{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:14:53Z","timestamp":1750306493092,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,12,5]],"date-time":"2015-12-05T00:00:00Z","timestamp":1449273600000},"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-0905509,CNS-1157377,CCF-1318103,CCF-1524852,CCF-1423108"],"award-info":[{"award-number":["CCF-0905509,CNS-1157377,CCF-1318103,CCF-1524852,CCF-1423108"]}],"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":[[2015,12,5]]},"DOI":"10.1145\/2830772.2830796","type":"proceedings-article","created":{"date-parts":[[2016,1,11]],"date-time":"2016-01-11T13:38:13Z","timestamp":1452519493000},"page":"204-215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Efficient warp execution in presence of divergence with collaborative context collection"],"prefix":"10.1145","author":[{"given":"Farzad","family":"Khorasani","sequence":"first","affiliation":[{"name":"University of California, Riverside, CA"}]},{"given":"Rajiv","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of California, Riverside, CA"}]},{"given":"Laxmi N.","family":"Bhuyan","sequence":"additional","affiliation":[{"name":"University of California, Riverside, CA"}]}],"member":"320","published-online":{"date-parts":[[2015,12,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.12"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815992"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485953"},{"key":"e_1_3_2_1_4_1","first-page":"25","volume-title":"Thread block compaction for efficient simt control flow,\" in HPCA","author":"Fung W.","year":"2011","unstructured":"W. Fung and T. Aamodt , \" Thread block compaction for efficient simt control flow,\" in HPCA , pp. 25 -- 36 , Feb. 2011 . W. Fung and T. Aamodt, \"Thread block compaction for efficient simt control flow,\" in HPCA, pp. 25--36, Feb. 2011."},{"key":"e_1_3_2_1_5_1","first-page":"61","volume-title":"Capri: Prediction of compaction-adequacy for handling control-divergence in gpgpu architectures,\" in ISCA","author":"Rhu M.","year":"2012","unstructured":"M. Rhu and M. Erez , \" Capri: Prediction of compaction-adequacy for handling control-divergence in gpgpu architectures,\" in ISCA , pp. 61 -- 71 , 2012 . M. Rhu and M. Erez, \"Capri: Prediction of compaction-adequacy for handling control-divergence in gpgpu architectures,\" in ISCA, pp. 61--71, 2012."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485954"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964184"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA3.2014.13"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2012.62"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810104"},{"key":"e_1_3_2_1_11_1","first-page":"29","volume-title":"Task management for irregular-parallel workloads on the gpu,\" in Conference on High Performance Graphics","author":"Tzeng S.","year":"2010","unstructured":"S. Tzeng , A. Patney , and J. D. Owens , \" Task management for irregular-parallel workloads on the gpu,\" in Conference on High Performance Graphics , pp. 29 -- 37 , 2010 . S. Tzeng, A. Patney, and J. D. Owens, \"Task management for irregular-parallel workloads on the gpu,\" in Conference on High Performance Graphics, pp. 29--37, 2010."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370879"},{"key":"e_1_3_2_1_13_1","volume-title":"Accelerating large graph algorithms on the gpu using cuda,\" in HiPC","author":"Harish P.","year":"2007","unstructured":"P. Harish and P. J. Narayanan , \" Accelerating large graph algorithms on the gpu using cuda,\" in HiPC , 2007 . P. Harish and P. J. Narayanan, \"Accelerating large graph algorithms on the gpu using cuda,\" in HiPC, 2007."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01737-7","volume-title":"Performance Analysis and Tuning for General Purpose Graphics Processing Units","author":"Kim H.","year":"2012","unstructured":"H. Kim , R. Vuduc , S. Baghsorkhi , J. Choi , and W.-m. Hwu , Performance Analysis and Tuning for General Purpose Graphics Processing Units . Morgan & Claypool Publishers , 1 st ed., 2012 . H. Kim, R. Vuduc, S. Baghsorkhi, J. Choi, and W.