{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:48:38Z","timestamp":1783007318726,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,13]],"date-time":"2015-06-13T00:00:00Z","timestamp":1434153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF 1337177"],"award-info":[{"award-number":["CCF 1337177"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,13]]},"DOI":"10.1145\/2749469.2750393","type":"proceedings-article","created":{"date-parts":[[2015,5,26]],"date-time":"2015-05-26T10:36:25Z","timestamp":1432636585000},"page":"528-540","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Dynamic thread block launch"],"prefix":"10.1145","author":[{"given":"Jin","family":"Wang","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Norm","family":"Rubin","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert","family":"Sidelnik","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudhakar","family":"Yalamanchili","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,6,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"\"Global flight network.\" {Online}. Available: http:\/\/www.visualizing.org\/datasets\/global-flights-network  \"Global flight network.\" {Online}. Available: http:\/\/www.visualizing.org\/datasets\/global-flights-network"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2008.01.047"},{"key":"e_1_3_2_1_4_1","volume-title":"10th dimacs implementation challenge: Graph partitioning and graph clustering","author":"Bader D. A.","year":"2011","unstructured":"D. A. Bader , H. Meyerhenke , P. Sanders , and D. Wagner , \" 10th dimacs implementation challenge: Graph partitioning and graph clustering , 2011 .\" D. A. Bader, H. Meyerhenke, P. Sanders, and D. Wagner, \"10th dimacs implementation challenge: Graph partitioning and graph clustering, 2011.\""},{"key":"e_1_3_2_1_5_1","first-page":"163","volume-title":"April 2009","author":"Bakhoda A.","unstructured":"A. Bakhoda , G. Yuan , W. Fung , H. Wong , and T. Aamodt , \" Analyzing cuda workloads using a detailed gpu simulator,\" in 2009 IEEE International Symposium on Performance Analysis of Systems and Software(ISPASS 2009) , April 2009 , pp. 163 -- 174 . A. Bakhoda, G. Yuan, W. Fung, H. Wong, and T. Aamodt, \"Analyzing cuda workloads using a detailed gpu simulator,\" in 2009 IEEE International Symposium on Performance Analysis of Systems and Software(ISPASS 2009), April 2009, pp. 163--174."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2398856.2364563"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-384988-5.00006-1"},{"key":"e_1_3_2_1_9_1","first-page":"185","volume-title":"2013 IEEE International Symposium on. IEEE","author":"Che S.","year":"2013","unstructured":"S. Che , B. M. Beckmann , S. K. Reinhardt , and K. Skadron , \" Pannotia: Understanding irregular gpgpu graph applications,\" in Workload Characterization (IISWC) , 2013 IEEE International Symposium on. IEEE , 2013 , pp. 185 -- 195 . S. Che, B. M. Beckmann, S. K. Reinhardt, and K. Skadron, \"Pannotia: Understanding irregular gpgpu graph applications,\" in Workload Characterization (IISWC), 2013 IEEE International Symposium on. IEEE, 2013, pp. 185--195."},{"key":"e_1_3_2_1_10_1","volume-title":"Efficient graph matching and coloring on the gpu,\" in GPU Technology Conference","author":"Cohen J.","year":"2012","unstructured":"J. Cohen and P. Castonguay , \" Efficient graph matching and coloring on the gpu,\" in GPU Technology Conference , 2012 . J. Cohen and P. Castonguay, \"Efficient graph matching and coloring on the gpu,\" in GPU Technology Conference, 2012."},{"key":"e_1_3_2_1_11_1","first-page":"732","article-title":"Thread group scheduler for computing on a parallel thread processor","volume":"8","author":"Coon B. W.","year":"2014","unstructured":"B. W. Coon , J. R. Nickolls , J. E. Lindholm , R. J. Stoll , N. Wang , and J. H. Choquette , \" Thread group scheduler for computing on a parallel thread processor ,\" US Patent 8 , 732 ,713, 2014 . B. W. Coon, J. R. Nickolls, J. E. Lindholm, R. J. Stoll, N. Wang, and J. H. Choquette, \"Thread group scheduler for computing on a parallel thread processor,\" US Patent 8,732,713, 2014.","journal-title":"US Patent"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442555"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.12"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.257"},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"A study of persistent threads style gpu programming for gpgpu workloads,\" in Innovative Parallel Computing (InPar), 2012","author":"Gupta K.","year":"2012","unstructured":"K. Gupta , J. A. Stuart , and J. D. Owens , \" A study of persistent threads style gpu programming for gpgpu workloads,\" in Innovative Parallel Computing (InPar), 2012 . IEEE , 2012 , pp. 1 -- 14 . K. Gupta, J. A. Stuart, and J. D. Owens, \"A study of persistent threads style gpu programming for gpgpu workloads,\" in Innovative Parallel Computing (InPar), 2012. IEEE, 2012, pp. 1--14.","journal-title":"IEEE"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312682"},{"key":"e_1_3_2_1_17_1","unstructured":"Khronos \"The opencl specification version 2.0 \" 2014.  Khronos \"The opencl specification version 2.0 \" 2014."},{"key":"e_1_3_2_1_18_1","volume-title":"USA","author":"Kuhl A.","year":"2010","unstructured":"A. Kuhl , \"Thermodynamic states in explosion fields,\" in 14th International Symposium on Detonation, Coeur d'Alene Resort, ID , USA , 2010 . A. Kuhl, \"Thermodynamic states in explosion fields,\" in 14th International Symposium on Detonation, Coeur d'Alene Resort, ID, USA, 2010."