Automated empirical optimizations of software and the ATLAS project

This paper describes the automatically tuned linear algebra software (ATLAS ) project, as well as the fundamental principles that underly it. ATLAS is an instantiation of a new paradigm in high performance library production a nd maintenance, which we term automated empirical optimization of software (AEOS); this style of library management has been created in order to allow software to keep pace with the incredible rate of hardware advancement inh erent in Moore's Law. ATLAS is the application of this new paradigm to line ar algebra software, with the present emphasis on the basic linear algebra subprograms (BLAS), a widely used. performance-critical, linear algebra ker nel library. (C) 2001 Elsevier Science B.V. All rights reserved.