DocumentCode :
2248098
Title :
On the distribution of exponent differences during floating point addition
Author :
Pillai, R.V.K. ; Al-Khalili, D. ; Al-Khalili, A.J.
Author_Institution :
Concordia Univ., Montreal, Que., Canada
Volume :
1
fYear :
1998
fDate :
24-28 May 1998
Firstpage :
105
Abstract :
The paper addresses the characterization of exponent differences during floating point accumulate and multiply accumulate (MAC) operations. Our investigations suggest the existence of a class of probability density functions (pdfs) that exhibit non zero modes, describing the behavior of exponent differences. The distributions also support the hypothesis that the power consumption of floating point adders can be reduced by bypassing the adder during certain situations, that are characterized by an apriori knowledge of the final result
Keywords :
adders; floating point arithmetic; probability; apriori knowledge; exponent differences; floating point accumulate; floating point adders; floating point addition; multiply accumulate operations; non zero modes; power consumption; probability density functions; Algorithm design and analysis; CMOS logic circuits; Councils; Educational institutions; Energy consumption; Equations; Logic design; Power engineering and energy; Probability density function; Scalability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Computer Engineering, 1998. IEEE Canadian Conference on
Conference_Location :
Waterloo, Ont.
ISSN :
0840-7789
Print_ISBN :
0-7803-4314-X
Type :
conf
DOI :
10.1109/CCECE.1998.682562
Filename :
682562
Link To Document :
بازگشت