Extended Abstract: A Study of Red-Black SOR Parallelization Using Chapel, D and Go Languages

Successive over-relaxation (SOR) is an important iterative solver for solving linear systems. We present parallel implementations of the red-black SOR method using three modern programming languages, namely Chapel, D and Go. We employ the SOR method for solving a 2D steady-state heat conduction problem. We discuss the optimizations incorporated and the features of these languages which are crucial for improving the program performance. Experiments have been performed using 2, 4, and 8 threads for a 4096×4096 square grid and performance results are compared with serial execution. The analysis of results provides important insights into the working of SOR method. These results have been published in a journal paper and both serial and parallel sourcecode in each of three languages have been made available to the public [1, 2]. We discuss the SOR algorithm and Chapel [3] specific details here and refer to [1] for other details.