Accelerating R with high performance linear algebra libraries

Journal Title: Revista Romana de Statistica - Year 2015, Vol 63, Issue 3

Abstract

Linear algebra routines are basic building blocks for the statistical software. In this paper we analyzed how can we improve R performance for matrix computations. We benchmarked few matrix operations using the standard linear algebra libraries included in the R distribution and high performance libraries like OpenBLAS, GotoBLAS and MKL. Our tests showed the best results are obtained with the MKL library, the other two libraries having similar performances, but lower than MKL.

Authors and Affiliations

Bogdan Oancea, Tudorel Andrei, Raluca Mariana Dragoescu

Keywords

Related Articles

Model for estimating Financial Results at Company Level by using Simple Linear Regression

The econometric model means a lot of numerical relations that enables simplified representation of the economic process subject to study. Current models often involves more than ten relations (equations). The validity o...

Classical Models used in the Management of Financial Instruments Portfolio

Classical models used in the management of financial instruments portfolio constitute the basis of modern portfolio theory even if you are currently their application lead to results limited.

Negotiation team – a brief technical overview

Negotiating team is actually part of the preparation of the negotiation and its role is solving all problems arising, evaluation, argumentation and counter-argumentation, explanation etc. It is almost impossible that one...

O succintă analiză de sezonalitate a pieţei autoturismelor în România

Acest articol prezintă o analiză succintă de sezonalitate axată pe statistici lunare ale unor variabile specifice vânzărilor totale de autoturisme autohtone și importate axate pe seriile de date ale ultimilor trei ani al...

Creditele neperformante şi impactul acestora asupra stabilităţii financiare

Stabilitate financiară reprezintă situaţia în care sistemul financiar – intermediari, piețe și infrastructuri de piață – poate să facă față șocurilor fără perturbări major, fiind capabil să atragă şi să plaseze fonduri b...

Download PDF file
  • EP ID EP100777
  • DOI -
  • Views 167
  • Downloads 0

How To Cite

Bogdan Oancea, Tudorel Andrei, Raluca Mariana Dragoescu (2015). Accelerating R with high performance linear algebra libraries. Revista Romana de Statistica, 63(3), 109-117. https://europub.co.uk/articles/-A-100777