Massive Parallelization of the Conjugated Gradients Algorithm applied to the reconstruction of Electrical Impedance Tomography Images

• Grant number: 11/01194-8
• Support type: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): April 01, 2011
• Effective date (End): March 31, 2012
• Field of knowledge: Engineering - Biomedical Engineering - Medical Engineering
• Principal Investigator: Thiago de Castro Martins
• Grantee: Jacqueline de Miranda Kian
• Home Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

The reconstruction of Electrical Impedance Tomography Images can be approached as an optimization problem, where one minimizes the differences between observed data and a syntetic model, simulated using the Finite Element Method (FEM). Under this approach, the bulk of computational costs is in spent solving the linear systems produced by the FEM. This project's goal is to research techniques for massive parallelization of the Conjugated Gradients Algorithm to solve such systems, considering the specifics of the studied problem.