@Article{Goto:2008:HPI,
  author =       "Kazushige Goto and Robert van de Geijn",
  title =        "High Performance Implementation of the Level-3 {BLAS}",
  journal =      "{ACM} Transactions on Mathematical Software",
  volume =       "35",
  number =       "1",
  month =        jul,
  year =         "2008",
  pages =        "4:1--4:14",
  URL =          "http://doi.acm.org/10.1145/1377603.1377607",
  abstract =     "A simple but highly effective approach for transforming high-performance implementations on
                 cache-based architectures of matrix-matrix multiplication into implementations of other commonly
                 used matrix-matrix computations (the level-3 BLAS) is presented. Exceptional performance is
                 demonstrated on various architectures.",
}