Preemptive Scheduling of Real-Time Tasks on Multiprocessor Systems
Journal of the ACM (JACM)
Scheduling independent tasks to reduce mean finishing time
Communications of the ACM
The complexity of theorem-proving procedures
STOC '71 Proceedings of the third annual ACM symposium on Theory of computing
Polynomial complete scheduling problems
SOSP '73 Proceedings of the fourth ACM symposium on Operating system principles
Bounds on scheduling with limited resources
SOSP '73 Proceedings of the fourth ACM symposium on Operating system principles
A task-scheduling algorithm for a multiprogramming computer system
SOSP '73 Proceedings of the fourth ACM symposium on Operating system principles
Analysis of scheduling algorithms for a model of a multiprocessor computer system.
Analysis of scheduling algorithms for a model of a multiprocessor computer system.
An Algorithm to Design the Memory Configuration of a Computer Network
Journal of the ACM (JACM)
Deterministic Processor Scheduling
ACM Computing Surveys (CSUR)
Scheduling tasks with critical sections
ACM '77 Proceedings of the 1977 annual conference
Hi-index | 0.00 |
The analysis of multiprocessor scheduling strategies has been the focus of substantial research in recent years. Because of the inherent complexity of the general scheduling problem, many researchers have proposed simple mathematical models of computing systems and analyzed the worst-case performance bounds of heuristic scheduling algorithms. This paper presents the analysis of simple scheduling strategies on a model of a computer system with an arbitrary number of identical but independent processors each with a possibly different storage capacity. Most simple strategies are shown to be unattractive as the bound on their worst-case behavior increases without limit. However, two strategies are presented with worst-case bounds asymptotically approaching 2. In addition, if the system has a preemptive-resume feature, a simple optimal strategy exists that will produce minimal-length schedules for any given task set.