Hardware support for UNUM floating point arithmetic

Andrea Bocco 1, 2 Yves Durand 1 Florent de Dinechin 2
2 SOCRATE - Software and Cognitive radio for telecommunications
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : The Universal NUMber, or UNUM, is a variable length floating-point format conceived to substitute the current one defined in the IEEE 754 standard. UNUM is able, through an internal algebra based on interval arithmetic, to keep track of the precision during operations, offering better result reliability than IEEE 754. This work discusses the implementation of UNUM arithmetic and reports hardware implementation results of some of the UNUM operators.
Document type :
Conference papers
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.inria.fr/hal-01618698
Contributor : Florent de Dinechin <>
Submitted on : Wednesday, October 18, 2017 - 12:23:03 PM
Last modification on : Tuesday, November 19, 2019 - 10:44:02 AM
Long-term archiving on: Friday, January 19, 2018 - 12:58:38 PM

File

07974115.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Andrea Bocco, Yves Durand, Florent de Dinechin. Hardware support for UNUM floating point arithmetic. 13th Conference on Ph.D. Research in Microelectronics and Electronics (PRIME), Jun 2017, Taormina, Italy. pp.93 - 96, ⟨10.1109/PRIME.2017.7974115⟩. ⟨hal-01618698⟩

Share

Metrics

Record views

343

Files downloads

10386