Improving the Coding Speed of Erasure Codes with Polynomial Ring Transforms

Jonathan Detchart (1) , Jérôme Lacan (1)

1 DISC - Département d'Ingénierie des Systèmes Complexes

Erasure codes are widely used in today’s storage systems to cope with failures. Most of them use the finite field arithmetic. In this paper, we propose an implementation and a coding speed evaluation of an original method called PYRIT (PolYnomial RIng Transform) to perform operations between elements of a finite field into a bigger ring by using fast transforms between these two structures. Working in such a ring is much easier than working in a finite field. Firstly, it reduces the coding complexity by design. Secondly, it allows simple but efficient xor-based implementations by unrolling the operations thanks to the properties of the ring structure. We evaluate this proposition for Maximum Distance Separable erasure codes and we show that our method has better performances than common codes. Compared to the best known implementations, the coding speeds are increased by a factor varying from 1.5 to 2.

Mots clés: Erasure codes; Xor-based implementation

Domaines: Réseaux et télécommunications [cs.NI]

Jonathan Detchart, Jérôme Lacan. Improving the Coding Speed of Erasure Codes with Polynomial Ring Transforms. GLOBECOM 2017 - 2017 IEEE Global Communications Conference, Dec 2017, Singapour, Singapore. pp.1-6, ⟨10.1109/GLOCOM.2017.8255009⟩. ⟨hal-01904733⟩