• multithreading
• parallel computing

The thesis describes an efficient implementation of a subset of the NPB algorithms for the multicore architecture with the FastFlow framework. The NPB is a specification of numeric benchmarks to compare different environments and implementations. FastFlow is a framework, targeted to shared memory systems, to sustain parallel algorithms based on structured parallel programming. Starting from the NPB specification, the thesis selects a subset of the NPB algorithms and discerns an efficient implementation for both the sequential and parallel algorithms, through FastFlow. Finally, experiments on state of the art multicore architectures compare the derived code with the reference implementation, provided by the NPB authors.