal-title":"Proc Design Autom Test Eur Conf Exhibition (DATE)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691165"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2013.279"},{"year":"0","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref24","first-page":"461","article-title":"Register and thread structure optimization for GPUs","author":"liang","year":"2013","journal-title":"Proc Asia South Pacific Design Autom Conf (ASP-DAC)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2593069.2593208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.18"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/7271134\/07090987.pdf?arnumber=7090987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:02:37Z","timestamp":1642003357000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7090987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10]]},"references-count":32,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2015.2424962","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2015,10]]}}}