Detail publikačního výsledku

Fast Linear Algebra on GPU

POLOK, L.; SMRŽ, P.

Originální název

Fast Linear Algebra on GPU

Anglický název

Fast Linear Algebra on GPU

Druh

Stať ve sborníku mimo WoS a Scopus

Originální abstrakt

GPUs have been successfullyused for acceleration of many mathematical functions and libraries. A commonlimitation of those libraries is the minimal size of primitives being handled,in order to achieve a significant speedup compared to their CPU versions. Theminimal size requirement can prove prohibitive for many applications. It can beloosened by batching operations in order to have sufficient amount of data toperform the calculation maximally efficiently on the GPU. A fast OpenCLimplementation of two basic vector functions - vector reduction and vectorscaling - is described in this paper. Its performance is analyzed by runningbenchmarks on two of the most common GPUs in use - Tesla and Fermi GPUs fromNVIDIA. Reported experimental results show that our implementation significantlyoutperforms the current state-of-the-art GPU-based basic linear algebra libraryCUBLAS.

Anglický abstrakt

GPUs have been successfullyused for acceleration of many mathematical functions and libraries. A commonlimitation of those libraries is the minimal size of primitives being handled,in order to achieve a significant speedup compared to their CPU versions. Theminimal size requirement can prove prohibitive for many applications. It can beloosened by batching operations in order to have sufficient amount of data toperform the calculation maximally efficiently on the GPU. A fast OpenCLimplementation of two basic vector functions - vector reduction and vectorscaling - is described in this paper. Its performance is analyzed by runningbenchmarks on two of the most common GPUs in use - Tesla and Fermi GPUs fromNVIDIA. Reported experimental results show that our implementation significantlyoutperforms the current state-of-the-art GPU-based basic linear algebra libraryCUBLAS.

Klíčová slova

GPU; parallel reduction; linear algebra;BLAS; OpenCL; CUDA

Klíčová slova v angličtině

GPU; parallel reduction; linear algebra;BLAS; OpenCL; CUDA

Autoři

POLOK, L.; SMRŽ, P.

Rok RIV

2013

Vydáno

25.06.2012

Nakladatel

IEEE Computer Society

Místo

Liverpool

ISBN

978-0-7695-4749-7

Kniha

IEEE conference proceedings

Strany od

1

Strany do

6

Strany počet

6

URL

https://www.fit.vut.cz/research/publication/10039/

BibTex

@inproceedings{BUT96982,
  author="Lukáš {Polok} and Pavel {Smrž}",
  title="Fast Linear Algebra on GPU",
  booktitle="IEEE conference proceedings",
  year="2012",
  pages="1--6",
  publisher="IEEE Computer Society",
  address="Liverpool",
  isbn="978-0-7695-4749-7",
  url="https://www.fit.vut.cz/research/publication/10039/"
}

Dokumenty

hpcc_ipolok_smrz_submitted_IGA_nochg