Parallel Multisets Sorting Using Aperiodic Multi-round Distribution Strategy on Heterogeneous Multi-core Clusters

To sort efficiently Multisets in parallel on the heterogeneous multi-core clusters that the nodes have different amount of processing cores, different computing and communication capabilities and distinct size of main memory, a novel a periodic multi-round data distribution model is presented and a parallel sorting algorithm for Multisets is designed by using the characteristics of multi-threading technology and multi-level caches on multi-core architectures. The first round scheduling assigns data blocks into the slave multi-core nodes according to the given distribution order, and the other rounds scheduling will distribute data blocks into the slave multi-core nodes by First Request First Distribution (FRFD) strategy to ensure that each slave multi-core node can receive the next required data block before it has sorting the current data block in its own main memory. The experimental results on the heterogeneous cluster with multi-core computers show that the presented parallel sorting Multisets algorithm is efficient and it obtains good speedup and scalability.