A Multiple-FPGA parallel computing architecture for real-time simulation of soft-object deformation

Abstract

Hardware-based parallel computing is proposed for acceleration of finite-element (FE) analysis of linear elastic deformation models. An implementation of the Preconditioned Conjugate Gradient algorithm on N Field Programmable Gate Array (FPGA) devices solves the large linear system of equations arising from the FE discretization. The system employs a large number of customized fixed-point computing units with a high-throughput memory architecture. An implementation of this scalable architecture on four Altera EP3SE110 FPGA devices yields a peak performance of 604 Giga Operations per second. This enables haptic simulation of a 3-dimensional deformable object of 21000 elements at an update rate of 400Hz. ACM Reference Format:Behzad Mahdavikhah, Ramin Mafi, Shahin Sirouspour, and Nicola Nicolici. 2014. A multiple-FPGA parallel computing architecture for real-time simulation of soft-object deformation. ACM Trans. Embedd. Comput.

Simulação de inserção de agulha para treinamento de procedimento de anestesia odontológica.

“…As medidas predictive validity e concurrent validity não foram adotadas.Para finalizar, com relaçãoà validação sob aspectos computacionais, o teste estatístico de regressão linear foi observado em 4,8% dos artigos, empregado para comparação entre métodos de Elementos Finitos Linear e Não Linear (LADJAL; HANUS; FERREIRA, 2013) (LADJAL; HANUS; FERREIRA, 2011), além da comparação de trajetórias(NISKY et al, 2011). Os testes estatísticos média e desvio-padrão foram adotados para análise de erros de processamento(MAHDAVIKHAH et al, 2014) (ZHANG et al, 2010b (MAH- DAVIKHAH et al, 2010) (VILLARD P.F.AND VIDAL et al, 2009).…”