Performance Models for Matrix Computations on Multicore Processors Using OpenMP

The matrix computations such as matrix-vector and matrix multiplication are very challenging computational kernels arising in scientific computing. In this paper, we study and evaluate a number of different data decomposition schemes for matrix computations on multicore architectures using OpenMP programming model. Further, in this work we propose a simple and fast analytical model to predict the performance of matrix computations by taking memory access costs into account and data access schemes that appear in many scientific applications.