Safety-related challenges and opportunities for GPUs in the automotive domain

GPUs have been shown to cover the computing performance needs of autonomous driving (AD) systems. However, since the GPUs used for AD build on designs for the mainstream market, they may lack fundamental properties for correct operation under automotive's safety regulations. In this paper, we a...

Descripción completa

Detalles Bibliográficos
Autores: Alcaide Portet, Sergi|||0000-0001-8561-7795, Kosmidis, Leonidas, Tabani, Hamid, Hernández Luz, Carles, Abella Ferrer, Jaume|||0000-0001-7951-4028, Cazorla Almeida, Francisco Javier
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/166388
Acceso en línea:https://hdl.handle.net/2117/166388
https://dx.doi.org/10.1109/MM.2018.2873870
Access Level:acceso abierto
Palabra clave:High performance computing
Traffic engineering
Graphics processing units
Safety
ISO Standards
Hardware acceleration
Automotive engineering
Redundancy
Unmanned autonomous vehicles
Supercomputadors
Enginyeria del trànsit
Unitats de processament gràfic
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
Descripción
Sumario:GPUs have been shown to cover the computing performance needs of autonomous driving (AD) systems. However, since the GPUs used for AD build on designs for the mainstream market, they may lack fundamental properties for correct operation under automotive's safety regulations. In this paper, we analyze some of the main challenges in hardware and software design to embrace GPUs as the reference computing solution for AD, with the emphasis in ISO 26262 functional safety requirements.