Leveraging parallel computing in multibody dynamics

At a time when sequential computing is limited to marginal year-to-year gains in speed, multi- and many-core architectures provide teraflop-grade performance to cost-conscious users. The ongoing shift to parallel computing spurs new research into solution methods that emphasize algorithmic concurrency. It also provides an opportunity to revisit complex real-life applications whose solutions have been until recently infeasible due to prohibitively heavy computational burdens. This paper concentrates on the use of commodity parallel computing in the field of multibody dynamics by illustrating how many-body frictional-contact dynamics, fluid–solid interaction analysis, and proximity computation have benefited from parallel computing. Preliminary results are encouraging and show one to two orders of magnitude reductions in simulation times. A set of open questions and final remarks round up the contribution.