Task-Parallel Programming on NUMA Architectures

The multicore era has led to a renaissance of shared memory parallel programming models. Moreover, the introduction of task-level parallelization raises the level of abstraction compared to thread-centric expression of parallelism. However, tasks might exhibit poor performance on NUMA systems if locality cannot be controlled and non-local data is accessed. This work investigates various approaches to express task-parallelism using the OpenMP tasking model, from a programmer's point of view. We describe and compare task creation strategies and devise methods to preserve locality on NUMA architectures while optimizing the degree of parallelism. Our proposals are evaluated on reasonably large NUMA systems with both important application kernels as well as real-world simulation codes.