{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:47:15Z","timestamp":1772164035911,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,2,25]],"date-time":"2012-02-25T00:00:00Z","timestamp":1330128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,2,25]]},"DOI":"10.1145\/2145816.2145820","type":"proceedings-article","created":{"date-parts":[[2012,2,28]],"date-time":"2012-02-28T07:58:45Z","timestamp":1330415925000},"page":"23-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Efficient performance evaluation of memory hierarchy for highly multithreaded graphics processors"],"prefix":"10.1145","author":[{"given":"Sara S.","family":"Baghsorkhi","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaac","family":"Gelado","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthieu","family":"Delahaye","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-mei W.","family":"Hwu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,2,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/clang.llvm.org\/.  http:\/\/clang.llvm.org\/."},{"key":"e_1_3_2_1_2_1","unstructured":"The OpenCL Specification 2009.  The OpenCL Specification 2009."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693470"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_5_1","unstructured":"G. Diamos A. Kerr and M. Kesavan. A dynamic compilation framework for ptx. http:\/\/code.google.com\/p\/gpuocelot.  G. Diamos A. Kerr and M. Kesavan. A dynamic compilation framework for ptx. http:\/\/code.google.com\/p\/gpuocelot."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/225160.225187"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.8699"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_10_1","volume-title":"ZAM","author":"Nagel W.","year":"1996","unstructured":"W. Nagel , A. Arnold , M. Weber , H. Hoppe , and K. Solchenbach . VAMPIR: Visualization and analysis of MPI resources. KFA , ZAM , 1996 . W. Nagel, A. Arnold, M. Weber, H. Hoppe, and K. Solchenbach. VAMPIR: Visualization and analysis of MPI resources. KFA, ZAM, 1996."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.41"},{"key":"e_1_3_2_1_12_1","unstructured":"NVIDIA. CUDA occupancy calculator.  NVIDIA. CUDA occupancy calculator."},{"key":"e_1_3_2_1_13_1","volume-title":"NVIDIA CUDA Programming Guide 4.0","author":"Staff NVIDIA","year":"2011","unstructured":"NVIDIA Staff . NVIDIA CUDA Programming Guide 4.0 , 2011 . NVIDIA Staff. NVIDIA CUDA Programming Guide 4.0, 2011."},{"key":"e_1_3_2_1_14_1","first-page":"17","volume":"44","author":"Pillet V.","year":"1995","unstructured":"V. Pillet , J. Labarta , T. Cortes , and S. Girona . PARAVER: A tool to visualise and analyze parallel code. In Proceedings of WoTUG-18: Transputer and occam Developments , volume 44 , pages 17 -- 31 , 1995 . V. Pillet, J. Labarta, T. Cortes, and S. Girona. PARAVER: A tool to visualise and analyze parallel code. In Proceedings of WoTUG-18: Transputer and occam Developments, volume 44, pages 17--31, 1995.","journal-title":"In Proceedings of WoTUG-18: Transputer and occam Developments"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2008.4510746"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_2_1_18_1","first-page":"342","volume-title":"Readings in computer architecture","author":"Smith B. J.","year":"2000","unstructured":"B. J. Smith . Readings in computer architecture . chapter Architecture and applications of the HEP mulitprocessor computer system, pages 342 -- 349 . Morgan Kaufmann Publishers Inc ., 2000 . B. J. Smith. Readings in computer architecture. chapter Architecture and applications of the HEP mulitprocessor computer system, pages 342--349. Morgan Kaufmann Publishers Inc., 2000."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/509058.509062"},{"key":"e_1_3_2_1_20_1","volume-title":"Probability, random processes, and estimation theory for engineers","author":"Stark H.","year":"1986","unstructured":"H. Stark and J. Woods . Probability, random processes, and estimation theory for engineers . Prentice-Hall, Inc. Upper Saddle River, NJ, USA, 1986 . H. Stark and J. Woods. Probability, random processes, and estimation theory for engineers. Prentice-Hall, Inc. Upper Saddle River, NJ, USA, 1986."},{"key":"e_1_3_2_1_21_1","volume-title":"Multi2Sim: A Simulation Framework to Evaluate Multicore-Multithreaded Processors","author":"Ubal R.","year":"2007","unstructured":"R. Ubal , J. Sahuquillo , S. Petit , and P. L\u00f3pez . Multi2Sim: A Simulation Framework to Evaluate Multicore-Multithreaded Processors . Oct. 2007 . R. Ubal, J. Sahuquillo, S. Petit, and P. L\u00f3pez. Multi2Sim: A Simulation Framework to Evaluate Multicore-Multithreaded Processors. Oct. 2007."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2014698.2014875"}],"event":{"name":"PPoPP '12: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","location":"New Orleans Louisiana USA","acronym":"PPoPP '12","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2145816.2145820","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2145816.2145820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:54:52Z","timestamp":1750226092000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2145816.2145820"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2,25]]},"references-count":22,"alternative-id":["10.1145\/2145816.2145820","10.1145\/2145816"],"URL":"https:\/\/doi.org\/10.1145\/2145816.2145820","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2370036.2145820","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2012,2,25]]},"assertion":[{"value":"2012-02-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}