{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:47:04Z","timestamp":1729619224261,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,10]]},"DOI":"10.1109\/pact.2011.59","type":"proceedings-article","created":{"date-parts":[[2012,1,6]],"date-time":"2012-01-06T19:28:47Z","timestamp":1325878127000},"page":"276-287","source":"Crossref","is-referenced-by-count":8,"title":["StVEC: A Vector Instruction Extension for High Performance Stencil Computation"],"prefix":"10.1109","author":[{"given":"Naser","family":"Sedaghati","sequence":"first","affiliation":[]},{"given":"Renji","family":"Thomas","sequence":"additional","affiliation":[]},{"given":"Louis-No\u00ebl","family":"Pouchet","sequence":"additional","affiliation":[]},{"given":"Radu","family":"Teodorescu","sequence":"additional","affiliation":[]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","DOI":"10.1145\/1062261.1062291","article-title":"Matrix register file and extended subwords: Two techniques for embedded media processors","author":"shahbahrami","year":"2005","journal-title":"CF"},{"key":"22","article-title":"Data layout transformation for stencil computations on short-vector simd architectures","author":"henretty","year":"2011","journal-title":"CC"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454119"},{"key":"18","article-title":"A register file with transposed access mode","author":"jung","year":"2000","journal-title":"ICCD"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71229-9_1"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/1509864.1509866"},{"journal-title":"Nangate open cell library","year":"0","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/996893.996853"},{"key":"11","article-title":"CACTI 6.0: A tool to model large caches","author":"muralimanohar","year":"2009","journal-title":"HP Labs Tech Rep HPL- 2009-85"},{"journal-title":"Synopsys Design Compiler","year":"0","key":"12"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2010.5416631"},{"key":"3","doi-asserted-by":"crossref","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 Rev"},{"key":"20","article-title":"Liner-time matrix transpose algorithms using vector register file with diagonal registers","author":"hanounik","year":"2001","journal-title":"IPDPS"},{"key":"2","article-title":"A multilevel parallelization framework for high-order stencil computations","author":"dursun","year":"2009","journal-title":"Euro-Par"},{"key":"1","article-title":"Optimized stencil computation using in-place calculation on modern multicore systems","author":"augustin","year":"2009","journal-title":"Euro-Par"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1145\/1111583.1111589"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1145\/76263.76337"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2009.82"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1250734.1250754"},{"key":"4","doi-asserted-by":"crossref","DOI":"10.1145\/1250734.1250761","article-title":"Effective automatic parallelization of stencil computations","author":"krishnamoorthy","year":"2007","journal-title":"PLDI"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/53990.54022"},{"journal-title":"Optimizing Compilers for Modern Architectures A Dependence-Based Approach","year":"2002","author":"kennedy","key":"8"}],"event":{"name":"2011 International Conference on Parallel Architectures and Compilation Techniques (PACT)","start":{"date-parts":[[2011,10,10]]},"location":"Galveston, TX, USA","end":{"date-parts":[[2011,10,14]]}},"container-title":["2011 International Conference on Parallel Architectures and Compilation Techniques"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6112806\/6113772\/06113836.pdf?arnumber=6113836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T08:57:11Z","timestamp":1686646631000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6113836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/pact.2011.59","relation":{},"subject":[],"published":{"date-parts":[[2011,10]]}}}