Accessing shared resources in multicore systems is usually protected by a software locking mechanism, which itself is implemented through atomic operations. This can result in a large synchronization overhead, which, in the context of real-time systems, increases the worst-case execution time and may void a task set's schedulability. In this paper we present a hardware locking mechanism to reduce the synchronization overhead. The solution is implemented for the chip-multiprocessor version of the Java Optimized Processor in the context of safety-critical Java. The implementation is compared to a software solution. The performance and the hardware cost are evaluated.
|Title of host publication||Proceedings of the 11th International Workshop on Java Technologies for Real-time and Embedded Systems|
|Publisher||Association for Computing Machinery|
|Publication status||Published - 2013|
|Event||11th International Workshop on Java Technologies for Real-time and Embedded Systems (JTRES 2013) - Karlsruhe, Germany|
Duration: 9 Oct 2013 → 10 Oct 2013
|Conference||11th International Workshop on Java Technologies for Real-time and Embedded Systems (JTRES 2013)|
|Period||09/10/2013 → 10/10/2013|