@Article{Goto:2008:AHP,
  author =       "Kazushige Goto and Robert A. van de Geijn",
  title =        "Anatomy of a High-Performance Matrix Multiplication",
  journal =      "{ACM} Transactions on Mathematical Software",
  volume =       "34",
  number =       "3",
  month =        may,
  year =         "2008",
  pages =        "12",
  note =         "Article 12, 25 pages",
  URL =          "http://doi.acm.org/10.1145/1356052.1356053",
  abstract =     "We present the basic principles which underlie the high-performance implementation of the 
                 matrix-matrix multiplication that is part of the widely used GotoBLAS library. Design decisions 
                 are justified by successively refining a model of architectures with multilevel memories. 
                 A simple but effective algorithm for executing this operation results. Implementations on a 
                 broad selection of architectures are shown to achieve near-peak performance.",
}