| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Acceleration of FMU Co-Simulation On Multi-core Architectures
Abstract : The design of cyber-physical systems is a complex process and relies on the simulation of the system behavior before its deployment. Co-simulation allows system designers to simulate a whole system composed of a number of interconnected subsystems. Traditionally, these models are modeled by experts of different fields using different tools, and then integrated into one environment to perform simulation at the system-level. This results in complex and heavy co-simulations and requires adequate solutions and tools in order to reduce the execution time. Unfortunately, most modeling tools perform only mono-core simulations and do not take advantage of the omnipresent multi-core processors. This paper addresses the problem of efficient parallelization of co-simulations. It presents a multi-core scheduling heuris-tic for parallelizing FMI-compliant models on multi-core processors. The limitations of this heuristic are highlighted and two solutions for dealing with them are presented. The obtained speed-up using each of these solutions is illustrated and discussed for further improvements .
Cited literature [12 references]
https://hal.inria.fr/hal-01400033
Contributor : Yves Sorel <>
Submitted on : Monday, November 21, 2016 - 1:04:08 PM
Last modification on : Monday, October 12, 2020 - 10:30:12 AM
Long-term archiving on: : Monday, March 20, 2017 - 5:57:50 PM
Contributor : Yves Sorel <>
Submitted on : Monday, November 21, 2016 - 1:04:08 PM
Last modification on : Monday, October 12, 2020 - 10:30:12 AM
Long-term archiving on: : Monday, March 20, 2017 - 5:57:50 PM
File
confModelica2016.pdf
Files produced by the author(s)