{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:34:54Z","timestamp":1763458494937,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,5]],"date-time":"2017-06-05T00:00:00Z","timestamp":1496620800000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100004311","name":"Advanced Micro Devices","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004311","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1216569"],"award-info":[{"award-number":["1216569"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6,5]]},"DOI":"10.1145\/2897937.2897966","type":"proceedings-article","created":{"date-parts":[[2016,5,25]],"date-time":"2016-05-25T16:14:10Z","timestamp":1464192850000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["A model-driven approach to warp\/thread-block level GPU cache bypassing"],"prefix":"10.1145","author":[{"given":"Hongwen","family":"Dai","sequence":"first","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saurabh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab, Oak Ridge, TN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christos","family":"Kartsaklis","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab, Oak Ridge, TN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Mantor","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Orlando, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD GCN Architecture White paper 2012."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"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\/TC.1976.5009230"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.43"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000075"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263599"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of InPar","author":"S.","year":"2012","unstructured":"S. Grauer-Gray et al. Auto-tuning a high-level language targeted to GPU codes. In Proceedings of InPar, 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2009.4"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1128022.1128064"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.59"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523721.2523745"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2004.10015"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807606"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844487"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056024"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_24_1","unstructured":"NVIDIA Kepler GK110 white paper. 2012."},{"key":"e_1_3_2_1_25_1","unstructured":"NVIDIA \"CUDA C\/C++ SDK code samples \" 2011."},{"key":"e_1_3_2_1_26_1","volume-title":"Fermi","author":"CUDA","year":"2009","unstructured":"NVIDIA's CUDA compute architecture: Fermi. 2009."},{"key":"e_1_3_2_1_27_1","unstructured":"NVIDIA Parallel Thread Execution ISA Version 4.2."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.49"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716283"},{"issue":"5","key":"e_1_3_2_1_32_1","volume":"31","author":"Wilton S.","year":"1996","unstructured":"S. Wilton et al. \"CACTI: An enhanced cache access and cycle time model.\" Solid-State Circuits, IEEE Journal of 31, no. 5 (1996).","journal-title":"IEEE Journal of"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/2014698.2014875"}],"event":{"name":"DAC '16: The 53rd Annual Design Automation Conference 2016","acronym":"DAC '16","location":"Austin Texas"},"container-title":["Proceedings of the 53rd Annual Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2897937.2897966","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2897937.2897966","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2897937.2897966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:30:20Z","timestamp":1763458220000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2897937.2897966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,5]]},"references-count":34,"alternative-id":["10.1145\/2897937.2897966","10.1145\/2897937"],"URL":"https:\/\/doi.org\/10.1145\/2897937.2897966","relation":{},"subject":[],"published":{"date-parts":[[2016,6,5]]},"assertion":[{"value":"2016-06-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}