DocumentCode :
3261122
Title :
Programmable numerical function generators based on quadratic approximation: architecture and synthesis method
Author :
Nasayama, S. ; Sasao, Tsutomu ; Butler, Jon T.
Author_Institution :
Dept. of CE, Hiroshima City Univ.
fYear :
2006
fDate :
24-27 Jan. 2006
Abstract :
This paper presents architecture and a synthesis method for programmable numerical function generators (NFGs) for trigonometric, logarithmic, square root, and reciprocal functions. Our NFG partitions a given domain of the function into nonuniform segments using a LUT cascade, and approximates the given function by a quadratic polynomial for each segment. Thus, we can implement fast and compact NFGs for a wide range of functions. Implementation results on an FPGA show that: 1) our NFGs require only 4% of the memory needed by NFGs based on the linear approximation with nonuniform segmentation; and 2) our NFGs require only 22% of the memory needed by NFGs based on the 5th-order approximation with uniform segmentation. Our automatic synthesis system generates such compact NFGs quickly
Keywords :
field programmable gate arrays; function generators; table lookup; FPGA; LUT cascade; automatic synthesis; linear approximation; logarithmic function; nonuniform segmentation; programmable numerical function generators; quadratic approximation; reciprocal functions; square root function; trigonometric function; Application software; Coprocessors; Error analysis; Field programmable gate arrays; Function approximation; Hardware design languages; Linear approximation; Polynomials; Signal generators; Table lookup;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Design Automation, 2006. Asia and South Pacific Conference on
Conference_Location :
Yokohama
Print_ISBN :
0-7803-9451-8
Type :
conf
DOI :
10.1109/ASPDAC.2006.1594712
Filename :
1594712
Link To Document :
بازگشت