{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:42:37Z","timestamp":1774942957935,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,4]]},"DOI":"10.1109\/ispass.2009.4919648","type":"proceedings-article","created":{"date-parts":[[2009,5,11]],"date-time":"2009-05-11T14:22:49Z","timestamp":1242051769000},"page":"163-174","source":"Crossref","is-referenced-by-count":1169,"title":["Analyzing CUDA workloads using a detailed GPU simulator"],"prefix":"10.1109","author":[{"given":"Ali","family":"Bakhoda","sequence":"first","affiliation":[]},{"given":"George L.","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Wilson W. L.","family":"Fung","sequence":"additional","affiliation":[]},{"given":"Henry","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Tor M.","family":"Aamodt","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","year":"0"},{"key":"35","year":"0"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/285305.285321"},{"key":"36","year":"0","journal-title":"Open64 The open research compiler"},{"key":"18","year":"0","journal-title":"Parboil benchmark suite"},{"key":"33","year":"0"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"key":"34","year":"2007","journal-title":"Press Release NVIDIA Tesla GPU Computing Processor Ushers In the Era of Personal Supercomputing"},{"key":"16","article-title":"the microarchitecture of the pentium 4 processor","volume":"5","author":"hinton","year":"2001","journal-title":"Intel\ufffd Technology Journal"},{"key":"39","first-page":"128","article-title":"Memory access scheduling","author":"rixner","year":"2000","journal-title":"Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat No RS00201) ISCA"},{"key":"13","author":"giles","year":"0","journal-title":"Notes on using the NVIDIA 8800 GTX graphics card"},{"key":"14","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1145\/384286.264152","article-title":"the design and analysis of a cache architecture for texture mapping","author":"hakura","year":"1997","journal-title":"Proc Int l Symp Computer Architecture"},{"key":"37","year":"0"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"38","year":"0"},{"key":"12","volume":"3 d","author":"giles","year":"0","journal-title":"Jacobi iteration for a Laplace discretisation on a"},{"key":"21","first-page":"81","article-title":"lockup-free instruction fetch\/prefetch cache organization","author":"kroft","year":"1981","journal-title":"Proc Int l Symp Computer Architecture"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183534"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1145\/1058129.1058142"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-474"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"45","first-page":"409","article-title":"scalable cache miss handling for high memory-level parallelism","author":"tuck","year":"2006","journal-title":"Proc 39th IEEE\/ACM Int'l Symp on Microarchitecture"},{"key":"44","year":"2007","journal-title":"OpenSPARCTM T2 Core Microarchitecture Specification"},{"key":"46","author":"warburton","year":"0","journal-title":"Mini Discontinuous Galerkin Solvers"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771788"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPC.2007.4728256"},{"key":"25","year":"0"},{"key":"26","author":"maxime","year":"0","journal-title":"Ray Tracing"},{"key":"27","year":"0"},{"key":"28","article-title":"nvidia's experience with open64","author":"murphy","year":"2008","journal-title":"1st Annual Workshop on Open64"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"3","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/1028176.1006734","article-title":"evaluating the imagine stream architecture","author":"ahn","year":"2004","journal-title":"Proc Int l Symp Computer Architecture"},{"key":"2","year":"2008","journal-title":"Press Release AMD Delivers Enthusiast Performance Leadership with the Introduction of the ATI Radeon HD 3870 X2"},{"key":"10","year":"0"},{"key":"1","year":"2006","journal-title":"ATI CTM guide"},{"key":"30","year":"0"},{"key":"7","article-title":"cell broadband engine interconnect and memory interface","author":"clark","year":"2005","journal-title":"Hot Chips 17"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2000.852632"},{"key":"32","year":"0","journal-title":"NVIDIA CUDA SDK code samples"},{"key":"5","year":"0","journal-title":"Billconan and Kavinguy A Neural Network on GPU"},{"key":"31","year":"0"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/1383422.1383443"},{"key":"9","author":"dally","year":"2004","journal-title":"Interconnection Networks"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050187"}],"event":{"name":"Software (ISPASS)","location":"Boston, MA, USA","start":{"date-parts":[[2009,4,26]]},"end":{"date-parts":[[2009,4,28]]}},"container-title":["2009 IEEE International Symposium on Performance Analysis of Systems and Software"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4907867\/4919623\/04919648.pdf?arnumber=4919648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T15:39:54Z","timestamp":1497800394000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4919648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,4]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ispass.2009.4919648","relation":{},"subject":[],"published":{"date-parts":[[2009,4]]}}}