Abstract
This paper describes an extension to the set of Basic Linear Algebra Subprograms. The extensions are targeted at matrix-vector operations that should provide for efficient and portable implementations of algorithms for high-performance computers
- 1 BARRON, D. W., AND SWINNERTON-DYER, H. P.F. Solution of simultaneous linear equations using a magnetic-tape store. Comput. J. 3 (1960), 28-33.Google Scholar
- 2 BERRY, M., GALLIVAN, K., HARROD, W., JALBY, W., LO, S., MEIER, U., PHILIPPE, B., AND SAMEH, A. Parallel algorithms on the CEDAR system. CSRD Report 581, 1986.Google Scholar
- 3 BISCHOF, C., AND VAN LOAN, C. The WY representation for products of Householder matrices. SIAM J. Sci. Star. Comput. 8, 1 (Jan. 1987), s2-s13. Google Scholar
- 4 BRONLUND, O. E., AND JOHNSEN, T. QR-factorization of partitioned matrices. Comput. Meth. Appl. Mech. Eng., vol. 3, pp. 153-172, 1974.Google Scholar
- 5 BUCHER, I., AND JORDAN, T. Linear algebra programs for use on a vector computer with a secondary solid state storage device. In Advances in Computer Methods for Partial Differential Equations, R. Vichnevetsky and R. Stepleman, Eds. IMACS, 1984, 546-550.Google Scholar
- 6 CALAHAN, D.A. Block-oriented local-memory-based linear equation solution on the CRAY-2: Uniprocessor algorithms. In Proceedings International Conference on Parallel Processing (Aug. 1986). IEEE Computer Society Press, New York, 1986.Google Scholar
- 7 CARNEVALI, P., RADICATI DI BROZOLO, G., ROBERT, Y., AND SGUAZZERO, P. Efficient Fortran implementation of the Gaussian elimination and Householder reduction algorithms on the IBM 3090 vector multiprocessor. IBM ECSEC Rep. ICE-0012, 1987.Google Scholar
- 8 CHARTRES, B. Adaption of the Jacobi and Givens methods for a computer with magnetic tape backup store. Univ. of Sydney Tech. Rep. 8, 1960.Google Scholar
- 9 DAVE, A. K., AND DUFF, I.S. Sparse matrix calculations on the CRAY-2. Parallel Comput. 5 (July 1987), 55-64.Google Scholar
- 10 DEMMEL, J., DONGARRA, J. J., DU CROZ, J., GREENBAUM, A., HAMMARLING, S., AND SORENSEN, D. Prospectus for the development of a linear algebra library for high-performance computers. Argonne National Lab. Rep. ANL-MCS-TM-97, Sept. 1987.Google Scholar
- 11 DIETRICH, G. A new formulation of the hypermatrix Householder QR-decomposition. Comput. Meth. AppI. Mech. Eng. 9 (1976), 273-280.Google Scholar
- 12 DODSON, D., AND LEWIS, J. Issues relating to extension of the basic linear algebra subprograms. ACM SIGNUM Newsl. 20, 1 (1985), 2-18. Google Scholar
- 13 DONGARRA, J. J., BUNCH, J., MOLER, C., AND STEWART, G. LINPACK Users' Guide. SIAM, Philadelphia, Pa., 1979.Google Scholar
- 14 DONGARRA, J. J., DuCRoz, J., HAMMARLING, S., AND HANSON, R. An extended set of Fortran basic linear algebra subprograms. ACM Trans. Math. Softw. 14, i (Mar. 1988), 1-17. Google Scholar
- 15 DONGARRA, J. J., DuCRoz, Z., HAMMARLING, S., AND HANSON, R. An extended set of Fortran basic linear algebra subprograms: Model implementation and test programs. ACM Trans. Math. Softw. 14, I (Mar. 1988), 18-32. Google Scholar
- 16 DONGARRA, J. J., DuCRoz, J., DUFF, I. S., AND HAMMARLING, S. A set of level 3 basic linear algebra subprograms: Model implementation and test programs. This issue, pp. 18-37. Google Scholar
- 17 DONGARRA, J. J., AND DUFF, I.S. Advanced architecture computers. Univ. of Tennessee, Rep. CS-89-90, Nov. 1989. Google Scholar
