Collapsing floating-point operations
Résumé
This paper addresses the issue of collapsing dependent floating-point operations. The presentation focuses on studying the dataflow graph of benchmark involving a large number of floating-point instructions. In particular, it focuses on the relevance of new floating-point operators performing two dependent operations which are similar to "fused multiply and add". Finally, this paper examines the implementation cost and critical path reduction from this strategy.
Domaines
Architectures Matérielles [cs.AR]Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...