{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:25:10Z","timestamp":1729617910045,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/hipc.2013.6799131","type":"proceedings-article","created":{"date-parts":[[2014,5,2]],"date-time":"2014-05-02T14:26:14Z","timestamp":1399040774000},"page":"452-461","source":"Crossref","is-referenced-by-count":22,"title":["Compiler generation and autotuning of communication-avoiding operators for geometric multigrid"],"prefix":"10.1109","author":[{"given":"Protonu","family":"Basu","sequence":"first","affiliation":[]},{"given":"Anand","family":"Venkat","sequence":"additional","affiliation":[]},{"given":"Mary","family":"Hall","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Van Straalen","sequence":"additional","affiliation":[]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Time skewing A value-based approach to optimizing for memory locality","year":"1999","author":"mccalpin","key":"19"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2000.845979"},{"key":"17","first-page":"425","article-title":"Dimepack-a cache-optimized multigrid library","volume":"1","author":"kowarschik","year":"2001","journal-title":"Proc of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA 2001)"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1504\/PCFD.2008.018088"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1145\/1250734.1250761"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304619"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407876"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400690"},{"key":"13","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1002\/nla.1808","article-title":"Improving the arithmetic intensity of multigrid with the help of polynomial smoothers","volume":"19","author":"ghysels","year":"2012","journal-title":"Numerical Linear Algebra with Applications"},{"key":"14","article-title":"Loop transformation recipes for code generation and auto-tuning","author":"hall","year":"2009","journal-title":"Proc of the 22nd International Workshop on Languages and Compilers for Parallel Computing"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259037"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407931"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259044"},{"key":"12","article-title":"Evaluation of cache-based superscalar and cacheless vector architectures for scientific computations","author":"frigo","year":"2005","journal-title":"Proc of the 19th ACM International Conference on Supercomputing (ICS05)"},{"key":"21","article-title":"Tiling optimizations for 3D scientific computations","author":"rivera","year":"2000","journal-title":"Proc of SCIS '00"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.2"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041295"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301668"},{"key":"24","article-title":"How to optimize geometric multigrid methods on GPUS","author":"sturmer","year":"2011","journal-title":"Proc Copper Mountain Conf Multigrid Methods"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1145\/1989493.1989508"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161054"},{"journal-title":"Efficiency Improvements of Iterative Numerical Algorithms on Modern Architectures","year":"2008","author":"treibig","key":"27"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2009.82"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536295"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882364"},{"journal-title":"Exposing Fine-grained Parallelism in Algebraic Multigrid Methods","year":"2011","author":"bell","key":"2"},{"key":"10","first-page":"21","article-title":"Cache optimization for structured and unstructured grid multigrid","volume":"10","author":"douglas","year":"2000","journal-title":"Elect Trans Numer Anal"},{"journal-title":"Optimizing Compilers for Modern Architectures A Dependence-Based Approach","year":"2002","author":"allen","key":"1"},{"key":"30","article-title":"Optimization of geometric multigrid for emerging multi-and manycore processors","author":"williams","year":"2012","journal-title":"Proc of the International Conference on High Performance Computing Networking Storage and Analysis SC '12"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"journal-title":"Chill A Framework for Composing High-level Loop Transformations","year":"2008","author":"chen","key":"6"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1145\/1128022.1128027"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/2254064.2254123"},{"key":"31","doi-asserted-by":"crossref","DOI":"10.1145\/2063384.2063458","article-title":"Extracting ultra-scale lattice boltzmann performance via hierarchical and distributed autotuning","author":"williams","year":"2011","journal-title":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654065"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"8","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"}],"event":{"name":"2013 20th International Conference on High Performance Computing (HiPC)","start":{"date-parts":[[2013,12,18]]},"location":"Bengaluru (Bangalore), Karnataka, India","end":{"date-parts":[[2013,12,21]]}},"container-title":["20th Annual International Conference on High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6784161\/6799095\/06799131.pdf?arnumber=6799131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T08:33:46Z","timestamp":1498120426000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6799131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/hipc.2013.6799131","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}