{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:49:36Z","timestamp":1755838176217,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T00:00:00Z","timestamp":1275436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-PS02-08ER08-19DEFG02-07ER25826DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-PS02-08ER08-19DEFG02-07ER25826DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,2]]},"DOI":"10.1145\/1810085.1810105","type":"proceedings-article","created":{"date-parts":[[2010,6,8]],"date-time":"2010-06-08T12:37:34Z","timestamp":1276000654000},"page":"127-136","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["An experimental approach to performance measurement of heterogeneous parallel applications using CUDA"],"prefix":"10.1145","author":[{"given":"Allen D.","family":"Malony","sequence":"first","affiliation":[{"name":"University of Oregon, Eugene, OR"}]},{"given":"Scott","family":"Biersdorff","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR"}]},{"given":"Wyatt","family":"Spear","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR"}]},{"given":"Shangkar","family":"Mayanglambam","sequence":"additional","affiliation":[{"name":"Qualcomm Corporation, Santa Clara, CA"}]}],"member":"320","published-online":{"date-parts":[[2010,6,2]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Barcelona Supercomputing Center. Paraver. http:\/\/www.bsc.es\/paraver\/.  Barcelona Supercomputing Center. Paraver . http:\/\/www.bsc.es\/paraver\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45209-6_7"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.49"},{"key":"e_1_3_2_1_4_1","first-page":"777","author":"Brunst H.","year":"2004","journal-title":"Distributed and Parallel Systems, Cluster and Grid Computing"},{"key":"e_1_3_2_1_5_1","unstructured":"CAPS Entreprise. HMPP Workbench. http:\/\/www.caps-entreprise.com\/hmpp\/.  CAPS Entreprise. HMPP Workbench . http:\/\/www.caps-entreprise.com\/hmpp\/."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_7_1","first-page":"1781","volume-title":"Journal of Computational Chemistry","author":"J.","year":"2005"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85451-7_19"},{"key":"e_1_3_2_1_9_1","first-page":"421","volume-title":"Petascale Computing: Algorithms and Applications","author":"Kale L.","year":"2008"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/11758525_71"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"volume-title":"International Conference on Parallel Computing (ParCo)","year":"2009","author":"Mayanglambam S.","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","unstructured":"NVIDIA Corporation. NVIDIA Performance Toolkit da-01800-001v03 edition May 2006.  NVIDIA Corporation. NVIDIA Performance Toolkit da-01800-001v03 edition May 2006."},{"key":"e_1_3_2_1_14_1","unstructured":"NVIDIA Corporation. NVIDIA CUDA Visual Profiler 1.1 edition 2007.  NVIDIA Corporation. NVIDIA CUDA Visual Profiler 1.1 edition 2007."},{"key":"e_1_3_2_1_15_1","unstructured":"NVIDIA Corporation. NVIDIA Nexus 2009. http:\/\/developer.nvidia.com\/nexus\/.  NVIDIA Corporation. NVIDIA Nexus 2009. http:\/\/developer.nvidia.com\/nexus\/."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_2_1_17_1","unstructured":"STMicroelectronics. PGI Accelerator Compilers. http:\/\/www.pgroup.com\/resources\/accel\/.  STMicroelectronics. PGI Accelerator Compilers . http:\/\/www.pgroup.com\/resources\/accel\/."},{"volume-title":"High Performance Networking and Computing (SC00)","year":"2000","author":"Wu C. E.","key":"e_1_3_2_1_18_1"}],"event":{"name":"ICS'10: International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Tsukuba Ibaraki Japan","acronym":"ICS'10"},"container-title":["Proceedings of the 24th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810105","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1810085.1810105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:45:52Z","timestamp":1750250752000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,2]]},"references-count":18,"alternative-id":["10.1145\/1810085.1810105","10.1145\/1810085"],"URL":"https:\/\/doi.org\/10.1145\/1810085.1810105","relation":{},"subject":[],"published":{"date-parts":[[2010,6,2]]},"assertion":[{"value":"2010-06-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}