{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:35:04Z","timestamp":1763458504596,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":24,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1337198&1311706"],"award-info":[{"award-number":["1337198&1311706"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472322"],"award-info":[{"award-number":["61472322"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for Central Universities of China","award":["3102014JSJ0001"],"award-info":[{"award-number":["3102014JSJ0001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6,5]]},"DOI":"10.1145\/2897937.2898103","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":8,"title":["TEMP"],"prefix":"10.1145","author":[{"given":"Mengjie","family":"Mao","sequence":"first","affiliation":[{"name":"University of Pittsburgh"}]},{"given":"Wujie","family":"Wen","sequence":"additional","affiliation":[{"name":"University of Pittsburgh"}]},{"given":"Xiaoxiao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Pittsburgh"}]},{"given":"Jingtong","family":"Hu","sequence":"additional","affiliation":[{"name":"Oklahoma State University"}]},{"given":"Danghui","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}]},{"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Pittsburgh"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"University of Pittsburgh"}]}],"member":"320","published-online":{"date-parts":[[2016,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"\"High bandwidth memory (hbm) dram.\" http:\/\/www.jedec.org\/standards-documents\/results\/jesd235\/."},{"key":"e_1_3_2_1_2_1","unstructured":"\"Hynix 1gb (32mx32) gddr5 sgram h5gq1h24afr \" http:\/\/www.hynix.com\/datasheet\/eng\/graphics\/details\/graphics_26_H5GQ1H24AFR.jsp\/."},{"key":"e_1_3_2_1_3_1","unstructured":"\"Micron ddr3 sdram part mt41j256m8.\" http:\/\/www.micron.com\/products\/dram\/ddr3-sdram\/."},{"key":"e_1_3_2_1_4_1","unstructured":"\"Micron system power calculators.\" http:\/\/www.micron.com\/products\/support\/power-calc\/."},{"key":"e_1_3_2_1_5_1","unstructured":"\"Nvidia cuda sdk.\" https:\/\/developer.nvidia.com\/cuda-downloads\/."},{"key":"e_1_3_2_1_6_1","unstructured":"\"Nvidia fermi architecture.\" http:\/\/www.nvidia.com\/object\/fermi-architecture.html\/."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694381"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2337159.2337207"},{"key":"e_1_3_2_1_9_1","first-page":"163","article-title":"Analyzing cuda workloads using a detailed gpu simulator","author":"Bakhoda A.","year":"2009","unstructured":"A. Bakhoda et al., \"Analyzing cuda workloads using a detailed gpu simulator,\" in ISPASS, 2009, pp. 163--174.","journal-title":"ISPASS"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408797"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168944"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370869"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744931"},{"key":"e_1_3_2_1_19_1","first-page":"568","article-title":"Supporting x86-64 address translation for 100s of gpu lanes","author":"Power J.","year":"2014","unstructured":"J. Power, M. Hill, and D. Wood, \"Supporting x86-64 address translation for 100s of gpu lanes,\" in HPCA, 2014, pp. 568--578.","journal-title":"HPCA"},{"key":"e_1_3_2_1_20_1","volume-title":"Amd heterogeneous uniform memory access","author":"Rogers P.","year":"2013","unstructured":"P. Rogers and C. Fellow, \"Amd heterogeneous uniform memory access,\" 2013."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_22_1","volume-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing,\" Center for Reliable and High-Performance Computing","author":"Stratton J. A.","year":"2012","unstructured":"J. A. Stratton et al., \"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_23_1","first-page":"344","article-title":"Improving system throughput and fairness simultaneously in shared memory cmp systems via dynamic bank partitioning","author":"Xie M.","year":"2014","unstructured":"M. Xie et al., \"Improving system throughput and fairness simultaneously in shared memory cmp systems via dynamic bank partitioning,\" in HPCA, 2014, pp. 344--355.","journal-title":"HPCA"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806606"}],"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\/2897937.2898103","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2897937.2898103","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2897937.2898103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:30:30Z","timestamp":1763458230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2897937.2898103"}},"subtitle":["thread batch enabled memory partitioning for GPU"],"short-title":[],"issued":{"date-parts":[[2016,6,5]]},"references-count":24,"alternative-id":["10.1145\/2897937.2898103","10.1145\/2897937"],"URL":"https:\/\/doi.org\/10.1145\/2897937.2898103","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"}}]}}