},{"key":"e_1_3_2_1_19_1","volume-title":"Lonestar: A suite of parallel irregular programs,\" in ISPASS '09: IEEE International Symposium on Performance Analysis of Systems and Software","author":"Kulkarni M.","year":"2009","unstructured":"M. Kulkarni , M. Burtscher , C. Cas\u00e7aval , and K. Pingali , \" Lonestar: A suite of parallel irregular programs,\" in ISPASS '09: IEEE International Symposium on Performance Analysis of Systems and Software , 2009 . M. Kulkarni, M. Burtscher, C. Cas\u00e7aval, and K. Pingali, \"Lonestar: A suite of parallel irregular programs,\" in ISPASS '09: IEEE International Symposium on Performance Analysis of Systems and Software, 2009."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.23"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/382912.382923"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815992"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145832"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.2312\/EGVE\/IPT_EGVE2005\/105-111"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2013.6691571"},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA \"Hyperq sample \" 2012.  NVIDIA \"Hyperq sample \" 2012."},{"key":"e_1_3_2_1_27_1","unstructured":"NVIDIA \"Cuda c programming guide version 6.5 \" 2014.  NVIDIA \"Cuda c programming guide version 6.5 \" 2014."},{"key":"e_1_3_2_1_28_1","unstructured":"NVIDIA \"Cuda dynamic parallelism programming guide \" 2014.  NVIDIA \"Cuda dynamic parallelism programming guide \" 2014."},{"key":"e_1_3_2_1_29_1","volume-title":"ISCA '14","author":"Orr M. S.","year":"2014","unstructured":"M. S. Orr , B. M. Beckmann , S. K. Reinhardt , and D. A. Wood , \" Fine-grain task aggregation and coordination on gpus,\" in Proceeding of the 41st Annual International Symposium on Computer Architecuture, ser . ISCA '14 , 2014 . M. S. Orr, B. M. Beckmann, S. K. Reinhardt, and D. A. Wood, \"Fine-grain task aggregation and coordination on gpus,\" in Proceeding of the 41st Annual International Symposium on Computer Architecuture, ser. ISCA '14, 2014."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778803"},{"key":"e_1_3_2_1_31_1","unstructured":"V. Podlozhnyuk \"Black-scholes option pricing \" Nvidia 2007.  V. Podlozhnyuk \"Black-scholes option pricing \" Nvidia 2007."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_33_1","first-page":"1","volume-title":"Workshops and Phd Forum (IPDPSW), 2010 IEEE International Symposium on. IEEE","author":"Solomon S.","year":"2010","unstructured":"S. Solomon and P. Thulasiraman , \" Performance study of mapping irregular computations on gpus,\" in Parallel & Distributed Processing , Workshops and Phd Forum (IPDPSW), 2010 IEEE International Symposium on. IEEE , 2010 , pp. 1 -- 8 . S. Solomon and P. Thulasiraman, \"Performance study of mapping irregular computations on gpus,\" in Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), 2010 IEEE International Symposium on. IEEE, 2010, pp. 1--8."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.45"},{"key":"e_1_3_2_1_35_1","volume-title":"Enabling preemptive multiprogramming on gpus,\" in Proceeding of the 41st Annual International Symposium on Computer Architecuture","author":"Tanasic I.","year":"2014","unstructured":"I. Tanasic , I. Gelado , J. Cabezas , A. Ramirez , N. Navarro , and M. Valero , \" Enabling preemptive multiprogramming on gpus,\" in Proceeding of the 41st Annual International Symposium on Computer Architecuture , 2014 . I. Tanasic, I. Gelado, J. Cabezas, A. Ramirez, N. Navarro, and M. Valero, \"Enabling preemptive multiprogramming on gpus,\" in Proceeding of the 41st Annual International Symposium on Computer Architecuture, 2014."},{"key":"e_1_3_2_1_36_1","volume-title":"October","author":"Wang J.","year":"2014","unstructured":"J. Wang and S. Yalamanchili , \" Characterization and analysis of dynamic parallelism in unstructured gpu applications,\" in 2014 IEEE International Symposium on Workload Characterization , October 2014 . J. Wang and S. Yalamanchili, \"Characterization and analysis of dynamic parallelism in unstructured gpu applications,\" in 2014 IEEE International Symposium on Workload Characterization, October 2014."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IMIS.2011.107"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.19"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961295.1950408"}],"event":{"name":"ISCA '15: The 42nd Annual International Symposium on Computer Architecture","location":"Portland Oregon","acronym":"ISCA '15","sponsor":["IEEE TCCA IEEE Computer Society Technical Committee on Computer Architecture","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 42nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2749469.2750393","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2749469.2750393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:00:40Z","timestamp":1750215640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2749469.2750393"}},"subtitle":["a lightweight execution mechanism to support irregular applications on GPUs"],"short-title":[],"issued":{"date-parts":[[2015,6,13]]},"references-count":40,"alternative-id":["10.1145\/2749469.2750393","10.1145\/2749469"],"URL":"https:\/\/doi.org\/10.1145\/2749469.2750393","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2872887.2750393","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2015,6,13]]},"assertion":[{"value":"2015-06-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}