A methodology for speeding up matrix vector multiplication for single/multi-core architectures - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Journal of Supercomputing Année : 2015

A methodology for speeding up matrix vector multiplication for single/multi-core architectures

Résumé

In this paper, a new methodology for computing the Dense Matrix Vector Multiplication, for both embedded (processors without SIMD unit) and general purpose processors (single and multi-core processors, with SIMD unit), is presented. This methodology achieves higher execution speed than ATLAS state-of-the-art library (speedup from 1.2 up to 1.45). This is achieved by fully exploiting the combination of the software (e.g., data reuse) and hardware parameters (e.g., data cache associativity) which are considered simultaneously as one problem and not separately, giving a smaller search space and high-quality solutions. The proposed methodology produces a different schedule for different values of the (i) number of the levels of data cache; (ii) data cache sizes; (iii) data cache associativities; (iv) data cache and main memory latencies; (v) data array layout of the matrix and (vi) number of cores.

Dates et versions

hal-01239702 , version 1 (08-12-2015)

Identifiants

Citer

Vasilios Kelefouras, Angeliki Kritikakou, Elissavet Papadima, Costas Goutis. A methodology for speeding up matrix vector multiplication for single/multi-core architectures. Journal of Supercomputing, 2015, 71 (7), pp.2644-2667. ⟨10.1007/s11227-015-1409-9⟩. ⟨hal-01239702⟩
120 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More