Thread-Locking Work Stealing under Parallel Data List
Jorge Buenabad-Chávez, Edgar F. Hernández-Ventura, Miguel Alfonso Castro-Garcia, José Luis Quiroz-Fabían, Graciela Román-Alonso, Daniel M. Yellin · Parallel and distributed computing and systems · 2011
In the context of processing data lists in parallel in a multicore platform, various threads share a workload, each using a list to get and insert the data items to be processed; and when a list becomes empty, the owner thread steals data items from another list — thus balancing the workload according to the processing capacity of each thread and transparently to the programmer.