FuzzyGPU: a fuzzy arithmetic library for GPU - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2013

FuzzyGPU: a fuzzy arithmetic library for GPU

Abstract

Data are traditionally represented using native format such as integer or floating-point numbers in various flavor. However, some applications rely on more complex representation format. This is the case when uncertainty needs to be apprehended. Fuzzy arithmetic is one of the major tools to address this problem, but the execution time of basic operations such as addition or multiplication makes its usage prohibitive. In this article, thanks to a new representation format and modern GPU characteristics we show that it is possible to greatly reduce the execution time of those operations. These techniques have been implemented in fuzzyGPU, a freely distributed library of common operations over fuzzy number.
Fichier principal
Vignette du fichier
fuzzyGPU.pdf (558.51 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00856617 , version 1 (02-09-2013)
hal-00856617 , version 2 (02-12-2013)

Identifiers

  • HAL Id : hal-00856617 , version 2

Cite

David Defour, Manuel Marin. FuzzyGPU: a fuzzy arithmetic library for GPU. [Research Report] LIRMM. 2013. ⟨hal-00856617v2⟩
170 View
745 Download

Share

Gmail Facebook Twitter LinkedIn More