@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",
 accepted =     "28 October 2007",
 upcoming =     "true",
 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."
}