-m. Hwu, Performance Analysis and Tuning for General Purpose Graphics Processing Units. Morgan & Claypool Publishers, 1st ed., 2012.","edition":"1"},{"key":"e_1_3_2_1_15_1","volume-title":"Chapter 3 - optimizing parallel prefix operations for the fermi architecture,\" in {GPU} Computing Gems Jade Edition (W.-m","author":"Harris M.","year":"2012","unstructured":"M. Harris and M. Garland , \" Chapter 3 - optimizing parallel prefix operations for the fermi architecture,\" in {GPU} Computing Gems Jade Edition (W.-m . W. Hwu, ed.), 2012 . M. Harris and M. Garland, \"Chapter 3 - optimizing parallel prefix operations for the fermi architecture,\" in {GPU} Computing Gems Jade Edition (W.-m. W. Hwu, ed.), 2012."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572792"},{"key":"e_1_3_2_1_17_1","first-page":"382","volume-title":"The cuda handbook: A comprehensive guide to gpu programming","author":"Wilt N.","year":"2013","unstructured":"N. Wilt , The cuda handbook: A comprehensive guide to gpu programming , pp. 382 -- 383 . Pearson Education , 2013 . N. Wilt, The cuda handbook: A comprehensive guide to gpu programming, pp. 382--383. Pearson Education, 2013."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/B978-0-12-385963-1.00004-6","volume-title":"Chapter 4 - building an efficient hash table on the {GPU},\" in {GPU} Computing Gems Jade Edition (W.-m","author":"Alcantara D. A.","year":"2012","unstructured":"D. A. Alcantara , V. Volkov , S. Sengupta , M. Mitzenmacher , J. D. Owens , and N. Amenta , \" Chapter 4 - building an efficient hash table on the {GPU},\" in {GPU} Computing Gems Jade Edition (W.-m . W. Hwu, ed.), pp. 39 -- 53 , Morgan Kaufmann , 2012 . D. A. Alcantara, V. Volkov, S. Sengupta, M. Mitzenmacher, J. D. Owens, and N. Amenta, \"Chapter 4 - building an efficient hash table on the {GPU},\" in {GPU} Computing Gems Jade Edition (W.-m. W. Hwu, ed.), pp. 39--53, Morgan Kaufmann, 2012."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/B978-0-12-384988-5.00018-8","volume-title":"Chapter 18 - high-performance iterated function systems,\" in {GPU} Computing Gems Emerald Edition (W.-m","author":"Schied C.","year":"2011","unstructured":"C. Schied , J. Hanika , H. Dammertz , and H. Lensch , \" Chapter 18 - high-performance iterated function systems,\" in {GPU} Computing Gems Emerald Edition (W.-m . W. Hwu, ed.), pp. 263 -- 273 , Morgan Kaufmann , 2011 . C. Schied, J. Hanika, H. Dammertz, and H. Lensch, \"Chapter 18 - high-performance iterated function systems,\" in {GPU} Computing Gems Emerald Edition (W.-m. W. Hwu, ed.), pp. 263--273, Morgan Kaufmann, 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150412"},{"key":"e_1_3_2_1_21_1","first-page":"35","volume-title":"Chapter 3 - dynamical quadrature grids: Applications in density functional calculations,\" in {GPU} Computing Gems Emerald Edition (W.-m","author":"Luehr N.","year":"2011","unstructured":"N. Luehr , I. Ufimtsev , and T. Martinez , \" Chapter 3 - dynamical quadrature grids: Applications in density functional calculations,\" in {GPU} Computing Gems Emerald Edition (W.-m . W. Hwu, ed.), pp. 35 -- 42 , 2011 . N. Luehr, I. Ufimtsev, and T. Martinez, \"Chapter 3 - dynamical quadrature grids: Applications in density functional calculations,\" in {GPU} Computing Gems Emerald Edition (W.-m. W. Hwu, ed.), pp. 35--42, 2011."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MAP.2012.6348120"},{"key":"e_1_3_2_1_23_1","volume-title":"Morgan Kaufmann","author":"Giles M.","year":"2012","unstructured":"M. Giles , \" Chapter 10 - approximating the erfinv function,\" in {GPU} Computing Gems Jade Edition (W.-m. W. Hwu , ed.), pp. 109--116 , Morgan Kaufmann , 2012 . M. Giles, \"Chapter 10 - approximating the erfinv function,\" in {GPU} Computing Gems Jade Edition (W.-m. W. Hwu, ed.), pp. 109--116, Morgan Kaufmann, 2012."