Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Dynamically Trading Frequency for Complexity in a GALS Microprocessor Steven Dropsho, Greg Semeraro, David H. Albonesi, Grigorios Magklis, and Michael L. Scott
 

Summary: Dynamically Trading Frequency for Complexity in a GALS Microprocessor
Steven Dropsho, Greg Semeraro, David H. Albonesi, Grigorios Magklis, and Michael L. Scott
University of Rochester
Abstract
Microprocessors are traditionally designed to provide
"best overall" performance across a wide range of applica-
tions and operating environments. Several groups have pro-
posed hardware techniques that save energy by "downsiz-
ing" hardware resources that are underutilized by the cur-
rent application phase. Others have proposed a different
energy-saving approach: dividing the processor into do-
mains and dynamically changing the clock frequency and
voltage within each domain during phases when the full do-
main frequency is not required. What has not been studied
to date is how to exploit the adaptive nature of these ap-
proaches to improve performance rather than to save en-
ergy.
In this paper, we describe an adaptive globally asyn-
chronous, locally synchronous (GALS) microprocessor with
a fixed global voltage and four independently clocked do-

  

Source: Albonesi, David H. - Computer Systems Laboratory, Cornell University

 

Collections: Computer Technologies and Information Sciences