Toward Approximate Computing for Coarse-Grained Reconfigurable Architectures

被引:15
作者
Akbari, Omid [1 ]
Kamal, Mehdi [1 ]
Afzali-Kusha, Ali [1 ]
Pedram, Massoud [2 ]
Shafique, Muhammad [3 ]
机构
[1] Univ Tehran, Sch Elect & Comp Engn, Tehran, Iran
[2] Univ Southern Calif, Dept Elect Engn, Los Angeles, CA USA
[3] Vienna Univ Technol, Inst Comp Engn, Vienna, Austria
基金
美国国家科学基金会;
关键词
DESIGN;
D O I
10.1109/MM.2018.2873951
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents a methodology for designing an approximate coarse-Qrained reconfigurable architecture (X-CGRA), and its use for accelerating both error-resilient and error-sensitive applications. The output quality of the X-CGRA is manageable at the run-time for better performance and power/energy consumption tradeoffs. Results show up to 1.9 x speedup and 2.3 x lower energy consumption at the cost of 9.7% accuracy loss for the studied applications.
引用
收藏
页码:63 / 72
页数:10
相关论文
共 11 条
[1]   RAP-CLA: A Reconfigurable Approximate Carry Look-Ahead Adder [J].
Akbari, Omid ;
Kamal, Mehdi ;
Afzali-Kusha, Ali ;
Pedram, Massoud .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2018, 65 (08) :1089-1093
[2]   Dual-Quality 4:2 Compressors for Utilizing in Dynamic Accuracy Configurable Multipliers [J].
Akbari, Omid ;
Kamal, Mehdi ;
Afzali-Kusha, Ali ;
Pedram, Massoud .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2017, 25 (04) :1352-1361
[3]  
Chin SA, 2017, IEEE INT CONF ASAP, P184, DOI 10.1109/ASAP.2017.7995277
[4]  
De Micheli G., 1994, SYNTHESIS OPTIMIZATI
[5]  
Esmaeilzadeh H, 2011, ISCA 2011: PROCEEDINGS OF THE 38TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, P365, DOI 10.1145/2024723.2000108
[6]  
Kulkarni P., 2011, Proceedings of the 24th International Conference on VLSI Design: concurrently with the 10th International Conference on Embedded Systems Design, P346, DOI 10.1109/VLSID.2011.51
[7]  
Li CH, 2015, ACSR ADV COMPUT, V11, P1
[8]   Design and Analysis of Approximate Compressors for Multiplication [J].
Momeni, Amir ;
Han, Jie ;
Montuschi, Paolo ;
Lombardi, Fabrizio .
IEEE TRANSACTIONS ON COMPUTERS, 2015, 64 (04) :984-994
[9]  
Shafique M, 2015, P 52 ACM EDAC IEEE D, P1
[10]  
Ye R, 2013, ICCAD-IEEE ACM INT, P48, DOI 10.1109/ICCAD.2013.6691096