{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:28:09Z","timestamp":1763458089173,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CCF-142150,"],"award-info":[{"award-number":["NSF-CCF-142150,"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006502","name":"Defense Sciences Office, DARPA","doi-asserted-by":"publisher","award":["PERFECT"],"award-info":[{"award-number":["PERFECT"]}],"id":[{"id":"10.13039\/100006502","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1145\/2925426.2926253","type":"proceedings-article","created":{"date-parts":[[2016,6,10]],"date-time":"2016-06-10T09:04:07Z","timestamp":1465549447000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Tag-Split Cache for Efficient GPGPU Cache Utilization"],"prefix":"10.1145","author":[{"given":"Lingda","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science, Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ari B.","family":"Hayes","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaiwen Leon","family":"Song","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eddy Z.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rutgers University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD Graphics Cores Next (GCN) Architecture White paper 2012."},{"key":"e_1_3_2_1_2_1","unstructured":"NVIDIA Kepler GK110 white paper. 2012."},{"key":"e_1_3_2_1_3_1","volume-title":"Fermi","author":"CUDA","year":"2009","unstructured":"NVIDIA's next generation CUDA compute architecture: Fermi. 2009."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540742"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/224538.224622"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/520549.822755"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815971"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523721.2523745"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.42"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370862"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389041"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.71.0015"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2209249.2209269"},{"key":"e_1_3_2_1_21_1","volume-title":"Dissecting gpu memory hierarchy through microbenchmarking. arXiv preprint arXiv:1509.02308","author":"Mei X.","year":"2015","unstructured":"X. Mei and X. Chu. Dissecting gpu memory hierarchy through microbenchmarking. arXiv preprint arXiv:1509.02308, 2015."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"e_1_3_2_1_23_1","volume-title":"NVIDIA","author":"IA.","year":"2011","unstructured":"NVIDIA. Whitepaper - nvidia next generation cuda compute architecture: Fermi. NVIDIA, 2011."},{"key":"e_1_3_2_1_24_1","volume-title":"Technical White Paper","author":"Packard H.","year":"2002","unstructured":"H. Packard. Inside the intel\u00ae itanium\u00ae 2 processor. Technical White Paper, 2002."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346202"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250709"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305156"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056031"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/192007.192072"},{"key":"e_1_3_2_1_33_1","volume-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"Stratton J. A.","year":"2012","unstructured":"J. A. Stratton, C. Rodrigues, I.-J. Sung, N. Obeid, L.-W. Chang, N. Anssari, G. D. Liu, and W.-M. W. Hwu. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing, 2012."},{"key":"e_1_3_2_1_34_1","volume-title":"April, 2","author":"Thoziyoor S.","year":"2008","unstructured":"S. Thoziyoor, N. Muralimanohar, J. Ahn, and N. Jouppi. Cacti 5.1. HP Laboratories, April, 2, 2008."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305188"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/2561828.2561929"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000100"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2337159.2337222"}],"event":{"name":"ICS '16: 2016 International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Istanbul Turkey","acronym":"ICS '16"},"container-title":["Proceedings of the 2016 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926253","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926253","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:17:17Z","timestamp":1763457437000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":39,"alternative-id":["10.1145\/2925426.2926253","10.1145\/2925426"],"URL":"https:\/\/doi.org\/10.1145\/2925426.2926253","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]},"assertion":[{"value":"2016-06-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}