Abstract

We present practical new algorithms for FIFO or priority-ordered spin locks on sharedmemory multiprocessors with an atomic swap instruction. Different versions of these queuing spin locks are designed for machines with coherent-cache and NUMA memory models. We include extensions to provide nested lock acquisition, conditional locking, timeout of lock requests, and preemption of waiters. These locks apply to both realtime and non-real-time parallel systems and we include a comparison of the traits of several lock schemes aimed at those environments. Our main technical contributions are our techniques and algorithms that provide tight control over lock grant order, use only the atomic swap instruction, use at most one (local only) spin for lock acquisition and no spinning for lock release, and need only O(L + P ) space on either a coherentcache or NUMA machine. This research was supported in part by the National Science Foundation under grant number CCR9200858 and by a Nationa...

Citations

597	Transactional Memory: Architectural Support for Lock-Free Data Structures. Digital Cambridge Research Lab - Herlihy, Moss - 1992
433	Algorithms for Scalable Synchronization on SharedMemory Multiprocessors - Mellor-Crummey, Scott - 1991
206	The performance of spin lock alternatives for shared-memory multiprocessors - Anderson - 1990
67	Fast mutual exclusion for uniprocessors - Bershad, Redell, et al.
15	Multiprocessor Synchronization Primitives with Priorities - Markatos - 1991
2	Graunke and Shreekant Thakkar. Synchronization Algorithms for Shared�Memory Mul� tiprocessors - Gary - 1990
2	Predictable Synchronization Mechanisms for Real-Time Systems - Molesky, Shen, et al. - 1990