Bit-width-aware constant-delay run-time Accuracy Programmable Adder for error-resilient applications

被引:18
作者
Garg, Bharat [1 ]
Dutt, Sunil [2 ]
Sharma, G. K. [1 ]
机构
[1] ABV Indian Inst Informat Technol & Management Gwa, Gwaliar, India
[2] Indian Inst Technol Guwahati, Gauhati, Assam, India
来源
MICROELECTRONICS JOURNAL | 2016年 / 50卷
关键词
Approximate computing; Error-resilient applications; Approximate adder; Speed-Power-Accuracy-Area (SPAA) trade-off; DESIGN; DATAPATH;
D O I
10.1016/j.mejo.2016.01.002
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Error-resilient applications such as image, audio and video processing adopt the concept of approximate computing to decorate delay, power and area metrics at the cost of accuracy. Approximate computing relaxes the exact equivalence between the design specifications and the design implementation to achieve Speed-Power-Accuracy-Area (SPAA) trade-off. In this paper, we propose a bit-width-aware constant-delay run-time Accuracy Programmable Adder (APA) in which the probability of input combinations exhibiting accurate results is programmable and adaptively controlled by the Number of Iterations (Nols). Simulation results based on the PTM 32 nm CMOS technology suggest that the proposed approach attains tremendous improvements in delay, power and area metrics with a trivial degradation in the output quality. The proposed APA shows 3.4 x improvement in performance and 41.5% reduction in area over the best known accuracy configurable adder. Even with 100% accuracy, a 32-bit APA improves delay, power and area by 33.92%, 23.04% and 17.44%, respectively, over Ripple Carry Adder (RCA). We also demonstrate an APA embedded error-resilient JPEG encoder architecture in order to inspect the efficacy of the proposed approach in real-time Digital Signal Processing (DSP) applications. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1 / 7
页数:7
相关论文
共 16 条
[1]  
[Anonymous], 49 ACM EDAC IEEE DES
[2]  
[Anonymous], IEEE T COMPUT
[3]   A REGULAR LAYOUT FOR PARALLEL ADDERS [J].
BRENT, RP ;
KUNG, HT .
IEEE TRANSACTIONS ON COMPUTERS, 1982, 31 (03) :260-264
[4]   Low-Power Digital Signal Processing Using Approximate Adders [J].
Gupta, Vaibhav ;
Mohapatra, Debabrata ;
Raghunathan, Anand ;
Roy, Kaushik .
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2013, 32 (01) :124-137
[5]   Low-power VLSI design for motion estimation using adaptive pixel truncation [J].
He, ZL ;
Tsui, CY ;
Chan, KK ;
Liou, ML .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2000, 10 (05) :669-678
[6]  
Jiawei Huang, 2011, 2011 16th Asia and South Pacific Design Automation Conference, ASP-DAC 2011, P579, DOI 10.1109/ASPDAC.2011.5722256
[7]   PARALLEL ALGORITHM FOR EFFICIENT SOLUTION OF A GENERAL CLASS OF RECURRENCE EQUATIONS [J].
KOGGE, PM ;
STONE, HS .
IEEE TRANSACTIONS ON COMPUTERS, 1973, C-22 (08) :786-793
[8]  
Krause PK, 2011, DES AUT TEST EUROPE, P944
[9]   Speeding up processing with approximation circuits [J].
Lu, SL .
COMPUTER, 2004, 37 (03) :67-+
[10]  
MALY W, 1994, ACM IEEE D, P135