电子学报2024，Vol.52Issue(2)：428-440,13.DOI:10.12263/DZXB.20230222
概率计算及混合概率计算
Stochastic Computing and Hybrid Stochastic Computing
摘要
Abstract
The calculation principle of non-positional stochastic number(SN)is a promising technique for realizing high-performance computing owing to its extremely low hardware cost.This paper introduces detailly the origin,develop-ment process and the domestic and foreign development present situation.However,a disadvantage of stochastic bitstream is that the computing latency,and information-carrying efficiency and so on.We presented a hybrid stochastic computing(HSC)based on a hybrid bitstream to solve these problems,which achieves a lower hardware cost,better accuracy,and fast-er speed.The HSC neural networks is fabricated by 40 nm low-power CMOS process,with a core area of 0.73 mm×0.73 mm,power of 102.3 mW and clock of 400 MHz,which has 4 544 multiply and accumulation(MAC).The proposed Hybrid stochastic computing is tested by FPGA and ASIC.Compared with other stochastic computing method,the method proposed gains 50×,2.5×,and 3.26×energy efficiency than other methods of traditional stochastic computing.关键词
概率数/概率计算/混合概率数/混合概率计算/深度神经网络/能效/算力Key words
stochastic number/stochastic computing/hybrid stochastic number/hybrid stochastic computing/deep neural network/energy efficiency/computing performance分类
信息技术与安全科学引用本文复制引用
李洪革,陈宇昊,吴俊毅,宋印杰,朱新宇..概率计算及混合概率计算[J].电子学报,2024,52(2):428-440,13.基金项目
国家自然科学基金(No.62071019) National Natural Science Foundation of China(No.62071019) （No.62071019）
