Parallelizing a Real-Time 3D Finite Element Algorithm using CUDA: Limitations, Challenges and Opportunities

GTC2014 talk. See: http://on-demand-gtc.gputechconf.com/gtc-quicklink/jlNmC8 for video recording and .pdfLearn about the challenges of parallelizing a Finite Element problem using the Total Lagrangian Explicit Dynamic formulation. We examine the algorithm and perform a detailed analysis of the performance limiting factors of parallelization using CUDA. Potential optimization benefits are elucidated in terms of register usage thresholds and other factors for better performance. Results of a larger usability study are presented on a simple problem examining single/double precision tradeoff on a wide range of GPUs and problem sizes. Discover the impact that real-time FE can bring to the intraoperative surgical setting with in-the-loop computation facilitating surgical robotics. - See more at: http://on-demand-gtc.gputechconf.com/gtcnew/on-demand-gtc.php?searchByKeyword=strbac&searchItems=&sessionTopic=&sessionEvent=&sessionYear=&sessionFormat=&submit=&select=#sthash.WaPJ8iEL.Vsg9T09T.dpufstatus: publishe