论文信息 - Rapid Development of High-Performance Linear Algebra Libraries

Rapid Development of High-Performance Linear Algebra Libraries

We present a systematic methodology for deriving and implementing linear algebra libraries. It is quite common that an application requires a library of routines for the computation of linear algebra operations that are not (exactly) supported by commonly used libraries like LAPACK. In this situation, the application developer has the option of casting the operation into one supported by an existing library, often at the expense of performance, or implementing a custom library, often requiring considerable effort. Our recent discovery of a methodology based on formal derivation of algorithm allows such a user to quickly derive proven correct algorithms. Furthermore it provides an API that allows the so-derived algorithms to be quickly translated into high-performance implementations.

[1] Robert A. van de Geijn,et al. FLAME: Formal Linear Algebra Methods Environment , 2001, TOMS.

[2] Robert A. van de Geijn,et al. Representing linear algebra algorithms in code: the FLAME application program interfaces , 2005, TOMS.

[3] Ed Anderson,et al. LAPACK Users' Guide , 1995 .

[4] D. B. Davis,et al. Intel Corp. , 1993 .

[5] Charles L. Lawson,et al. Basic Linear Algebra Subprograms for Fortran Usage , 1979, TOMS.

[6] Robert A. van de Geijn,et al. Using PLAPACK - parallel linear algebra package , 1997 .

[7] Jack J. Dongarra,et al. An extended set of FORTRAN basic linear algebra subprograms , 1988, TOMS.

[8] Robert A. van de Geijn,et al. Formal derivation of algorithms: The triangular sylvester equation , 2003, TOMS.

[9] Jack J. Dongarra,et al. A set of level 3 basic linear algebra subprograms , 1990, TOMS.

[10] Isak Jonsson,et al. Recursive Blocked Algorithms, Data Structures, and High-Performance Software for Solving Linear Systems and Matrix Equations , 2003 .

[11] Robert A. van de Geijn,et al. The science of deriving dense linear algebra algorithms , 2005, TOMS.