OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Data-types optimization for floating-point formats by program transformation

Damouche, Nasrine and Martel, Matthieu and Chapoutot, Alexandre Data-types optimization for floating-point formats by program transformation. (2016) In: International Conference on Control, Decision and Information Technologies (CoDIT 2016), 6 April 2016 - 8 April 2016 (Saint Julian's, Malta).

[img] (Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: https://doi.org/10.1109/CoDIT.2016.7593626


In floating-point arithmetic, a desirable property of computations is to be accurate, since in many industrial context small or large perturbations due to round-off errors may cause considerable damages. To cope with this matter of fact, we have developed a tool which corrects these errors by automatically transforming programs in a source to source manner. Our transformation, relying on static analysis by abstract abstraction, concerns pieces of code with assignments, conditionals and loops. By transforming programs, we can significantly optimize the numerical accuracy of computations by minimizing the error relatively to the exact result. An interesting side-effect of our technique is that more accurate computations may make it possible to use smaller data-types. In this article, we show that our transformed programs, executed in single precision, may compete with not transformed codes executed in double precision.

Item Type:Conference or Workshop Item (Paper)
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Other partners > Ecole Nationale Supérieure de Techniques Avancées - ENSTA (FRANCE)
Other partners > Université Paris-Saclay (FRANCE)
Other partners > Université de Perpignan Via Domitia - UPVD (FRANCE)
Laboratory name:
Deposited On:03 Feb 2023 10:09

Repository Staff Only: item control page