Increasing Double Precision Throughput on NVIDIA Maxwell GPUs
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU121591" target="_blank" >RIV/00216305:26230/16:PU121591 - isvavai.cz</a>
Result on the web
<a href="http://dl.acm.org/citation.cfm?id=2972989" target="_blank" >http://dl.acm.org/citation.cfm?id=2972989</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Increasing Double Precision Throughput on NVIDIA Maxwell GPUs
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/TA04011606" target="_blank" >TA04011606: TraumaTech - Modern Image Processing Techniques and Computer-based Planning in Trauma Treatment</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 24th High Performance Computing Symposium
ISBN
978-1-5108-2318-1
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
146-153
Publisher name
Association for Computing Machinery
Place of publication
Pasadena / Los Angeles
Event location
Pasadena, CA
Event date
Apr 3, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—