Simultaneous Optimisation of Dynamic Power, Area and Delay in Behavioural Synthesis

Williams, A.C., Brown, A.D. and Zwolinski, M. (2000) Simultaneous Optimisation of Dynamic Power, Area and Delay in Behavioural Synthesis


[img] PDF iee_lowpower.pdf - Other
Download (129kB)


Concern over power dissipation coupled with the continuing rise in system size and complexity means that there is a growing need for high-level design tools capable of automatically optimising systems to take into account power dissipation, in addition to the more conventional metrics of area, delay and testability. Current methods for reducing power consumption tend to be ad-hoc: for example, slowing down, or turning off idle parts of the system, or a controlled reduction in power supply. The behavioural synthesis system described in this paper features an integrated incremental power estimation capability, which makes use of activity profiles, generated automatically through simulation of a design on any standard VHDL simulator; accurate circuit-level cell models (generated, again automatically, via Spice simulation); and a comprehensive system power model. This data, along with similar estimators for area and delay, guides the optimisation of a design towards independent, user-specified objectives for final area, delay, clock speed, and energy consumption. In addition, a range of power reducing features are included encompassing: supply voltage scaling, clock gating, input latching, input gating, low-power cells, and pipelined and multicycle units. These are automatically exploited during optimisation as part of the area/delay/power dissipation trade-off process. The resulting system is capable of reducing the estimated energy consumption of several benchmark designs by factors of between 3.5 and 7.0 times. Furthermore, the design exploration capability enables a range of alternative structural implementations to be generated from a single behavioural description, with differing area/delay/power trade-offs.

Item Type: Other
Organisations: EEE
ePrint ID: 254052
Date :
Date Event
November 2000Published
Date Deposited: 05 Jul 2001
Last Modified: 17 Apr 2017 23:19
Further Information:Google Scholar

Actions (login required)

View Item View Item