- 18 DONGARRA, J. J., GUSTAVSON, F., AND KARP, A. Implementing linear algebra algorithms for dense matrices on a vector pipeline machine. SIAM Rev. 26, 1 (1984), 91-112.Google Scholar
- 19 DONGARRA, J. J., HAMMARLING, S., AND SORENSEN, O. C. Block reduction of matrices to condensed forms for eigenvalue computations. Argonne National Lab. Rep. ANL-MCS-TM-99, Sept. 1987.Google Scholar
- 20 DONGARRA, J. J., AND HEWITT, T. Implementing dense linear algebra using multitasking on the CRAY X-MP-4. J. Comput. Appl. Math. 27 (1989), 215-227.Google Scholar
- 21 DONGARRA, J. J., AND SORENSEN, D.C. Linear algebra on high-performance computers. In Proceedings Parallel Computing 85, U. Schendel, Ed. North Holland, Amsterdam, 1986, 113-136.Google Scholar
- 22 DuCRoz, J., NUGENT, S., REID, J., AND TAYLOR, D. Solving large full sets of linear equations in a paged virtual store. ACM Trans. Math. Softw. 7, 4 (1981), 527-536. Google Scholar
- 23 DUFF, I. S. Full matrix techniques in sparse Gaussian elimination. In Numerical Analysis Proceedings, Dundee 1981, Lecture Notes in Mathematics 912. Springer-Verlag, New York, 1981, 71-84.Google Scholar
- 24 GALLIVAN, K., JALBV, W., AND MEIER, U. The use of BLAS3 in linear algebra on a parallel processor with a hierarchical memory. SIAM J. Sci. Star. Comput. 8, 6 (Nov. 1987), 1079-1084. Google Scholar
- 25 GEORGE, A., AND RASHWAN, S. Auxiliary storage methods for solving finite element systems. SIAM J. Sci. Star. Comput. 6, 4 (Oct. 1985), 882-910.Google Scholar
- 26 IBM. Engineering and scientific subroutine library. Program 5668-863, 1986.Google Scholar
- 27 LAWSON, C., HANSON, R. KINCAID, D., AND KROGH, F. Basic linear algebra subprograms for Fortran usage. ACM Trans. Math. Softw. 5 (1979), 308-323. Google Scholar
- 28 LAWSON, C., HANSON, R., KINCAID, D., AND KROGH, F. Algorithm 539: Basic linear algebra subprograms for Fortran usage. ACM Trans. Math. Softw. 5 (1979), 324-325. Google Scholar
- 29 MCKELLAR, A. C., AND COFFMAN, E. G., JR. Organizing matrices and matrix operations for paged memory systems. Commun. ACM 12, 3 (1969), 153-165. Google Scholar
- 30 ROBERT, Y., AND SGUAZZERO, P. The LU decomposition algorithm and its efficient Fortran implementation on the IBM 3090 vector multiprocessor. IBM ECSEC Rep. ICE-0006, 1987.Google Scholar
- 31 SCHREIBER, R. Module design specification (Version 1.0). SAXPY Computer Corp., 255 San Geronimo Way, Sunnyvale, CA 94086, 1986.Google Scholar
- 32 SCHREIBER, R., AND PARLETT, B. Block reflectors: Theory and computation. SIAM J. Numer. Anal. 25, 1 (Feb. 1988), 189-205. Google Scholar
Index Terms
- A set of level 3 basic linear algebra subprograms
Recommendations
Algorithm 679: A set of level 3 basic linear algebra subprograms: model implementation and test programs
This paper describes a model implementation and test software for the Level 3 Basic Linear Algebra Subprograms (Level3 BLAS). The Level3 BLAS are targeted at matrix-matrix operations with the aim of providing more efficient, but portable, ...
Level 3 basic linear algebra subprograms for sparse matrices: a user-level interface
This article proposes a set of Level 3 Basic Linear Algebra Subprograms and associated kernels for sparse matrices. A major goal is to design and develop a common framework to enable efficient, and portable, implementations of iterative algorithms for ...
Comments