Pedro Carvalho Moreno

Abstract

Abstract
Lock-free implementation techniques are known to improve the overall throughput of concurrent data structures. A hash map is an important data structure used to organize information that must be accessed frequently. A key role of a hash map is the ability to balance workloads by dynamically adjusting its internal data structures in order to provide the fastest possible access to the information. This work extends a previous lock-free hash map design to also support lock-free compression. The main goal is to significantly reduce the depth of the internal hash levels within the hash map, in order to minimize cache misses and increase the overall throughput. To materialize our design, we redesigned the existent search, insert, remove and expand operations in order to maintain the lock-freedom property of the whole design. Experimental results show that lock-free compression effectively improves the search operation and, in doing so, it outperforms the previous design, which was already quite competitive when compared against the concurrent hash map design supported by Intel. © Springer Nature Switzerland AG 2020.

Abstract
Hash tries are a trie-based data structure with nearly ideal characteristics for the implementation of hash maps. Starting from a particular lock-free hash map data structure, named Lock-Free Hash Tries (LFHT), we focus on solving the problem of memory reclamation without losing the lockfreedom property. We propose an approach that explores the characteristics of the LFHT structure in order to achieve efficient memory reclamation with low and well-defined memory bounds. Experimental results show that our approach obtains better results when compared with other state-of-the-art memory reclamation methods and provides a competitive and scalable hash map implementation, if compared to lock-based implementations. © 2019 IEEE.