Detail publikace

Increasing Double Precision Throughput on NVIDIA Maxwell GPUs

POLOK, L. SMRŽ, P.

Originální název

Increasing Double Precision Throughput on NVIDIA Maxwell GPUs

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper deals with the impact the architectural changes of modern GPUs have on their use in scientific computing. It particularly focuses on significant drops in the number of double precision functional units in NVIDIA Maxwell architecture. Proposed remedies of the potential negative impact on GPGPU applications that are based on multiple precision arithmetics are discussed. Two new algorithms for fast and precise multiplication and fused multiply add for double precision arithmetics emulation are also presented here.  Using these methods, we were able to boost the double precision performance of NVIDIA GTX 980 Ti from 95 GFLOPS up to 286 GFLOPS. The proposed methods are applicable also to other GPUs.

Klíčová slova

double precision calculation, multiple precision arithmetics, GPGPU

Autoři

POLOK, L.; SMRŽ, P.

Vydáno

3. 4. 2016

Nakladatel

Association for Computing Machinery

Místo

Pasadena / Los Angeles

ISBN

978-1-5108-2318-1

Kniha

Proceedings of the 24th High Performance Computing Symposium

Strany od

146

Strany do

153

Strany počet

8

URL

http://dl.acm.org/citation.cfm?id=2972989

BibTex

@inproceedings{BUT130935,
  author="Lukáš {Polok} and Pavel {Smrž}",
  title="Increasing Double Precision Throughput on NVIDIA Maxwell GPUs",
  booktitle="Proceedings of the 24th High Performance Computing Symposium",
  year="2016",
  pages="146--153",
  publisher="Association for Computing Machinery",
  address="Pasadena / Los Angeles",
  isbn="978-1-5108-2318-1",
  url="http://dl.acm.org/citation.cfm?id=2972989"
}