{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:16:31Z","timestamp":1767626191091,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1109\/ipdps.2010.5470421","type":"proceedings-article","created":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T20:25:07Z","timestamp":1275510307000},"page":"1-12","source":"Crossref","is-referenced-by-count":124,"title":["An auto-tuning framework for parallel multicore stencil computations"],"prefix":"10.1109","author":[{"given":"Shoaib","family":"Kamil","sequence":"first","affiliation":[]},{"given":"Cy","family":"Chan","sequence":"additional","affiliation":[]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[]},{"given":"John","family":"Shalf","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"A case for machine learning to optimize multicore performance","author":"ganapathi","year":"2009","journal-title":"Workshop on Hot Topics in Parallelism"},{"journal-title":"GreenFlash","year":"0","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1995)123<1862:NIOTSW>2.0.CO;2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/12.40842"},{"key":"ref14","article-title":"A generalized framework for auto-tuning stencil computations","author":"kamil","year":"2009","journal-title":"Cray User Group"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1178597.1178605"},{"journal-title":"Lapack&#x2014 Linear Algebra Package","year":"0","key":"ref16"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1145\/379539.379586","article-title":"Blocking and array contraction across arbitrarily nested loops using affine partitioning","author":"lim","year":"2001","journal-title":"ACM Symposium on Principles and Practice of Parallel Programming"},{"journal-title":"LLVM Homepage","year":"0","key":"ref18"},{"key":"ref19","first-page":"141","author":"mitra","year":"2000","journal-title":"ParA-gent A Domain-Specific Semi-automatic Parallelization Tool"},{"journal-title":"Auto-tuning Stencil Codes for Cache-based Multicore Platforms","year":"2009","author":"datta","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"journal-title":"Embeddable Common Lisp","year":"0","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1137\/070693199","article-title":"Optimization and performance modeling of stencil computations on modern microprocessors","volume":"51","author":"datta","year":"2009","journal-title":"SIAM Review"},{"journal-title":"OpenMP API Specification for Parallel Programming","year":"0","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1379022.1375595"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2004.1342537"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/301631.301661"},{"key":"ref1","article-title":"The landscape of parallel computing research: A view from Berkeley","author":"asanovic","year":"2006","journal-title":"Technical Report UCB\/EECS-2006&#x2013;183 EECS"},{"key":"ref20","first-page":"232","article-title":"Program Generation, Optimization, and Adaptation","volume":"93","author":"piischel","year":"2005","journal-title":"SPIRAL Code generation for DSP transforms Proceedings of the IEEE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041295"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2000.10015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1250734.1250754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref25","first-page":"1","article-title":"Automated Empirical Optimization of Software and the ATLAS project","volume":"27","author":"whaley","year":"2001","journal-title":"Parallel Computing"}],"event":{"name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","start":{"date-parts":[[2010,4,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2010,4,23]]}},"container-title":["2010 IEEE International Symposium on Parallel &amp; Distributed Processing (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5465899\/5470342\/05470421.pdf?arnumber=5470421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T07:42:29Z","timestamp":1711525349000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5470421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2010.5470421","relation":{},"subject":[],"published":{"date-parts":[[2010]]}}}