The development of multi-core processor makes the parallelization of traditional sequential algorithms increasingly important. Meanwhile, transactional memory serves a good parallel programming model. This paper takes...
详细信息
The development of multi-core processor makes the parallelization of traditional sequential algorithms increasingly important. Meanwhile, transactional memory serves a good parallel programming model. This paper takes the advantage of software transactional memory to parallelize the Multi-Exit Asymmetric Adaboost algorithm for face detection. The parallel version is evaluated on three different implementations of software transactional memory. The experiment results show that the transactional memory based parallelization outperforms the traditional lock based approach. A speedup of nearly seven is achieved on a eight-core machine on an eight-core system.
In this paper, we describe a consistency control algorithm for managing replicated files in the face of network partitioning due to node or communication link failures. It adopts a pessimistic approach in that mutual ...
详细信息
In this paper, we describe a consistency control algorithm for managing replicated files in the face of network partitioning due to node or communication link failures. It adopts a pessimistic approach in that mutual consistency among copies of a file is maintained by permitting files to be accessed only in a single partition at any given time. Our algorithm simplifies the Davcev-Burkhard 'dynamic voting' algorithm and also improves its availability by adding the notion of 'linearly ordered copies.' We also give a proof that any pessimistic algorithm with fresh reads is one-copy serializable. [ABSTRACT FROM AUTHOR]
暂无评论