High performance dynamic lock-free hash tables and list-based sets
By Maged M. Michael. ACM Symposium on Parallelism in Algorithms and Architectures, 2002
469 citations recorded by the source corpus.
Subfields: Computer Networks and Communications
View Paper: https://www.semanticscholar.org/paper/fb47306b9007a2a901f7214e2a9b2005f20ed4b7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
- T. Harris
- Keir Fraser
- Maged M. Michael
- Maurice Herlihy
- Eric Koskinen
- Carl Kingsford
- Guillaume Marçais
- Liang Luo
Citations in the corpus
- A fast, lock-free approach for efficient parallel counting of occurrences of k-mers (2011, background): “However, this strategy is extremely slow and implementing multithreaded access to the hash table via standard locking mechanisms results in slower performance than a singlethreaded implementation (Michael and Scott, 1996; Purcell and Harris, 2005).”
- Hekaton: SQL server's memory-optimized OLTP engine (2013, unknown): “Hekaton supports two types of indexes: hash indexes which are implemented using lockfree hash tables [13] and range indexes which are implemented using Bw-trees, a novel lock-free version of B-trees [10].”
- Concurrent programming without locks (2007, methodology): “Schemes like SMR or pass-the-buck would be necessary for prompt memory reuse in workloads with more threads than processors.”
- Transactional boosting: a methodology for highly-concurrent transactional objects (2008, background): “All critical sections are short-lived, and multiple threads can traverse the list concurrently.”
- Hazard pointers: safe memory reclamation for lock-free objects (2004, methodology): “, [11], [9], [23], [28], [21], [26], [4], [16], [7], [6], [18], for the purposes”
- GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks (2017, background): “Although we can replace existing codes with lock-based designs and enable SLE/TM optimizations, the performance would still be worse than the lock-free design because of the overhead of lock/unlock/SLE operations [52], [53].”
- IncBricks: Toward In-Network Computation with an In-Network Cache (2017, background): “The hash table uses lock-free operations to access and modify its state [26, 37].”