Predictable interprocessor synchronization and fast interrupt response are important for real-time systems constructed using asymmetric shared-memory multiprocessors. This paper points out the problem that existing spin lock algorithms cannot satisfy both requirements at the same time, and proposes a new algorithm to solve this problem. The algorithm, an extension of queueing spin locks modified to be preemptable for servicing interrupts, can give an upper bound on the time to acquire and release an interprocessor lock while achieving fast response to interrupt requests. The effectiveness of the algorithm is demonstrated through performance evaluation. 1 Introduction Requirements for large-scale and high performance real-time systems are i...
Spin locks are task synchronization mechanism used to provide mutual exclusion to shared software re...
Reader preference, writer preference, and task-fair reader-writer locks are shown to cause undue blo...
With the proliferation of multicore platforms, the embedded systems world has shifted more and more ...
Synchronization primitives for large scale multiprocessors need to provide low latency and low conte...
Various approaches can be utilized upon resource locking for mutually exclusive resource access in m...
Queue-based spinlocks allow programs with busy-wait synchronization to scale to very large multiproc...
Queue-based spin locks allow programs with busy-wait synchronization to scale to very large multipro...
Support for exclusive access to shared (global) resources is instrumental in the context of embedded...
Link to published version: http://portal.acm.org/ft_gateway.cfm?id=379566&type=pdf&coll=portal&dl=AC...
Reactive spin-lock algorithms that can automatically adapt to contention variation on the lock have ...
Busy-wait techniques are heavily used for mutual exclusion and barrier synchronization in shared-mem...
Queue-based spin locks allow programs with busy-wait syn-chronization to scale to very large multipr...
Busy-wait techniques are heavily used for mutual exclusion and barrier synchronization in shared-mem...
Large-scale shared-memory multiprocessors typically have long latencies for remote data accesses. A ...
Reactive spin-lock algorithms that can automatically adapt to contention variation on the lock have ...
Spin locks are task synchronization mechanism used to provide mutual exclusion to shared software re...
Reader preference, writer preference, and task-fair reader-writer locks are shown to cause undue blo...
With the proliferation of multicore platforms, the embedded systems world has shifted more and more ...
Synchronization primitives for large scale multiprocessors need to provide low latency and low conte...
Various approaches can be utilized upon resource locking for mutually exclusive resource access in m...
Queue-based spinlocks allow programs with busy-wait synchronization to scale to very large multiproc...
Queue-based spin locks allow programs with busy-wait synchronization to scale to very large multipro...
Support for exclusive access to shared (global) resources is instrumental in the context of embedded...
Link to published version: http://portal.acm.org/ft_gateway.cfm?id=379566&type=pdf&coll=portal&dl=AC...
Reactive spin-lock algorithms that can automatically adapt to contention variation on the lock have ...
Busy-wait techniques are heavily used for mutual exclusion and barrier synchronization in shared-mem...
Queue-based spin locks allow programs with busy-wait syn-chronization to scale to very large multipr...
Busy-wait techniques are heavily used for mutual exclusion and barrier synchronization in shared-mem...
Large-scale shared-memory multiprocessors typically have long latencies for remote data accesses. A ...
Reactive spin-lock algorithms that can automatically adapt to contention variation on the lock have ...
Spin locks are task synchronization mechanism used to provide mutual exclusion to shared software re...
Reader preference, writer preference, and task-fair reader-writer locks are shown to cause undue blo...
With the proliferation of multicore platforms, the embedded systems world has shifted more and more ...