{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:50:14Z","timestamp":1782589814600,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,8]],"date-time":"2015-06-08T00:00:00Z","timestamp":1433721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. National Science Foundation","award":["CNS-1320349"],"award-info":[{"award-number":["CNS-1320349"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11372067"],"award-info":[{"award-number":["11372067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,8]]},"DOI":"10.1145\/2751205.2751234","type":"proceedings-article","created":{"date-parts":[[2015,6,2]],"date-time":"2015-06-02T18:40:11Z","timestamp":1433270411000},"page":"15-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["A Stall-Aware Warp Scheduling for Dynamically Optimizing Thread-level Parallelism in GPGPUs"],"prefix":"10.1145","author":[{"given":"Yulong","family":"Yu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University, Richmond, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xubin","family":"He","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University, Richmond, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Guo","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588768.2576780"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458538"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.22"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.95"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628101"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168947"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815992"},{"key":"e_1_3_2_1_14_1","volume-title":"The open standard for parallel programming of heterogeneous systems","author":"Khronos Group","year":"2013","unstructured":"Khronos Group . The open standard for parallel programming of heterogeneous systems , 2013 . Khronos Group. The open standard for parallel programming of heterogeneous systems, 2013."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470413"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000093"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2166879.2166882"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465021"},{"key":"e_1_3_2_1_20_1","first-page":"49","volume-title":"ISCA","author":"Brunie N.","year":"2012","unstructured":"N. Brunie , S. Collange , and G. Diamos . Simultaneous branch and warp interweaving for sustained GPU performance . In ISCA , pages 49 -- 60 , 2012 . N. Brunie, S. Collange, and G. Diamos. Simultaneous branch and warp interweaving for sustained GPU performance. In ISCA, pages 49--60, 2012."},{"key":"e_1_3_2_1_21_1","unstructured":"NVIDIA. CUDA C\/C++SDK code samples 2011.  NVIDIA. CUDA C\/C++SDK code samples 2011."},{"key":"e_1_3_2_1_22_1","volume-title":"CUDA C Programming Guide","author":"NVIDIA.","year":"2012","unstructured":"NVIDIA. CUDA C Programming Guide , 2012 . NVIDIA. CUDA C Programming Guide, 2012."},{"key":"e_1_3_2_1_23_1","first-page":"157","volume-title":"PACT","author":"Kayiran O.","year":"2013","unstructured":"O. Kayiran , A. Jog , M. Kandemir , Neither more nor less: optimizing thread-level parallelism for GPGPUs . In PACT , pages 157 -- 166 , 2013 . O. Kayiran, A. Jog, M. Kandemir, et al. Neither more nor less: optimizing thread-level parallelism for GPGPUs. In PACT, pages 157--166, 2013."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.62"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465022"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628107"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628117"},{"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":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2014698.2014893"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.12"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2479870"},{"issue":"8","key":"e_1_3_2_1_35_1","first-page":"1","article-title":"A credit-based load-balance-aware CTA scheduling optimization scheme","volume":"42","author":"Yu Y.","year":"2014","unstructured":"Y. Yu , X. He , H. Guo , A credit-based load-balance-aware CTA scheduling optimization scheme in GPGPU. International Journal of Parallel Programming , 42 ( 8 ): 1 -- 21 , 2014 . Y. Yu, X. He, H. Guo, et al. A credit-based load-balance-aware CTA scheduling optimization scheme in GPGPU. International Journal of Parallel Programming, 42(8):1--21, 2014.","journal-title":"GPGPU. International Journal of Parallel Programming"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588768.2576789"}],"event":{"name":"ICS'15: 2015 International Conference on Supercomputing","location":"Newport Beach California USA","acronym":"ICS'15","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 29th ACM on International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2751205.2751234","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2751205.2751234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:43:06Z","timestamp":1750225386000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2751205.2751234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,8]]},"references-count":35,"alternative-id":["10.1145\/2751205.2751234","10.1145\/2751205"],"URL":"https:\/\/doi.org\/10.1145\/2751205.2751234","relation":{},"subject":[],"published":{"date-parts":[[2015,6,8]]},"assertion":[{"value":"2015-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}