On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework

Rafaelle Montella; Giulio Giunta; Giuliano Laccetti; Marco Lapegna; Carlo Palmieri; Carmine Ferraro; Valentina Pelliccia; Cheol-Ho Hong; Ivor Spence; Dimitrios Nikolopoulos

doi:10.1007/s10766-016-0462-1

On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework

Rafaelle Montella, Giulio Giunta, Giuliano Laccetti, Marco Lapegna, Carlo Palmieri, Carmine Ferraro, Valentina Pelliccia, Cheol-Ho Hong, Ivor Spence, Dimitrios Nikolopoulos

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

30 Citations (Scopus)

1371 Downloads (Pure)

Abstract

The astonishing development of diverse and different hardware platforms is twofold: on one side, the challenge for the exascale performance for big data processing and management; on the other side, the mobile and embedded devices for data collection and human machine interaction. This drove to a highly hierarchical evolution of programming models. GVirtuS is the general virtualization system developed in 2009 and firstly introduced in 2010 enabling a completely transparent layer among GPUs and VMs. This paper shows the latest achievements and developments of GVirtuS, now supporting CUDA 6.5, memory management and scheduling. Thanks to the new and improved remoting capabilities, GVirtus now enables GPU sharing among physical and virtual machines based on x86 and ARM CPUs on local workstations,computing clusters and distributed cloud appliances.

Original language	English
Pages (from-to)	1142-1163
Number of pages	22
Journal	International Journal of Parallel Programming
Volume	45
Issue number	5
Early online date	13 Oct 2016
DOIs	https://doi.org/10.1007/s10766-016-0462-1
Publication status	Published - Oct 2017

Access to Document

10.1007/s10766-016-0462-1Licence: Unspecified

On the Virtualization of CUDA based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework
© 2016 Springer Verlag. The final publication is available at Springer via http://dx.doi.org/ 10.1007/s10766-016-0462-1
Accepted author manuscript, 9.37 MBLicence: Unspecified

Cite this

@article{4c301beebbe44c639ce89151f71947d6,

title = "On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework",

abstract = "The astonishing development of diverse and different hardware platforms is twofold: on one side, the challenge for the exascale performance for big data processing and management; on the other side, the mobile and embedded devices for data collection and human machine interaction. This drove to a highly hierarchical evolution of programming models. GVirtuS is the general virtualization system developed in 2009 and firstly introduced in 2010 enabling a completely transparent layer among GPUs and VMs. This paper shows the latest achievements and developments of GVirtuS, now supporting CUDA 6.5, memory management and scheduling. Thanks to the new and improved remoting capabilities, GVirtus now enables GPU sharing among physical and virtual machines based on x86 and ARM CPUs on local workstations,computing clusters and distributed cloud appliances.",

author = "Rafaelle Montella and Giulio Giunta and Giuliano Laccetti and Marco Lapegna and Carlo Palmieri and Carmine Ferraro and Valentina Pelliccia and Cheol-Ho Hong and Ivor Spence and Dimitrios Nikolopoulos",

year = "2017",

month = oct,

doi = "10.1007/s10766-016-0462-1",

language = "English",

volume = "45",

pages = "1142--1163",

journal = "International Journal of Parallel Programming",

issn = "0885-7458",

publisher = "Springer New York",

number = "5",

}

TY - JOUR

T1 - On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework

AU - Montella, Rafaelle

AU - Giunta, Giulio

AU - Laccetti, Giuliano

AU - Lapegna, Marco

AU - Palmieri, Carlo

AU - Ferraro, Carmine

AU - Pelliccia, Valentina

AU - Hong, Cheol-Ho

AU - Spence, Ivor

AU - Nikolopoulos, Dimitrios

PY - 2017/10

Y1 - 2017/10

N2 - The astonishing development of diverse and different hardware platforms is twofold: on one side, the challenge for the exascale performance for big data processing and management; on the other side, the mobile and embedded devices for data collection and human machine interaction. This drove to a highly hierarchical evolution of programming models. GVirtuS is the general virtualization system developed in 2009 and firstly introduced in 2010 enabling a completely transparent layer among GPUs and VMs. This paper shows the latest achievements and developments of GVirtuS, now supporting CUDA 6.5, memory management and scheduling. Thanks to the new and improved remoting capabilities, GVirtus now enables GPU sharing among physical and virtual machines based on x86 and ARM CPUs on local workstations,computing clusters and distributed cloud appliances.

AB - The astonishing development of diverse and different hardware platforms is twofold: on one side, the challenge for the exascale performance for big data processing and management; on the other side, the mobile and embedded devices for data collection and human machine interaction. This drove to a highly hierarchical evolution of programming models. GVirtuS is the general virtualization system developed in 2009 and firstly introduced in 2010 enabling a completely transparent layer among GPUs and VMs. This paper shows the latest achievements and developments of GVirtuS, now supporting CUDA 6.5, memory management and scheduling. Thanks to the new and improved remoting capabilities, GVirtus now enables GPU sharing among physical and virtual machines based on x86 and ARM CPUs on local workstations,computing clusters and distributed cloud appliances.

UR - https://link.springer.com/article/10.1007/s10766-016-0462-1

U2 - 10.1007/s10766-016-0462-1

DO - 10.1007/s10766-016-0462-1

M3 - Article

SN - 0885-7458

VL - 45

SP - 1142

EP - 1163

JO - International Journal of Parallel Programming

JF - International Journal of Parallel Programming

IS - 5

ER -

On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework

Abstract

Access to Document

Other files and links

Fingerprint

R6933CSC: Heterogeneous Secure Multi-Level Remote Acceleration Service for Low-Power Integrated System and Devices

Ivor Spence

Cite this

On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS Framework

Abstract

Access to Document

Other files and links

Fingerprint

Projects

R6933CSC: Heterogeneous Secure Multi-Level Remote Acceleration Service for Low-Power Integrated System and Devices

Profiles

Ivor Spence

Cite this