2008/05/01 by Kazushige Goto, Robert A. Geijn · 3 citations
Computer Science · Engineering · Mathematics · #Parallel Computing and Optimization Techniques #Interconnection Networks and Systems #Low-power high-performance VLSI design #Computer science #Matrix multiplication #Multiplication (music) #Simple (philosophy) #Selection (genetic algorithm) #Implementation #Matrix (chemical analysis) #Parallel computing #Computer architecture #Arithmetic #Computer engineering #Computational science #Algorithm #Artificial intelligence #Programming language #Mathematics
paper · doi:10.1145/1356052.1356053
openalex publication_date 2008/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
We present the basic principles that 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.