High Performance Computing

Welcome to High Performance Computing Practice using OpenMP, OpenMPI and CUDA.

Overview of the course can be found here.

OpenMP

Exercise 1: Parallelizing Matrix Addition and Vector Arithmetic using OpenMP [Code]

Exercise 2: Analyzing Performance of Matrix Multiplication Algorithms in OpenMP [Code] [Report]

Exercise 3: Analyzing Performance of Spatial-Domain Linear Filtering on Multi-Channel Images using OpenMP [Code] [Report]

Exercise 4: Parallelizing Computation of Maximum Among Elements of N Matrices using OpenMP [Code]

Project: SVM Learning Algorithm

OpenMP: Analyzing Parallelizability of the SVM Classification Algorithm using OpenMP [Code] [Report]

OpenMPI: Parallel Sequential Minimal Optimization (SMO) for Training of Support Vector Machines [Code] [Report]