Measuring and Improving the Performance of Cache-efficient Priority Queues in Dijkstra’s Algorithm

The priority queue is an useful data structure in computation. There currently exist many implementations of this data structure, including some that are cache-aware and some cache-oblivious. In this study, we compare the performance of several implementations of priority queues in Dijkstra’s Single Source Shortest Path algorithm. We compare high performance heaps, such as the 4ary Aligned Heap, Fast Binary Heap and Sequence Heap against in-house heap implementations, namely Buffer Heap and Auxiliary Buffer Heap, and against well-known implementations such as the textbook Binary Heap. We focus our analysis on the benefit of supporting decrease-key operations within the priority queue. Results indicate that graph density affect the relative performance of the different priority queues, and that using the Decrease-Key operation incurs unexpected performance hits. Furthermore, we will propose a parallel version of Buffer Heap which remains cache-oblivious and scales to a high level of parallelism.