中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Float-Fix: An Efficient and Hardware-Friendly Data Type for Deep Neural Network

文献类型：期刊论文

作者Wang, Yibo1; Han, Dong3,4; Zhou, Shengyuan3,4; Zhi, Tian4; Liu, Shaoli2,4
刊名INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING
出版日期2019-06-01
卷号47期号:3页码:345-359
关键词Float-Fix Neural network Hardware accelerator Data type
ISSN号0885-7458
DOI10.1007/s10766-018-00626-7
英文摘要Recent years, as deep learning rose in prominence, neural network accelerators boomed. The existing research shows that both speed and energy-efficiency can be improved by low precision data structure. However, decreasing the precision of data might compromise the usefulness and accuracy of the underlying AI. And the existing studies can not meet all AI application requirements. In the paper, we propose a new data type, called Float-Fix (FF). We introduce the structure of FF and compare it with other data types. In our evaluation, the accuracy loss of 8-bit FF is less than 0.12% on a subset of known neural network models, 7x better than fixed-point, DFX and floating-point on average. We implement the hardware architectures of operators and neural processing unit using 8-bit FF data type with TSMC 65nm Gplus High VT library. The experiments show that the hardware cost of convertors converting between 16-bit fixed-point and FF is really small. And the multiplier of 8-bit FF only needs 1188m2 area, which is nearly 8-bit fixed-point. Comparing with the neural processing unit of DianNao, FF reduces 34.3% area.
资助项目National Key Research and Development Program of China[2017YFA0700902] ; National Key Research and Development Program of China[2017YFB1003101] ; NSF of China[6147239] ; NSF of China[61432016] ; NSF of China[61473275] ; NSF of China[61522211] ; NSF of China[61532016] ; NSF of China[61521092] ; NSF of China[61502446] ; NSF of China[61672491] ; NSF of China[61602441] ; NSF of China[61602446] ; NSF of China[61732002] ; NSF of China[61702478] ; 973 Program of China[2015CB358800] ; National Science and Technology Major Project[2018ZX01031102] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDBS01050200]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000471644400002
出版者SPRINGER/PLENUM PUBLISHERS
源URL[http://119.78.100.204/handle/2XEOYT63/4179]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Liu, Shaoli
作者单位1.Tsinghua Univ, Beijing, Peoples R China
2.Cambricon Tech Ltd, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
4.Chinese Acad Sci, Intelligent Processor Res Ctr, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Yibo,Han, Dong,Zhou, Shengyuan,et al. Float-Fix: An Efficient and Hardware-Friendly Data Type for Deep Neural Network[J]. INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING,2019,47(3):345-359.
APA Wang, Yibo,Han, Dong,Zhou, Shengyuan,Zhi, Tian,&Liu, Shaoli.(2019).Float-Fix: An Efficient and Hardware-Friendly Data Type for Deep Neural Network.INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING,47(3),345-359.
MLA Wang, Yibo,et al."Float-Fix: An Efficient and Hardware-Friendly Data Type for Deep Neural Network".INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING 47.3(2019):345-359.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。