A practical concurrent binary search tree

Bronson, Nathan; Casper, Jared; Chafi, Hassan; Olukotun, Kunle

doi:10.1145/1693453.1693488

Cited by 154 publications

(135 citation statements)

References 13 publications

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…Prior work has focused on deriving concurrent versions of unbalanced BSTs [16], self-balancing BSTs [9,12,13,19] and skip lists [14,20] [20] whereas Crain et al [14] propose a nonblocking skip list.…”

Section: Concurrent Algorithmsmentioning

confidence: 99%

“…To do deletions, we use the tombstone method [9]. Once the item is located in the tree, if it is a leaf, it is deleted, and if its parent is empty its parent is replaced by its remaining child; if it is a unary node, it is replaced by its only child; but if it has two children it is merely marked as empty, and left in the tree to guide future searches.…”

Section: Binary Search Trees and System Modelmentioning

confidence: 99%

“…We chose to implement and test the CB tree using the optimistic concurrency control technique of Bronson et al [9]. This technique handles synchronization of generic BST operations including traversals, insertion and deletion of nodes, and rotations.…”

Section: The Concurrent Cb Treementioning

confidence: 99%

“…An example of the former is the lockfree concurrent unbalanced BST implementation of Ellen et al [16]. Examples of the latter include balanced concurrent BSTs that rely on locking [9,19] and the transaction-friendly concurrent BST of Crain et al [12], in which a dedicated thread continuously scans the tree repairing balance rule violations. None of these solutions meets our goals: unbalanced BSTs provide no performance guarantees, and balanced BSTs do not prioritize popular items and hence do not provide optimal performance if the access pattern is skewed or changes over time.…”

Section: Introductionmentioning

confidence: 99%

“…Our implementation uses Bronson et al's [9] optimistic BST concurrency control technique. We compare our CB tree implementation with other sequential and concurrent implementations of other kinds of BSTs on real workloads and show that the CB tree has short access paths and excellent throughput.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

The CB tree: a practical concurrent self-adjusting search tree

et al. 2014

View full text Add to dashboard Cite

We present the CB tree, a counting-based selfadjusting binary search tree in which, as in splay trees, more-frequently accessed items move closer to the root. In a sequential execution, after m operations of which c(v) access item v, an access of v traverses a path of length O 1 + log m c(v) while doing few if any rotations. Unlike the original splay tree, in which each access moves the accessed item all the way to the root via a sequence of rotations, accesses in a CB tree do very few rotations, specifically O n + n log m n , during a sequence of m operations of which n are insertions. This is o(1) (subconstant) amortized per operation if m n. We adapt the CB tree into a scalable concurrent self-adjusting BST. We show experimentally that the concurrent CB tree scales well because it, too, performs few rotations, and therefore self-adjusts without having rotations create a bottleneck. Our evaluation shows that the concurrent CB tree performs better than existing concurrent search trees A preliminary version of this on non-uniform access sequences derived from real workloads.

show abstract

Section: Concurrent Algorithmsmentioning

confidence: 99%

Section: Binary Search Trees and System Modelmentioning

confidence: 99%

Section: The Concurrent Cb Treementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The CB tree: a practical concurrent self-adjusting search tree

et al. 2014

View full text Add to dashboard Cite

show abstract

A concurrent van Emde Boas array as a fast and simple concurrent dynamic set alternative

Kułakowski

2013

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYIncreasing demand for computationally efficient algorithms and processors has turned the attention of researchers toward parallel and concurrent solutions. Because the frequency of contemporary processors cannot be tweaked infinitely, the only hopes for squeezing more performance from computers are parallel processing and parallel computation. The important part of every parallel solution is concurrent data structures, which allow multithread programming environments to be taken advantage of. In this article, a new concurrent dynamic set structure is proposed. It is based on the van Emde Boas trees concept, where on every node of a tree, an array of the node's children is stored. The structure is equipped with a simple but effective locking algorithm, which allows it to be used concurrently by any number of threads. The presented algorithm idea is accompanied by an experimental implementation written in JAVA 6. Preliminary tests prove that, especially for moderately larger data sets with a predominance of read operations, the concurrent van Emde Boas array proposed in this article may be a viable alternative for other structures providing a similar functionality.

show abstract

Relativistic red‐black trees

Howard

Walpole

2013

Concurrency and Computation

View full text Add to dashboard Cite

Operating system performance and scalability on sharedmemory many-core systems depends critically on efficient access to shared data structures. Scalability has proven difficult to achieve for many data structures. In this paper we present a novel and highly scalable concurrent red-black tree.Red-black trees are widely used in operating systems, but typically exhibit poor scalability. Our red-black tree has linear read scalability, uncontended read performance that is at least 25% faster than other known approaches, and deterministic lookup times for a given tree size, making it suitable for realtime applications.

show abstract

A practical concurrent binary search tree

Cited by 154 publications

References 13 publications

The CB tree: a practical concurrent self-adjusting search tree

The CB tree: a practical concurrent self-adjusting search tree

A concurrent van Emde Boas array as a fast and simple concurrent dynamic set alternative

Relativistic red‐black trees

Contact Info

Product

Resources

About