Affiliation:
1. ENSEEIHT-IRIT, Toulouse, France
2. CERFACS, Toulouse, France
Abstract
We describe an implementation of Level-3 BLAS (Basic Linear Algebra Subprograms) based on the use of the matrix-matrix multiplication kernel (GEMM). Blocking techniques are used to express the BLAS in terms of operations involving triangular blocks and calls to GEMM. A principal advantage of this approach is that most manufacturers provide at least an efficient serial version of GEMM so that our implementation can capture a significant percentage of the computer performance. A parameter which controls the blocking allows an efficient exploitation of the memory hierarchy of the various target computers. Furthermore, this blocked version of Level-3 BLAS is naturally parallel. We present results on the ALLIANT FX/80, the CONVEX C220, the CRAY-2, and the IBM 3090/VF. For GEMM, we always use the manufacturer-supplied versions. For the operations dealing with triangular blocks, we use assembler or tuned Fortran (using loop-unrolling) codes, depending on the efficiency of the available libraries.
Publisher
Association for Computing Machinery (ACM)
Subject
Applied Mathematics,Software
Reference25 articles.
1. AIvlESTOY P R. DAYD~ M. J. DUFF h S. AND MORgRE P. 1992 Linear algebra calculations on the BBN TC2000. CERFACS Rep. TR/PA/92/69. AIvlESTOY P R. DAYD~ M. J. DUFF h S. AND MORgRE P. 1992 Linear algebra calculations on the BBN TC2000. CERFACS Rep. TR/PA/92/69.
2. ANDERSON E. BAI Z. BISCHOF C. DEMMEL J. W. DONGARRA J J. DU CROZ J. GREENBAUM A. HAMMARLING S McKENNEY A OSTROUCHOV S AND SORENSEN D. C. 1992. LAPACK Users' Guide. SIAM Philadelphia Pa. ANDERSON E. BAI Z. BISCHOF C. DEMMEL J. W. DONGARRA J J. DU CROZ J. GREENBAUM A. HAMMARLING S McKENNEY A OSTROUCHOV S AND SORENSEN D. C. 1992. LAPACK Users' Guide. SIAM Philadelphia Pa.
3. BEm~En P DAYDI~ M J. AND MORi~RE P. 1991 Implementation and use of Level 3 BLAS kernels on a transputer T800 Ring Network. CERFACS Rep. TR/PA/91/54. BEm~En P DAYDI~ M J. AND MORi~RE P. 1991 Implementation and use of Level 3 BLAS kernels on a transputer T800 Ring Network. CERFACS Rep. TR/PA/91/54.
4. BlSCHOF C. AND VAN LOAN C. 1987. The WY representation for products of house-holder matrices SIAM J ScL Stat Comput. 8 2 2-13. 10.1137/0908009 BlSCHOF C. AND VAN LOAN C. 1987. The WY representation for products of house-holder matrices SIAM J ScL Stat Comput. 8 2 2-13. 10.1137/0908009
5. Block-oriented, local-memory-based linear equation solution on the CRAY-2: Uniprocessor algorithms. In Proceedings of the International Con/brence on Parallel Processing. IEEE Computer Society, Washington;CALAHAN D. A.;D C.,1986
Cited by
14 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献