{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T11:48:13Z","timestamp":1763466493251,"version":"3.38.0"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/hipc.2010.5713187","type":"proceedings-article","created":{"date-parts":[[2011,2,16]],"date-time":"2011-02-16T00:26:36Z","timestamp":1297815996000},"page":"1-10","source":"Crossref","is-referenced-by-count":5,"title":["An integer programming framework for optimizing shared memory use on GPUs"],"prefix":"10.1109","author":[{"given":"Wenjing","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gagan","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/190787.190793"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168898"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335468"},{"key":"ref32","article-title":"Fast n-body simulation with cuda","volume":"3","author":"nyland","year":"2007","journal-title":"GPU Gems"},{"journal-title":"Nvidia CUDA Programming Guide Version 3 0","year":"0","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/238721.238734"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161039"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/330249.330250"},{"key":"ref34","first-page":"104","article-title":"Data Parallel Three-Dimensional Cahn-Hilliard Field Equation Simulation on GPUs with CUDA","author":"playne","year":"2009","journal-title":"PDPTA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0096-0551(81)90048-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1151074.1151085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.11"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum Likelihood Estimation from Incomplete Data via the EM Algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society"},{"journal-title":"Optimizing local memory allocation and assignment through a decoupled approach","year":"2009","author":"boubacar","key":"ref13"},{"journal-title":"Cuda supercomputing for the masses Part 5","year":"0","author":"farber","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-024X(199608)26:8<929::AID-SPE40>3.3.CO;2-K"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/177492.177499"},{"key":"ref18","first-page":"430","author":"eladio","year":"2008","journal-title":"Memory locality exploitation strategies for fft on the cuda architecture"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-40889-4_6"},{"year":"0","author":"makhorin","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/71.762818"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542331"},{"journal-title":"StatLib","year":"0","key":"ref3"},{"key":"ref6","first-page":"267","article-title":"Optimal Bitwise Register Allocation Using Integer Linear Programming","author":"barik","year":"2006","journal-title":"LCPC"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2009.5226334"},{"key":"ref5","article-title":"CUDA-lite: Reducing GPU Programming Complexity","author":"baghsorkhi","year":"2008","journal-title":"LCPC 2008"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1145\/177492.177575","article-title":"Improvements to Graph Coloring Register Allocation","volume":"16","author":"preston","year":"1994","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"ref7","first-page":"1","article-title":"Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories","author":"manikandan baskaran","year":"2008","journal-title":"PPoPP'08 Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"},{"journal-title":"Principal Components Analysis","year":"0","key":"ref2"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1145\/989393.989403","article-title":"Register allocation and spilling via graph coloring","volume":"39","author":"chaitin","year":"2004","journal-title":"SIGPLAN Not"},{"year":"0","key":"ref1"},{"key":"ref20","article-title":"Mars: A MapReduce Framework on Graphics Processors","author":"bingsheng","year":"2008","journal-title":"International Conference on Parallel Architectures and Compilation Techniques"},{"year":"0","author":"keng liao","key":"ref22"},{"journal-title":"Algorithms for clustering data","year":"1988","author":"jain","key":"ref21"},{"journal-title":"High Performance Compilers for Parallel Computing","year":"1995","author":"wolfe","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"ref23","first-page":"346","article-title":"Data-centric multi-level blocking","author":"kodukula","year":"1997","journal-title":"Proceedings of the SIGPLAN Conference on Programming Language Design and Implementation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1254766.1254805"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/1504176.1504194","article-title":"OpenMP to GPGPU: A Compiler Framework for Automatic Translation and Optimization","author":"lee","year":"2009","journal-title":"PPoPP'09"}],"event":{"name":"2010 International Conference on High Performance Computing (HiPC)","start":{"date-parts":[[2010,12,19]]},"location":"Goa, India","end":{"date-parts":[[2010,12,22]]}},"container-title":["2010 International Conference on High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5708271\/5713158\/05713187.pdf?arnumber=5713187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T17:08:17Z","timestamp":1740935297000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5713187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/hipc.2010.5713187","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}