
Embedded Multiprocessor Systems-on-Chip (MPSoCs) commonly run multiple applications at once. These applications may have different time criticalities, i.e. non real-time, soft real-time, and firm or hard real-time. Application-level composability is used to provide each application with its own virtual platform, such that each application may be developed, verified, and executed independently, given its virtual platform specification. Composability of functional and temporal properties has been demonstrated in previous work. In this paper, we extend composability to include power management, where each application can manage its energy usage independently. Each application receives an independent energy and/or power budget, which it can manage as it sees fit, with its own application-specific power-management policy. Time, energy, and power budgets allocated to each application ensure that its power-management policy cannot cause any interference to the functional, timing, and power behaviours of other applications. We implement our technique on an existing composable and predictable hardware platform (CompSoC), and extend its Real-Time Operating System (OS) with a power-management infrastructure. Applications use a power-management API to communicate with the OS that implements time, energy, and power budgets. We demonstrate the applicability of our techniques by running several concurrent applications with their own power managers on an FPGA prototype.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 14 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 10% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
