A GPU offloading mechanism for LHCb

Alexey Badalov; Daniel Hugo Cámpora Pérez; Alexander Zvyagin; Niko Neufeld; Xavier Vilasís-Cardona

doi:10.1088/1742-6596/513/5/052004

A GPU offloading mechanism for LHCb

Alexey Badalov^*, Daniel Hugo Cámpora Pérez, Alexander Zvyagin, Niko Neufeld, Xavier Vilasís-Cardona

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

The current computational infrastructure at LHCb is designed for sequential execution. It is possible to make use of modern multi-core machines by using multi-threaded algorithms and running multiple instances in parallel, but there is no way to make efficient use of specialized massively parallel hardware, such as graphical processing units and Intel Xeon/Phi. We extend the current infrastructure with an out-of-process computational server able to gather data from multiple instances and process them in large batches.

Original language	English
Article number	052004
Number of pages	5
Journal	Journal of Physics: Conference Series
Volume	513
Issue number	5
DOIs	https://doi.org/10.1088/1742-6596/513/5/052004
Publication status	Published - 1 Jun 2014
Externally published	Yes

Access to Document

10.1088/1742-6596/513/5/052004Licence: CC BY

http://stacks.iop.org/1742-6596/513/i=5/a=052004?key=crossref.dc522797221ad597289a8347077a7634

Cite this

@article{01ae1a56fb744e5dab36d07a8c7e04e5,

title = "A GPU offloading mechanism for LHCb",

abstract = "The current computational infrastructure at LHCb is designed for sequential execution. It is possible to make use of modern multi-core machines by using multi-threaded algorithms and running multiple instances in parallel, but there is no way to make efficient use of specialized massively parallel hardware, such as graphical processing units and Intel Xeon/Phi. We extend the current infrastructure with an out-of-process computational server able to gather data from multiple instances and process them in large batches.",

author = "Alexey Badalov and {C{\'a}mpora P{\'e}rez}, {Daniel Hugo} and Alexander Zvyagin and Niko Neufeld and Xavier Vilas{\'i}s-Cardona",

year = "2014",

month = jun,

day = "1",

doi = "10.1088/1742-6596/513/5/052004",

language = "English",

volume = "513",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "5",

}

TY - JOUR

T1 - A GPU offloading mechanism for LHCb

AU - Badalov, Alexey

AU - Cámpora Pérez, Daniel Hugo

AU - Zvyagin, Alexander

AU - Neufeld, Niko

AU - Vilasís-Cardona, Xavier

PY - 2014/6/1

Y1 - 2014/6/1

N2 - The current computational infrastructure at LHCb is designed for sequential execution. It is possible to make use of modern multi-core machines by using multi-threaded algorithms and running multiple instances in parallel, but there is no way to make efficient use of specialized massively parallel hardware, such as graphical processing units and Intel Xeon/Phi. We extend the current infrastructure with an out-of-process computational server able to gather data from multiple instances and process them in large batches.

AB - The current computational infrastructure at LHCb is designed for sequential execution. It is possible to make use of modern multi-core machines by using multi-threaded algorithms and running multiple instances in parallel, but there is no way to make efficient use of specialized massively parallel hardware, such as graphical processing units and Intel Xeon/Phi. We extend the current infrastructure with an out-of-process computational server able to gather data from multiple instances and process them in large batches.

U2 - 10.1088/1742-6596/513/5/052004

DO - 10.1088/1742-6596/513/5/052004

M3 - Article

SN - 1742-6588

VL - 513

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 5

M1 - 052004

ER -