{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T09:26:41Z","timestamp":1791019601330,"version":"4.1.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1109\/hipc.2009.5433179","type":"proceedings-article","created":{"date-parts":[[2010,3,24]],"date-time":"2010-03-24T14:33:20Z","timestamp":1269441200000},"page":"463-472","source":"Crossref","is-referenced-by-count":64,"title":["A performance prediction model for the CUDA GPGPU platform"],"prefix":"10.1109","author":[{"given":"Kishore","family":"Kothapalli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rishabh","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Suhail","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suryakant","family":"Patidar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P. J.","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kannan","family":"Srinathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"key":"ref11","first-page":"37","article-title":"Designing Practical Efficient Algorithms for Symmetric Multiprocessors","author":"helman","year":"1999","journal-title":"Proc ALENEX"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-6783-0_10"},{"key":"ref14","article-title":"Introduction to Parallel Algorithms","author":"j\u00e1j\u00e1","year":"1992"},{"key":"ref15","first-page":"1","article-title":"Canny Edge Detection on Nvidia CUDA","author":"luo","year":"2008","journal-title":"Proc IEEE Computer Vision and Pattern Recognition"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542313"},{"key":"ref17","article-title":"Gpu Gems 3","author":"nguyen","year":"2007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref19","article-title":"Cuda: Compute Unified Device Architecture Programming Guide","year":"2007","journal-title":"Tech Rep"},{"key":"ref4","first-page":"1","article-title":"LogP: Towards a Realistic Model of Parallel Computation","author":"culler","year":"0","journal-title":"In Proc ACM PPoPP (1993)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2003.1250387"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0890-5401(89)90036-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0024714"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/800133.804339"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2007.09.006"},{"key":"ref7","first-page":"733","article-title":"The Queue-Read Queue-Write PRAM Model: Accounting for Contention in Parallel Algorithms","volume":"2","author":"gibbons","year":"1999","journal-title":"SIAM J Compo 28"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370266"},{"key":"ref9","first-page":"430","article-title":"Memory Locality Exploitation Strategies for FFT on the CUDA Architecture","author":"gutierrez","year":"2008","journal-title":"In Proc of High Perf Compo for Compo Sci"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(90)90196-5"},{"key":"ref20","article-title":"Scalable Split and Gather Primitives for the GPU","author":"patidar","year":"2009","journal-title":"Tech Rep 11-IT\/TR\/2009\/99"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542311"},{"key":"ref24","first-page":"97","article-title":"Scan Primitives for GPU Computing","author":"sengupta","year":"2007","journal-title":"Proc ACM Symp Graph Hardw"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4563095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"}],"event":{"name":"2009 International Conference on High Performance Computing (HiPC)","location":"Kochi, India","start":{"date-parts":[[2009,12,16]]},"end":{"date-parts":[[2009,12,19]]}},"container-title":["2009 International Conference on High Performance Computing (HiPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5426440\/5433175\/05433179.pdf?arnumber=5433179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,18]],"date-time":"2017-03-18T20:50:46Z","timestamp":1489870246000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5433179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/hipc.2009.5433179","relation":{},"subject":[],"published":{"date-parts":[[2009,12]]}}}