CME342 - Parallel Methods in Numerical Analysis

Emphasis is on techniques for obtaining maximum parallelism in numerical algorithms, especially those occurring when solving matrix problems and partial differential equations, and the subsequent mapping onto the computer. Implementation issues on parallel computers. Topics: parallel architecture, programming models, matrix computations, FFT, fast multiple methods, domain decomposition, and graph partitioning. Prerequisite: CME 302 or 200/ME300A, or consent of instructor. Recommended: differential equations and advanced programming language such as C or C++. GERs: None