{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T00:58:16Z","timestamp":1725670696240},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1109\/nas.2017.8026851","type":"proceedings-article","created":{"date-parts":[[2017,9,7]],"date-time":"2017-09-07T16:34:32Z","timestamp":1504802072000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["DD-L1D: Improving the Decoupled L1D Efficiency for GPU Architecture"],"prefix":"10.1109","author":[{"given":"Weiguang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Kan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.44"},{"key":"ref32","first-page":"157","article-title":"Neither more nor less: Optimizing thread-level parallelism for gpgpus","author":"kayran","year":"2013","journal-title":"In Proc of PACT-13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0318-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2007.4336215"},{"key":"ref34","first-page":"81","article-title":"Bypass and insertion algorithms for exclusive last-level caches","author":"gaur","year":"2011","journal-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA) ISCA"},{"journal-title":"Gpgpu-sim manual University of British Columbia","year":"2012","author":"aamodt","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"journal-title":"CUDA C\/C++ SDK CODE Samples","year":"2011","key":"ref12"},{"journal-title":"IMPACT-12-01","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","year":"2012","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"journal-title":"NVIDIA-kepler-GK110-Architecture-Whitepaper pdf","article-title":"Nvidia's next generation cudatm compute architecture: kepler tm gk110","year":"2012","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250709"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691165"},{"journal-title":"Nvidia's next generation cuda compute architecture fermi NVIDIA_Fermi_Compute_Architecture_Whitepaper pdf","year":"2009","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/jlpea6020005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.43"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807606"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540742"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"}],"event":{"name":"2017 International Conference on Networking, Architecture, and Storage (NAS)","start":{"date-parts":[[2017,8,7]]},"location":"Shenzhen, China","end":{"date-parts":[[2017,8,9]]}},"container-title":["2017 International Conference on Networking, Architecture, and Storage (NAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8026516\/8026626\/08026851.pdf?arnumber=8026851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,2]],"date-time":"2017-10-02T23:28:38Z","timestamp":1506986918000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8026851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/nas.2017.8026851","relation":{},"subject":[],"published":{"date-parts":[[2017,8]]}}}