},{"key":"e_1_3_2_1_24_1","volume-title":"CUDA by Example: An Introduction to General-Purpose GPU Programming","author":"Sanders J.","year":"2010","unstructured":"J. Sanders and E. Kandrot , CUDA by Example: An Introduction to General-Purpose GPU Programming . Addison-Wesley Professional , 1 st ed., 2010 . J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Professional, 1st ed., 2010.","edition":"1"},{"key":"e_1_3_2_1_25_1","first-page":"1355","article-title":"Community structure in large networks: Natural cluster sizes and the absence of large well-defined clusters","volume":"0810","author":"Leskovec J.","year":"2008","unstructured":"J. Leskovec , K. J. Lang , A. Dasgupta , and M. W. Mahoney , \" Community structure in large networks: Natural cluster sizes and the absence of large well-defined clusters ,\" CoRR , vol. abs\/ 0810 . 1355 , 2008 . J. Leskovec, K. J. Lang, A. Dasgupta, and M. W. Mahoney, \"Community structure in large networks: Natural cluster sizes and the absence of large well-defined clusters,\" CoRR, vol. abs\/0810.1355, 2008.","journal-title":"CoRR"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.24"},{"key":"e_1_3_2_1_28_1","first-page":"49","volume-title":"Simultaneous branch and warp interweaving for sustained gpu performance,\" in 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 , pp. 49 -- 60 , 2012 . N. Brunie, S. Collange, and G. Diamos, \"Simultaneous branch and warp interweaving for sustained gpu performance,\" in ISCA, pp. 49--60, 2012."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522352"},{"key":"e_1_3_2_1_30_1","first-page":"248","volume-title":"A scalable multi-path microarchitecture for efficient gpu control flow,\" in HPCA","author":"ElTantawy A.","year":"2014","unstructured":"A. ElTantawy , J. Ma , M. O'Connor , and T. Aamodt , \" A scalable multi-path microarchitecture for efficient gpu control flow,\" in HPCA , pp. 248 -- 259 , Feb 2014 . A. ElTantawy, J. Ma, M. O'Connor, and T. Aamodt, \"A scalable multi-path microarchitecture for efficient gpu control flow,\" in HPCA, pp. 248--259, Feb 2014."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155676"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2479870"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555258"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145832"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458525"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2692916.2555254"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.23"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628101"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2687355"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.63"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523815"},{"key":"e_1_3_2_1_43_1","volume-title":"Profiling divergences in gpu applications,\" Concurrency and Computation: Practice and Experience, 25(6)","author":"Coutinho B.","year":"2013","unstructured":"B. Coutinho , D. Sampaio , F. M. Q. Pereira , and W. Meira , \" Profiling divergences in gpu applications,\" Concurrency and Computation: Practice and Experience, 25(6) , 2013 . B. Coutinho, D. Sampaio, F. M. Q. Pereira, and W. Meira, \"Profiling divergences in gpu applications,\" Concurrency and Computation: Practice and Experience, 25(6), 2013."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723742.2723760"}],"event":{"name":"MICRO-48: The 48th Annual IEEE\/ACM International Symposium of Microarchitecture","sponsor":["IEEE Computer Society TC-uARCH","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"Waikiki Hawaii","acronym":"MICRO-48"},"container-title":["Proceedings of the 48th International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2830772.2830796","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2830772.2830796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:48:40Z","timestamp":1750225720000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2830772.2830796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12,5]]},"references-count":44,"alternative-id":["10.1145\/2830772.2830796","10.1145\/2830772"],"URL":"https:\/\/doi.org\/10.1145\/2830772.2830796","relation":{},"subject":[],"published":{"date-parts":[[2015,12,5]]},"assertion":[{"value":"2015-12-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}