{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T21:22:48Z","timestamp":1786224168784,"version":"build-2736575974"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1109\/hpca.2014.6835937","type":"proceedings-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T18:48:01Z","timestamp":1406573281000},"page":"260-271","source":"Crossref","is-referenced-by-count":141,"title":["Improving GPGPU resource utilization through alternative thread block scheduling"],"prefix":"10.1109","author":[{"given":"Minseok","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seokwoo","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joosik","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Woong","family":"Seo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeongon","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soojung","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","author":"munshi","year":"2011","journal-title":"The OpenCL Specification"},{"key":"17","article-title":"Effect of instruction fetch and memory scheduling on gpu performance","author":"lakshminarayana","year":"2010","journal-title":"Workshop on Language Compiler and Architecture Support for GPGPU"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2013.6618813"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2009.4"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000093"},{"key":"12","first-page":"10","article-title":"Fine-grained resource sharing for concurrent gpgpu kernels","author":"gregg","year":"2012","journal-title":"Proceedings of the 4th USENIX Conference on Hot Topics in Parallelism (HotPar)"},{"key":"21","author":"nickolls","year":"0","journal-title":"The GPU Computing Era"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"22","year":"2011","journal-title":"CUDA C\/C++ SDK CODE Samples"},{"key":"23","year":"2011"},{"key":"24","year":"2012","journal-title":"CUDA C Programming Guide"},{"key":"25","year":"2012","journal-title":"Kepler The Fastest Most Efficient HPC Architecture Ever Built"},{"key":"26","year":"0"},{"key":"27","year":"2013","journal-title":"Profile User's Guide"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451160"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522337"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.57"},{"key":"1","author":"abdalla","year":"2013","journal-title":"Scheduling and Execution of Compute Tasks"},{"key":"30","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"stratton","year":"2012","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.39"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"5","article-title":"Programming CUDA","author":"buck","year":"2007","journal-title":"Supercomputing 2007 Tutorial"},{"key":"31","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1145\/1346281.1346317","article-title":"Feedback-driven threading: Power-efficient and high-performance execution of multi-threaded workloads on cmps","author":"suleman","year":"2008","journal-title":"International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749714"}],"event":{"name":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)","location":"Orlando, FL, USA","start":{"date-parts":[[2014,2,15]]},"end":{"date-parts":[[2014,2,19]]}},"container-title":["2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6823235\/6835920\/06835937.pdf?arnumber=6835937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T17:25:41Z","timestamp":1498152341000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6835937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/hpca.2014.6835937","relation":{},"subject":[],"published":{"date-parts":[[2014,2]]}}}