A PVM-based library for sparse matrix factorizations
We present 3LM, a C Linked List Management Library for parallel sparse factorizations on a PVM environment which takes into account the fill-in, an important drawback of sparse computations. It is restricted to a mesh topology and is based on an SPMD paradigm. Our goal is to facilitate the programming in such environments by means of a set of list and vector-oriented operations. The result is a pseudo-sequential code, in which the interprocessor communications and the sparse data structures are hidden from the programmer.
Unable to display preview. Download preview PDF.
- 1.Choi, J., Demmel, J., Dhillon, I., Dongarra, J., Ostrouchov, S., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLAPACK: a Portable Linear Algebra Library for Distributed Memory Computers-Design Issues and Performance. Tech. Report CS-95-283, Dep. Computer Science, University of Tennessee (1995).Google Scholar
- 2.Doallo, R., Fraguela, B.B., Touriño, J., Zapata, E.L.: Parallel Sparse Modified Gram-Schmidt QR Decomposition. In Int'l Conference on High-Performance Computing and Networking, HPCN'96, Brussels. Lecture Notes in Computer Science, Vol. 1067, Springer-Verlag (1996) 646–653.Google Scholar
- 3.Duff, I.S., Grimes, R.G., Lewis, J.G.: User's Guide for the Harwell-Boeing Sparse Matrix Collection. Tech. Report TR-PA-92-96, CERFACS (1992).Google Scholar
- 4.Golub, G.H., van Loan, C.F.: Matrix Computations. The Johns Hopkins University Press, second edition (1989).Google Scholar
- 5.Remington, K.A., Pozo, R.: NIST Sparse BLAS User's Guide. National Institute of Standards and Technology (1996).Google Scholar
- 6.Touriño, J.: Parallelization and Compilation Issues of Sparse QR Algorithms. PhD Thesis, Dep. of Electronics and Systems, University of A Coruna, Spain (1998).Google Scholar