Author :
Albonesi, David H. ; Balasubramonian, Rajeev ; Dropsbo, S.G. ; Dwarkadas, Sandhya ; Friedman, Eby G. ; Huang, Michael C. ; Kursun, Volkan ; Magklis, Grigorios ; Scott, Michael L. ; Semeraro, Greg ; Bose, Pradip ; Buyuktosunoglu, Alper ; Cook, Peter W. ; S
Abstract :
By using adaptive processing to dynamically tune major microprocessor resources, developers can achieve greater energy efficiency with reasonable hardware and software overhead while avoiding undue performance loss. Adaptive processors require few additional transistors. Further, because adaptation occurs only in response to infrequent trigger events, the decision logic can be placed into a low-leakage state until such events occur.
Keywords :
adaptive systems; computer architecture; digital integrated circuits; integrated circuit design; microprocessor chips; software engineering; adaptive processing; adaptive processors; decision logic; energy efficiency; hardware overhead; infrequent trigger events; low-leakage state; microprocessor resources; performance loss; processor resource tuning; software overhead; Application software; Batteries; Energy efficiency; Hardware; Microprocessors; Parallel processing; Performance loss; Productivity; Software performance; Web search;