Low Power Probabilistic Floating Point Multiplier Design

被引:18
作者
Gupta, Aman [1 ,5 ]
Mandavalli, Satyam [1 ]
Mooney, Vincent J. [2 ,3 ,4 ,5 ]
Ling, Keck-Voon [2 ,5 ]
Basu, Arindam [2 ,5 ]
Johan, Henry [3 ,5 ]
Tandianus, Budianto [5 ]
机构
[1] Int Inst Informat Technol, Hyderabad, Andhra Pradesh, India
[2] Nanyang Technol Univ NTU, Sch Elect & Elect Engn, Singapore, Singapore
[3] Nanyang Technol Univ NTU, Sch Comp Engn, Singapore, Singapore
[4] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
[5] Nanyang Technol Univ, NTU Rice Inst Sustainable & Appl Infodynam, Singapore, Singapore
来源
2011 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI) | 2011年
关键词
probabilistic computation; floating point multiplication;
D O I
10.1109/ISVLSI.2011.54
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
080201 [机械制造及其自动化];
摘要
We present a low power probabilistic floating point multiplier. Probabilistic computation has been shown to be a technique for achieving energy efficient designs. As best known to the authors, this is the first attempt to use probabilistic digital logic to attain low power in a floating point multiplier. To validate the approach, probabilistic multiplications are introduced in a ray tracing algorithm used in computer graphics applications. It is then shown that energy savings of around 31% can be achieved in a ray tracing algorithm's floating point multipliers with negligible degradation in the perceptual quality of the generated image.
引用
收藏
页码:182 / 187
页数:6
相关论文
共 13 条
[1]
[Anonymous], ACT HDL 6 3 MAN
[2]
[Anonymous], 2008, 7542008 IEEE, P1
[3]
[Anonymous], [No title captured]
[4]
Chakrapani L.N. B., 2008, proc. of the IEEE/ACM International Conference on Compilers, Architectures, P187, DOI 10.1145/1450095.1450124
[5]
George J., 2006, INT C COMPILERS ARCH, P158, DOI DOI 10.1145/1176760.1176781
[6]
End of Moore's law: thermal (noise) death of integration in micro and nano electronics [J].
Kish, LB .
PHYSICS LETTERS A, 2002, 305 (3-4) :144-149
[7]
Koo KH, 2005, IEEE INT SYMP CIRC S, P1063
[8]
Palem K.V., 2003, PROC IEEEACM INT C C, P113
[9]
Singh A., 2011, P VLSI DES TEST C VL
[10]
Reducing power by optimizing the necessary precision/range of floating-point arithmetic [J].
Tong, JYF ;
Nagle, D ;
Rutenbar, RA .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2000, 8 (03) :273-286