Proceedings of the fourteenth annual ACM symposium on Principles of distributed computing
Fixed-priority preemptive multiprocessor scheduling: to partition or not to partition
RTCSA '00 Proceedings of the Seventh International Conference on Real-Time Systems and Applications
Beyond Ada 2005: allocating tasks to processors in SMP systems
IRTAW '07 Proceedings of the 13th international workshop on Real-time Ada
Suggestions for stream based parallel systems in Ada
IRTAW '07 Proceedings of the 13th international workshop on Real-time Ada
Sporadic Multiprocessor Scheduling with Few Preemptions
ECRTS '08 Proceedings of the 2008 Euromicro Conference on Real-Time Systems
Portioned EDF-based scheduling on multiprocessors
EMSOFT '08 Proceedings of the 8th ACM international conference on Embedded software
Ada and cc-NUMA architectures what can be achieved with Ada 2005?
ACM SIGAda Ada Letters
Support for multiprocessor platforms
ACM SIGAda Ada Letters
Going real-time with Ada 2012 and GNAT
ACM SIGAda Ada Letters
Session summary: multiprocessor issues, part 1
ACM SIGAda Ada Letters
Hi-index | 0.00 |
Multiprocessor platforms are becoming the norm for more powerful embedded real-time systems. Although Ada allows its tasks to be executed on such platforms it provides no explicit support that allows programmers to map tasks to processors. If Ada is going to be an effective language for multiprocessor systems then it needs to address the mapping issue that will allow the programmer to express their requirements for task to processor affinity. A number of different mapping and scheduling approaches are advocated in the scheduling literature. The primitives in the language should allow these schemes to be directly supported. In this paper we propose a minimum set of such primitives, with the aim of initiating a debate that will lead to an agreed language change that can be accepted within the Ada community.