Hybrid global/local search strategies for dynamic voltage scaling in embedded multiprocessors

Hardware/Software Codesign - Proceedings of the International Workshop

Volumn , Issue , 2001, Pages 243-248

  Bambha, N K ^a   Bhattacharyya, S S ^a   Teich, J ^a   Zitzler, E ^a  

^a UNIVERSITY OF MARYLAND   (United States)

Author keywords

Dynamic voltage scaling; Simulated heating

Indexed keywords

ALGORITHMS; CONSTRAINT THEORY; ELECTRIC POTENTIAL; EMBEDDED SYSTEMS; ENERGY UTILIZATION; GRAPH THEORY; PROGRAM PROCESSORS;

DYNAMIC VOLTAGE SCALING;

MULTIPROCESSING SYSTEMS;

EID: 0034828184     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/371636.371744     Document Type: Conference Paper

References (19)

1. A joint power/performance optimization technique for multiprocessor systems using a period graph construct
2. Design issues for dynamic voltage scaling
3. Low-power CMOS digital design
4. Register allocation and binding for low power
5. Faster maximum and minimum mean cycle algorithms for system-performance analysis
6. Simultaneous scheduling and binding for power minimization during microarchitecture synthesis
7. Optimizing global-local search hybrids
8. Microarchitectural synthesis of performance-constrained low-power VLSI designs
9. Multi-objective genetic local search algorithm
10. A comparison of multiprocessor scheduling heuristics
11. Scheduling strategies for multiprocessor real time DSP
12. Performance analysis of embedded software using implicit path enumeration
13. On the use of microarchitecture-driven dynamic voltage scaling
14. The simulation and evaluation fo dynamic voltage scaling algorithms
15. Behavioral synthesis for low power
16. A hybrid genetic algorithm for the fixed channel assignment problem
17. A compile-time scheduling heuristic for interconnection-constrained heterogeneous processor architectures
18. The GENITOR algorithm and selective pressure: Why rank-based allocation of reproductive trials is best
19. Optimizing the efficiency of parameterized local search within global search: A preliminary study