Basic sparse computations on data parallel computers
William R. Ferng, Serge G. Petiton, Kesheng John Wu · PPSC · 1993
This paper presents a preliminary experimental study of the performance of basic sparse matrix computations on the CM-200 and the CM-5 massively parallel computers. We concentrate on examining various ways of performing general sparse matrix-vector operations and the basic primitives on which there are based in SIMD data parallel mode. Various data structures for storing sparse matrices and their corresponding matrix-vector multiplications are compared.