VADI

GPU Virtualization for an Automotive Platform

Chiyoung Lee, Se Won Kim, Hyuck Yoo

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Modern vehicles are evolving with more electronic components than ever before (In this paper, 'vehicle' means 'automotive vehicle.' It is also equal to 'car.') One notable example is graphical processing unit (GPU), which is a key component to implement a digital cluster. To implement the digital cluster that displays all the meters (such as speed and fuel gauge) together with infotainment services (such as navigator and browser), the GPU needs to be virtualized; however, GPU virtualization for the digital cluster has not been addressed yet. This paper presents a Virtualized Automotive DIsplay (VADI) system to virtualize a GPU and its attached display device. VADI manages two execution domains: one for the automotive control software and the other for the in-vehicle infotainment (IVI) software. Through GPU virtualization, VADI provides GPU rendering to both execution domains, and it simultaneously displays their images on a digital cluster. In addition, VADI isolates GPU from the IVI software in order to protect it from potential failures of the IVI software. We implement VADI with Vivante GC2000 GPU and perform experiments to ensure requirements of International Standard Organization (ISO) safety standards. The results show that VADI guarantees 30 frames per second (fps), which is the minimum frame rate for digital cluster mandated by ISO safety standards even with the failure of the IVI software. It also achieves 60 fps in a synthetic workload.

Original languageEnglish
Article number7359144
Pages (from-to)277-290
Number of pages14
JournalIEEE Transactions on Industrial Informatics
Volume12
Issue number1
DOIs
Publication statusPublished - 2016 Feb 1

Fingerprint

Display devices
Processing
Fuel gages
Virtualization
Railroad cars
Experiments

Keywords

  • Automotive virtualization
  • Device isolation
  • Driver information systems
  • GPU Virtualization
  • Road vehicle software

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications
  • Information Systems

Cite this

VADI : GPU Virtualization for an Automotive Platform. / Lee, Chiyoung; Kim, Se Won; Yoo, Hyuck.

In: IEEE Transactions on Industrial Informatics, Vol. 12, No. 1, 7359144, 01.02.2016, p. 277-290.

Research output: Contribution to journalArticle

Lee, Chiyoung ; Kim, Se Won ; Yoo, Hyuck. / VADI : GPU Virtualization for an Automotive Platform. In: IEEE Transactions on Industrial Informatics. 2016 ; Vol. 12, No. 1. pp. 277-290.
@article{9b724a35d46c49778ff3c75b7f22fcf4,
title = "VADI: GPU Virtualization for an Automotive Platform",
abstract = "Modern vehicles are evolving with more electronic components than ever before (In this paper, 'vehicle' means 'automotive vehicle.' It is also equal to 'car.') One notable example is graphical processing unit (GPU), which is a key component to implement a digital cluster. To implement the digital cluster that displays all the meters (such as speed and fuel gauge) together with infotainment services (such as navigator and browser), the GPU needs to be virtualized; however, GPU virtualization for the digital cluster has not been addressed yet. This paper presents a Virtualized Automotive DIsplay (VADI) system to virtualize a GPU and its attached display device. VADI manages two execution domains: one for the automotive control software and the other for the in-vehicle infotainment (IVI) software. Through GPU virtualization, VADI provides GPU rendering to both execution domains, and it simultaneously displays their images on a digital cluster. In addition, VADI isolates GPU from the IVI software in order to protect it from potential failures of the IVI software. We implement VADI with Vivante GC2000 GPU and perform experiments to ensure requirements of International Standard Organization (ISO) safety standards. The results show that VADI guarantees 30 frames per second (fps), which is the minimum frame rate for digital cluster mandated by ISO safety standards even with the failure of the IVI software. It also achieves 60 fps in a synthetic workload.",
keywords = "Automotive virtualization, Device isolation, Driver information systems, GPU Virtualization, Road vehicle software",
author = "Chiyoung Lee and Kim, {Se Won} and Hyuck Yoo",
year = "2016",
month = "2",
day = "1",
doi = "10.1109/TII.2015.2509441",
language = "English",
volume = "12",
pages = "277--290",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - VADI

T2 - GPU Virtualization for an Automotive Platform

AU - Lee, Chiyoung

AU - Kim, Se Won

AU - Yoo, Hyuck

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Modern vehicles are evolving with more electronic components than ever before (In this paper, 'vehicle' means 'automotive vehicle.' It is also equal to 'car.') One notable example is graphical processing unit (GPU), which is a key component to implement a digital cluster. To implement the digital cluster that displays all the meters (such as speed and fuel gauge) together with infotainment services (such as navigator and browser), the GPU needs to be virtualized; however, GPU virtualization for the digital cluster has not been addressed yet. This paper presents a Virtualized Automotive DIsplay (VADI) system to virtualize a GPU and its attached display device. VADI manages two execution domains: one for the automotive control software and the other for the in-vehicle infotainment (IVI) software. Through GPU virtualization, VADI provides GPU rendering to both execution domains, and it simultaneously displays their images on a digital cluster. In addition, VADI isolates GPU from the IVI software in order to protect it from potential failures of the IVI software. We implement VADI with Vivante GC2000 GPU and perform experiments to ensure requirements of International Standard Organization (ISO) safety standards. The results show that VADI guarantees 30 frames per second (fps), which is the minimum frame rate for digital cluster mandated by ISO safety standards even with the failure of the IVI software. It also achieves 60 fps in a synthetic workload.

AB - Modern vehicles are evolving with more electronic components than ever before (In this paper, 'vehicle' means 'automotive vehicle.' It is also equal to 'car.') One notable example is graphical processing unit (GPU), which is a key component to implement a digital cluster. To implement the digital cluster that displays all the meters (such as speed and fuel gauge) together with infotainment services (such as navigator and browser), the GPU needs to be virtualized; however, GPU virtualization for the digital cluster has not been addressed yet. This paper presents a Virtualized Automotive DIsplay (VADI) system to virtualize a GPU and its attached display device. VADI manages two execution domains: one for the automotive control software and the other for the in-vehicle infotainment (IVI) software. Through GPU virtualization, VADI provides GPU rendering to both execution domains, and it simultaneously displays their images on a digital cluster. In addition, VADI isolates GPU from the IVI software in order to protect it from potential failures of the IVI software. We implement VADI with Vivante GC2000 GPU and perform experiments to ensure requirements of International Standard Organization (ISO) safety standards. The results show that VADI guarantees 30 frames per second (fps), which is the minimum frame rate for digital cluster mandated by ISO safety standards even with the failure of the IVI software. It also achieves 60 fps in a synthetic workload.

KW - Automotive virtualization

KW - Device isolation

KW - Driver information systems

KW - GPU Virtualization

KW - Road vehicle software

UR - http://www.scopus.com/inward/record.url?scp=84962521288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962521288&partnerID=8YFLogxK

U2 - 10.1109/TII.2015.2509441

DO - 10.1109/TII.2015.2509441

M3 - Article

VL - 12

SP - 277

EP - 290

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 1

M1 - 7359144

ER -