Decomposition of Extended Finite State Machine for Low Power Design

碩士 === 國立清華大學 === 資訊工程學系 === 90 === Previous work has shown that power reduction can be achieved through turning off portions of circuit when they are idle. Unlike previous work which focused only on either controller or datapath, we propose a decomposition technique taking both controller and datap...

Full description

Bibliographic Details
Main Authors: Lee MingHung, 李明鴻
Other Authors: Hwang TingTing
Format: Others
Language:en_US
Published: 2002
Online Access:http://ndltd.ncl.edu.tw/handle/76240420137714987806
id ndltd-TW-090NTHU0392066
record_format oai_dc
spelling ndltd-TW-090NTHU03920662015-10-13T10:34:06Z http://ndltd.ncl.edu.tw/handle/76240420137714987806 Decomposition of Extended Finite State Machine for Low Power Design 低功率設計之延伸式自動狀態機分解 Lee MingHung 李明鴻 碩士 國立清華大學 資訊工程學系 90 Previous work has shown that power reduction can be achieved through turning off portions of circuit when they are idle. Unlike previous work which focused only on either controller or datapath, we propose a decomposition technique taking both controller and datapath into consideration. The state probability of a FSM provides the execution frequency of operation in that state. Operations performed in states provide the resource requirement which can be used to determine the resource sharing among states. Experimental results show that on the average, 10% area reduction and 24% power reduction can be achieved as compared to designs without decomposition. Hwang TingTing 黃婷婷 2002 學位論文 ; thesis 32 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立清華大學 === 資訊工程學系 === 90 === Previous work has shown that power reduction can be achieved through turning off portions of circuit when they are idle. Unlike previous work which focused only on either controller or datapath, we propose a decomposition technique taking both controller and datapath into consideration. The state probability of a FSM provides the execution frequency of operation in that state. Operations performed in states provide the resource requirement which can be used to determine the resource sharing among states. Experimental results show that on the average, 10% area reduction and 24% power reduction can be achieved as compared to designs without decomposition.
author2 Hwang TingTing
author_facet Hwang TingTing
Lee MingHung
李明鴻
author Lee MingHung
李明鴻
spellingShingle Lee MingHung
李明鴻
Decomposition of Extended Finite State Machine for Low Power Design
author_sort Lee MingHung
title Decomposition of Extended Finite State Machine for Low Power Design
title_short Decomposition of Extended Finite State Machine for Low Power Design
title_full Decomposition of Extended Finite State Machine for Low Power Design
title_fullStr Decomposition of Extended Finite State Machine for Low Power Design
title_full_unstemmed Decomposition of Extended Finite State Machine for Low Power Design
title_sort decomposition of extended finite state machine for low power design
publishDate 2002
url http://ndltd.ncl.edu.tw/handle/76240420137714987806
work_keys_str_mv AT leeminghung decompositionofextendedfinitestatemachineforlowpowerdesign
AT lǐmínghóng decompositionofextendedfinitestatemachineforlowpowerdesign
AT leeminghung dīgōnglǜshèjìzhīyánshēnshìzìdòngzhuàngtàijīfēnjiě
AT lǐmínghóng dīgōnglǜshèjìzhīyánshēnshìzìdòngzhuàngtàijīfēnjiě
_version_ 1716829144206016512