Matrix factorization is known to be an effective method for recommender systems that are given only the ratings from users to items. Currently, stochastic gradient (SG) method is one of the most popular algorithms for...
详细信息
Matrix factorization is known to be an effective method for recommender systems that are given only the ratings from users to items. Currently, stochastic gradient (SG) method is one of the most popular algorithms for matrix factorization. However, as a sequential approach, SG is difficult to be parallelized for handling web-scale problems. In this article, we develop a fast parallel SG method, FPSG, for sharedmemory systems. By dramatically reducing the cache-miss rate and carefully addressing the load balance of threads, FPSG is more efficient than state-of-the-art parallel algorithms for matrix factorization.
When a process attempts to acquire a mutex lock, it may be forced to wait if another process currently holds the lock. In certain applications, such as real-time operating systems and databases, indefinite waiting can...
详细信息
ISBN:
(纸本)9783642336515
When a process attempts to acquire a mutex lock, it may be forced to wait if another process currently holds the lock. In certain applications, such as real-time operating systems and databases, indefinite waiting can cause a process to miss an important deadline [19]. Hence, there has been research on designing abortable mutual exclusion locks, and fairly efficient algorithms of O(log n) RMR complexity have been discovered [11,14] (n denotes the number of processes for which the algorithm is designed). The abort feature is just as important for a reader-writer lock as it is for a mutual exclusion lock, but to the best of our knowledge there are currently no abortable reader-writer locks that are starvation-free. We show the surprising result that any abortable, starvation-free mutual exclusion algorithm of RMR complexity t(n) can be transformed into an abortable, starvation-free reader-writer exclusion algorithm of RMR complexity O(t(n)). Thus, we obtain the first abortable, starvation-free reader-writer exclusion algorithm of O(log n) RMR complexity. Our results apply to the Cache-Coherent (CC) model of multiprocessors.
暂无评论