[ACM Press the 4th International Workshop - Grenoble, France (2010.07.21-2010.07.23)] Proceedings of the 4th International Workshop on Parallel and Symbolic Computation - PASCO '10 - Exact sparse matrix-vector multiplication on GPU's and multicore architectures

✍ Scribed by Boyer, Brice; Dumas, Jean-Guillaume; Giorgi, Pascal

• Book ID: 121415701
• Publisher: ACM Press
• Year: 2010
• Weight: 613 KB
• Category: Article
• ISBN: 1450300677
• DOI: 10.1145/1837210.1837224

✦ Synopsis

We propose different implementations of the sparse matrixdense vector multiplication (SpMV) for finite fields and rings Z /m Z. We take advantage of graphic card processors (GPU) and multi-core architectures. Our aim is to improve the speed of SpMV in the LinBox library, and henceforth the speed of its black-box algorithms. Besides, we use this library and a new parallelisation of the sigma-basis algorithm in a parallel block Wiedemann rank implementation over finite fields.