SUMMA: scalable universal matrix multiplication algorithm Export

@article{citeulike:4405750, abstract = {In the paper we give a straightforward, highly efficient, scalable implementation of common matrix multiplication operations. The algorithms are much simpler than previously published methods, yield better performance, and require less work space. MPI implementations are given, as are performance results on the Intel Paragon system. {\copyright} 1997 by John Wiley \& Sons, Ltd.}, address = {Department of Computer Sciences, The University of Texas at Austin, Taylor Hall 2.124, Austin, TX 78712-1188, USA; Scalable Concurrent Programming Laboratory, California Institute of Technology, Pasadena, CA 91125, USA}, author = {Van De Geijn, R. A. and Watts, J.}, citeulike-article-id = {4405750}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/(SICI)1096-9128(199704)9:4%3C255::AID-CPE250%3E3.0.CO;2-2}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/13861/ABSTRACT}, doi = {10.1002/(SICI)1096-9128(199704)9:4%3C255::AID-CPE250%3E3.0.CO;2-2}, journal = {Concurrency: Practice and Experience}, keywords = {algorithm, numerical, parallel}, number = {4}, pages = {255--274}, posted-at = {2009-04-26 08:56:18}, priority = {2}, title = {SUMMA: scalable universal matrix multiplication algorithm}, url = {http://dx.doi.org/10.1002/(SICI)1096-9128(199704)9:4%3C255::AID-CPE250%3E3.0.CO;2-2}, volume = {9}, year = {1997} }

TY - JOUR ID - citeulike:4405750 L3 - citeulike-article-id:4405750 N2 - In the paper we give a straightforward, highly efficient, scalable implementation of common matrix multiplication operations. The algorithms are much simpler than previously published methods, yield better performance, and require less work space. MPI implementations are given, as are performance results on the Intel Paragon system. © 1997 by John Wiley & Sons, Ltd. IS - 4 JF - Concurrency: Practice and Experience AD - Department of Computer Sciences, The University of Texas at Austin, Taylor Hall 2.124, Austin, TX 78712-1188, USA; Scalable Concurrent Programming Laboratory, California Institute of Technology, Pasadena, CA 91125, USA EP - 274 TI - SUMMA: scalable universal matrix multiplication algorithm VL - 9 SP - 255 KW - algorithm KW - numerical KW - parallel AU - Van De Geijn, RA AU - Watts, J PY - 1997/// UR - http://dx.doi.org/10.1002/(SICI)1096-9128(199704)9:4%3C255::AID-CPE250%3E3.0.CO;2-2 ER -