Topic
Transactional memory
About: Transactional memory is a research topic. Over the lifetime, 2365 publications have been published within this topic receiving 60818 citations.
Papers published on a yearly basis
Papers
More filters
••
09 Sep 2014TL;DR: The architecture and the programming abstractions provided by this framework are described and the performance of the Beehive framework is presented for several graph problems such as maximum flow, minimum weight spanning tree, graph coloring, and the PageRank algorithm.
Abstract: Beehive is a parallel programming framework designed for cluster-based computing environments in cloud data centers. It is specifically targeted for graph data analysis problems. The Beehive framework provides the abstraction of key-value based global object storage, which is maintained in memory of the cluster nodes. Its computation model is based on optimistic concurrency control in executing concurrent tasks as atomic transactions for harnessing amorphous parallelism in graph analysis problems. We describe here the architecture and the programming abstractions provided by this framework, and present the performance of the Beehive framework for several graph problems such as maximum flow, minimum weight spanning tree, graph coloring, and the PageRank algorithm.
4 citations
••
18 Apr 2016TL;DR: A broadly useful mechanism for supporting condition synchronization among transactions, which supports a number of linguistic constructs for coordinating transactions, and does so without introducing overhead on in-flight hardware transactions.
Abstract: Few transactional memory implementations allow for condition synchronization among transactions. The problems are many, most notably the lack of consensus about a single appropriate linguistic construct, and the lack of mechanisms that are compatible with hardware transactional memory. In this paper, we introduce a broadly useful mechanism for supporting condition synchronization among transactions. Our mechanism supports a number of linguistic constructs for coordinating transactions, and does so without introducing overhead on in-flight hardware transactions. Experiments show that our mechanisms work well, and that the diversity of linguistic constructs allows programmers to chose the technique that is best suited to a particular application.
4 citations
••
TL;DR: A machine learning-based approach that enables the dynamic selection of the best suited number of threads to be kept alive along specific phases of the execution of STM applications, depending on (variations of) the shared data access pattern is presented.
4 citations
••
TL;DR: This letter formally derive utilization based necessary and sufficient scheduling condition for a STM system using lazy conflict detection and derives the execution semantics of STM from the classical preemptive or nonpreemptive model.
Abstract: Software transactional memory (STM) is a transactional mechanism of controlling access to shared resources in memory. Recently, variants of STM with real-time support have been presented. Due to its abort-restart nature, the execution semantics of STM are different from the classical preemptive or nonpreemptive model. In this letter, we formally derive utilization based necessary and sufficient scheduling condition for a STM system using lazy conflict detection.
4 citations
•
30 Jan 2013
4 citations