Accelerating Correctly Rounded Floating-PointDivision when the Divisor is Known in Advance

Abstract : We present techniques for accelerating the floating-point computation of x/y when y is known before x. The proposed algorithms are oriented toward architectures with available fused-mac operations. The goal is to get exactly the same result as with usual division with rounding to nearest. It is known that the advanced computation of 1/y allows performing correctly rounded division in one multiplication plus two fused-macs. We show algorithms that reduce this latency to one multiplication and one fused-mac. This is achieved if a precision of at least n+1 bits is available, where n is the number of mantissa bits in the target format, or if y satisfies some properties that can be easily checked at compile-time. This requires a double-word approximation of 1/y (we also show how to get it). Compilers to accelerate some numerical programs without loss of accuracy can use these techniques.
Type de document :
Article dans une revue
IEEE Transactions on Computers, Institute of Electrical and Electronics Engineers, 2004, 53 (8), pp.1069- 1072. 〈10.1109/TC.2004.37〉
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal-ens-lyon.archives-ouvertes.fr/ensl-00087465
Contributeur : Jean-Michel Muller <>
Soumis le : lundi 24 juillet 2006 - 16:27:52
Dernière modification le : samedi 21 avril 2018 - 01:27:21
Document(s) archivé(s) le : mardi 6 avril 2010 - 00:24:15

Identifiants

Citation

Jean-Michel Muller, Nicolas Brisebarre, Saurabh Raina. Accelerating Correctly Rounded Floating-PointDivision when the Divisor is Known in Advance. IEEE Transactions on Computers, Institute of Electrical and Electronics Engineers, 2004, 53 (8), pp.1069- 1072. 〈10.1109/TC.2004.37〉. 〈ensl-00087465〉

Partager

Métriques

Consultations de la notice

250

Téléchargements de fichiers

298