Dhrystone: a synthetic systems programming benchmark
Communications of the ACM
The benefits of event: driven energy accounting in power-sensitive systems
EW 9 Proceedings of the 9th workshop on ACM SIGOPS European workshop: beyond the PC: new challenges for the operating system
Temperature-aware microarchitecture: Modeling and implementation
ACM Transactions on Architecture and Code Optimization (TACO)
Power emulation: a new paradigm for power estimation
Proceedings of the 42nd annual Design Automation Conference
Power prediction for intel XScale® processors using performance monitoring unit events
ISLPED '05 Proceedings of the 2005 international symposium on Low power electronics and design
A fast HW/SW FPGA-based thermal emulation framework for multi-processor system-on-chip
Proceedings of the 43rd annual Design Automation Conference
Balancing power consumption in multiprocessor systems
Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006
Accurate on-line prediction of processor and memoryenergy usage under voltage scaling
EMSOFT '07 Proceedings of the 7th ACM & IEEE international conference on Embedded software
Low-Impact Processor for Dynamic Runtime Power Management
IEEE Design & Test
Full-system chip multiprocessor power evaluations using FPGA-based emulation
Proceedings of the 13th international symposium on Low power electronics and design
System-level power estimation using an on-chip bus performance monitoring unit
Proceedings of the 2008 IEEE/ACM International Conference on Computer-Aided Design
An emulation-based real-time power profiling unit for embedded software
SAMOS'09 Proceedings of the 9th international conference on Systems, architectures, modeling and simulation
Real-time performance analysis of multiprocessor systems with shared memory
ACM Transactions on Embedded Computing Systems (TECS)
IDAMC: A Many-Core Platform with Run-Time Monitoring for Mixed-Criticality
HASE '12 Proceedings of the 2012 IEEE 14th International Symposium on High-Assurance Systems Engineering
Hi-index | 0.00 |
Mixed-critical applications on a many-core platform have to be sufficiently independent to be certified separately. This does not only include independence in terms of time and space, but also in terms of power consumption as the available energy for a many-core system has to be shared by all running applications. Increased power consumption of one application may reduce the available energy for other applications or the reliability and lifetime of the complete chip. This paper presents a monitoring and control mechanism based on event-driven power estimation to isolate dynamic power consumption of mixed-critical applications running on a many-core platform. Isolating dynamic power consumption significantly reduces safety requirements for lower critical applications and therefore overall certification costs, making many-core systems more attractive for safety-critical applications.