Fixed-Point Trigonometric Functions on FPGAs

Florent de Dinechin 1, 2 Matei Istoan 1, 2 Guillaume Sergent 1
1 LIP - Laboratoire de l'Informatique du Parallélisme
2 ARIC - Arithmetic and Computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Three approaches for computing sines and cosines on FPGAs are studied in this paper, with a focus of high-throughput pipelined architecture, and state-of-the-art implementation techniques. The first approach is the classical CORDIC iteration, for which we suggest a reduced iteration technique and fine optimizations in datapath width and latency. The second is an ad-hoc architecture specifically designed around trigonometric identities. The third uses a generic table- and DSP-based polynomial approximator. These three architectures are implemented and compared in the FloPoCo framework.
Document type :
Conference papers
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download
https://hal-ens-lyon.archives-ouvertes.fr/ensl-00802777
Contributor : Florent de Dinechin <>
Submitted on : Wednesday, March 20, 2013 - 2:28:13 PM
Last modification on : Wednesday, November 20, 2019 - 3:06:52 AM
Long-term archiving on : Sunday, April 2, 2017 - 3:58:39 PM

File

2013-SinCos-RR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : ensl-00802777, version 1

Collections

ENS-LYON | CNRS | INRIA | LIP | UNIV-LYON1

Citation

Florent de Dinechin, Matei Istoan, Guillaume Sergent. Fixed-Point Trigonometric Functions on FPGAs. Fourth International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, Jun 2013, Edimburgh, United Kingdom. pp.1-6. ⟨ensl-00802777⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

410

Files downloads

3085

Contact

CCSD