Error Analysis for Fused Floating-point Square-root and Division based on Goldschmidt Algorithm

doi:10.1109/NEWCAS57931.2023.10198192

	Error Analysis for Fused Floating-point Square-root and Division based on Goldschmidt Algorithm
	Liangtao Dai1 ; Binzhe Yuan1 ; Yuan Wang 2; Chao Yang1 ; Xin Lou1
	2023-06-26
会议录名称	2023 21ST IEEE INTERREGIONAL NEWCAS CONFERENCE (NEWCAS)
ISSN	2472-467X
发表状态	已发表
DOI	10.1109/NEWCAS57931.2023.10198192
摘要	This paper presents an error analysis method for floating-point square-root and division based on Goldschmidt algorithm. The proposed analysis is sufficiently concise to guide circuit design and leads to intermediate results for state-of-the-art word length reduction. This error analysis method is applicable to both division and square-root and can help designers achieve a high degree of resource reuse for these two operations. To validate our method, we have designed a fused square-root and division module for IEEE 754 single precision and compare the theoretical error bound with the simulated error bound under 100 trillion random tests. The module not only excels among existing floating-point units, but also achieves a high degree of resource reuse for division and square-root.
关键词	Goldschmidt algorithm error analysis floating-point square-root division
会议地点	Edinburgh, United Kingdom
会议日期	26-28 June 2023
URL	查看原文
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333403
专题	信息科学与技术学院信息科学与技术学院_PI研究组_娄鑫组信息科学与技术学院_硕士生信息科学与技术学院_本科生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.School of Integrated Circuit Science and Engineering, UESTC, Chengdu, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Liangtao Dai,Binzhe Yuan,Yuan Wang,et al. Error Analysis for Fused Floating-point Square-root and Division based on Goldschmidt Algorithm[C],2023.