Processor energy estimation method using cycle-approximate simulatorCycle-approximate 시뮬레이터를 사용한 프로세서 에너지 예측방법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 472
  • Download : 0
The estimation of energy consumption by processor is essential among the software optimization process in the energy aspect. But as the size and complexity of software have rapidly increased recently, the processor energy estimation is being bottlenecked in the software optimization process. Therefore a fast and accurate processor energy estimation method is necessary. The existing processor energy estimation method can be mainly classified into two types. The first method is the method using the cycle-accurate simulator. While this method is accurate because the energy consumption of processor is estimated using cycle-accurate simulator providing a lot of information, there is a disadvantage of taking up long estimation time. The second method is C-code static analysis method. This is the method of estimating energy consumption of processor by directly analyzing the given c-code and while it has an advantage of being able to estimate the energy consumption within short period of time, there is disadvantage of being estimated very inaccurately. In this paper, a processor energy estimation method using cycle-approximate simulator combining advantage of above two methods has been proposed. This method enables fast and accurate energy estimation.
Advisors
Kyung, Chong-Minresearcher경종민researcher
Description
한국과학기술원 : 전기및전자공학전공,
Publisher
한국과학기술원
Issue Date
2008
Identifier
301988/325007  / 020064063
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학전공, 2008. 8., [ vi, 39 p. ]

Keywords

power estimation; energy estimation; power model; energy model; power analysis; 전력 예측; 에너지 예측; 전력 모델; 에너지 모델; 전력 분석; power estimation; energy estimation; power model; energy model; power analysis; 전력 예측; 에너지 예측; 전력 모델; 에너지 모델; 전력 분석

URI
http://hdl.handle.net/10203/38647
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=301988&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0