A Novel SIMD-Optimized Implementation for Fast and Memory-Efficient Trigonometric Computation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Goyal, Nikhil Dev, Arora, Parth
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912233484713984
author Goyal, Nikhil Dev
Arora, Parth
author_facet Goyal, Nikhil Dev
Arora, Parth
contents This paper proposes a novel set of trigonometric implementations which are 5x faster than the inbuilt C++ functions. The proposed implementation is also highly memory efficient requiring no precomputations of any kind. Benchmark comparisons are done versus inbuilt functions and an optimized taylor implementation. Further, device usage estimates are also obtained, showing significant hardware usage reduction compared to inbuilt functions. This improvement could be particularly useful for low-end FPGAs or other resource-constrained devices.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel SIMD-Optimized Implementation for Fast and Memory-Efficient Trigonometric Computation
Goyal, Nikhil Dev
Arora, Parth
Mathematical Software
This paper proposes a novel set of trigonometric implementations which are 5x faster than the inbuilt C++ functions. The proposed implementation is also highly memory efficient requiring no precomputations of any kind. Benchmark comparisons are done versus inbuilt functions and an optimized taylor implementation. Further, device usage estimates are also obtained, showing significant hardware usage reduction compared to inbuilt functions. This improvement could be particularly useful for low-end FPGAs or other resource-constrained devices.
title A Novel SIMD-Optimized Implementation for Fast and Memory-Efficient Trigonometric Computation
topic Mathematical Software
url https://arxiv.org/abs/2502.10831