Communication efficient work distributions in stencil operation based applications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F15%3A86087969" target="_blank" >RIV/61989100:27740/15:86087969 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1002/cpe.3210" target="_blank" >http://dx.doi.org/10.1002/cpe.3210</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1002/cpe.3210" target="_blank" >10.1002/cpe.3210</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Communication efficient work distributions in stencil operation based applications

Popis výsledku v původním jazyce

In recent years, the use of accelerators in conjunction with CPUs, known as heterogeneous computing, has brought about significant performance increases for scientific applications. One of the best examples of this is lattice quantum chromodynamics (QCD), a stencil operation based simulation. These simulations have a large memory footprint necessitating the use of many graphics processing units (GPUs) in parallel. This requires the use of a heterogeneous cluster with one or more GPUs per node. In orderto obtain optimal performance, it is necessary to determine an efficient communication pattern between GPUs on the same node and between nodes. In this paper, we present a performance model based method for min- imizing the communication time of applications with stencil operations, such as lattice QCD, on hetero- geneous computing systems with a non-blocking InfiniBand interconnection network. The proposed method is able to increase the performance of the most computationally intensive

Název v anglickém jazyce

Communication efficient work distributions in stencil operation based applications

Popis výsledku anglicky

In recent years, the use of accelerators in conjunction with CPUs, known as heterogeneous computing, has brought about significant performance increases for scientific applications. One of the best examples of this is lattice quantum chromodynamics (QCD), a stencil operation based simulation. These simulations have a large memory footprint necessitating the use of many graphics processing units (GPUs) in parallel. This requires the use of a heterogeneous cluster with one or more GPUs per node. In orderto obtain optimal performance, it is necessary to determine an efficient communication pattern between GPUs on the same node and between nodes. In this paper, we present a performance model based method for min- imizing the communication time of applications with stencil operations, such as lattice QCD, on hetero- geneous computing systems with a non-blocking InfiniBand interconnection network. The proposed method is able to increase the performance of the most computationally intensive

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/ED1.1.00%2F02.0070" target="_blank" >ED1.1.00/02.0070: Centrum excelence IT4Innovations</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Concurrency Computation Practice and Experience

ISSN

1532-0626

e-ISSN

—

Svazek periodika

27

Číslo periodika v rámci svazku

13

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

18

Strana od-do

"3262-3280"

Kód UT WoS článku

000360178400007

EID výsledku v databázi Scopus

2-s2.0-84939487242