Dual segmentation approximate multiplier

被引：4
作者：
Li, Ling [1 ]
Hammad, Issam [1 ]
El-Sankary, Kamal [1 ]
机构：
[1] Dalhousie Univ, Dept Elect & Comp Engn, Halifax, NS, Canada
来源：
ELECTRONICS LETTERS | 2021年 / 57卷 / 19期
关键词：
DESIGN;
D O I：
10.1049/ell2.12243
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：
This letter proposes a new design for a dual segmentation approximate multiplier. The proposed approximate multiplier uses the static segment method (SSM) to select an initial multiplication segment. Following that, the dynamic segment method (DSM) is utilized to further reduce the initial segment size. Using only the DSM segmenter leads to reduced performance gains. Therefore, the proposed multiplier uses a mixture of the SSM and DSM approaches. Compared to the DSM approach, the proposed design can reduce the energy by 37.90% for 32-bit multipliers, and by 16.68% for 16-bit multipliers. The DSM and proposed multipliers have almost identical accuracy.
引用
收藏
页码：718 / 720
页数：3
相关论文
共 14 条
[1]   Approximate Multipliers Based on New Approximate Compressors [J].
Esposito, Darjn ;
Strollo, Antonio Giuseppe Maria ;
Napoli, Ettore ;
De Caro, Davide ;
Petra, Nicola .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2018, 65 (12) :4169-4182
[2]  
Hammad I., 2019, 2019 IEEE INT C ROB, DOI [10.1109/ROBIO49542.2019.8961780, DOI 10.1109/ROBIO49542.2019.8961780]
[3]   CNN Inference Using a Preprocessing Precision Controller and Approximate Multipliers With Various Precisions [J].
Hammad, Issam ;
Li, Ling ;
El-Sankary, Kamal ;
Snelgrove, W. Martin .
IEEE ACCESS, 2021, 9 :7220-7232
[4]   Impact of Approximate Multipliers on VGG Deep Learning Network [J].
Hammad, Issam ;
El-Sankary, Kamal .
IEEE ACCESS, 2018, 6 :60438-60444
[5]  
Han J, 2013, PROC EUR TEST SYMP
[6]  
Hashemi S, 2015, ICCAD-IEEE ACM INT, P418, DOI 10.1109/ICCAD.2015.7372600
[7]   The Effects of Approximate Multiplication on Convolutional Neural Networks [J].
Kim, Min Soo ;
Del Barrio, Alberto A. ;
Kim, Hyunjin ;
Bagherzadeh, Nader .
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2022, 10 (02) :904-916
[8]   Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications [J].
Narayanamoorthy, Srinivasan ;
Moghaddam, Hadi Asghari ;
Liu, Zhenhong ;
Park, Taejoon ;
Kim, Nam Sung .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2015, 23 (06) :1180-1184
[9]   Comparison and Extension of Approximate 4-2 Compressors for Low-Power Approximate Multipliers [J].
Strollo, Antonio Giuseppe Maria ;
Napoli, Ettore ;
De Caro, Davide ;
Petra, Nicola ;
Meo, Gennaro Di .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2020, 67 (09) :3021-3034
[10]   TOSAM: An Energy-Efficient Truncation- and Rounding-Based Scalable Approximate Multiplier [J].
Vahdat, Shaghayegh ;
Kamal, Mehdi ;
Afzali-Kusha, Ali ;
Pedram, Massoud .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2019, 27 (05) :1161-1173
12