CBPQ: High Performance Lock-Free Priority Queue

Priority queues are an important algorithmic component and are ubiquitous in systems and software. With the rapid deployment of parallel platforms, concurrent versions of priority queues are becoming increasingly important. In this paper, we present a novel concurrent lock-free linearizable algorithm for priority queues that scales significantly better than all known (lock-based or lock-free) priority queues. Our design employs several techniques to obtain its advantages including lock-free chunks, the use of the efficient fetchand-increment atomic instruction, and elimination. Measurements under high contention demonstrate performance improvement by up to a factor of 1.8 over existing approaches.