Parallel computing, benchmarking and ATLAS software on ARM

This thesis explores the use of the ARM architecture in high energy physics computing. ARM processors are predominantly found in smartphones and mobile tablets. Results from benchmarks which were performed on the armv7l architecture are presented. These provide qualitative data as well as confirmation that specialized high energy physics software does run on ARM. This thesis presents the first ever port of the ATLAS software stack to the ARM architecture, as well as the issues that ensued. A new framework, ANA, is introduced which facilitates the compilation of the ATLAS software stack on ARM.

Grantor dc:publisher.institution

Department of Physics

Year dc:date.issued

2015

Author dc:creator

• Smith, Joshua Wyatt

Advisor dc:contributor.advisor

• Hamilton, Andrew

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/11427/20009

OAI identifier oai:identifier

oai:open.uct.ac.za:11427/20009