Computing on multi-core platform
Malvika Pimple, Shailesh R. Sathe · 2011
The ubiquity of multi-core processors in commodity computing systems has raised a significant programming challenge for their effective use. As multi-core processors with tens or hundreds of cores begin to proliferate, system optimization issues once faced by the high-performance computing (HPC) community will become important to all programmers. The focus of the multi-core programmer will be on productivity, portability as well as performance. We discuss in this paper mainly the performance issues involved in developing the software on the multi-core platform. This will help the developer in fine tuning his application on multi-core architecture. The paper studies a way to incorporate data locality problem into the parallel programming system using tiling approach coupled with OpenMP. The paper also shows that, there is a considerable performance enhancement with this approach when used in the algorithm.