计算机工程与科学2025，Vol.47Issue(5)：761-774,14.DOI:10.3969/j.issn.1007-130X.2025.05.001
面向国产芯片的可复现矩阵分解
Reproducible matrix decomposition on domestic chip
摘要
Abstract
The reproducibility of floating-point programs refers to the fact that the same floating-point program exactly obtains the same numerical results in bits in multiple different runs.This is of great significance for program debugging or correctness verification of numerical results,and is widely used in numerical simulation.However,the results of floating-point calculations are often influenced by the order of calculations,so the dynamic scheduling & disordered execution of instructions makes the reproducibility a challenge.Matrix decomposition algorithms are widely used in numerical simulation applications.Reproducible matrix decomposition algorithms can effectively improve the efficiency of de-bugging and result analysis in precision sensitive numerical simulation applications.Based on error free transformation technology,three reproducible matrix decomposition algorithms are implemented based on the reproducible BLAS library,including block LU decomposition,Cholesky decomposition,and QR decomposition,and verified on domestic processor.The experimental results show that reproducible matrix decomposition algorithms are numerical accurate and reproducible.关键词
可复现/LU分解/Cholesky分解/QR分解Key words
reproducibility/LU decomposition/Cholesky decomposition/QR decomposition分类
计算机与自动化引用本文复制引用
唐滔,姜浩,彭林,漆海俊,鲁轻风..面向国产芯片的可复现矩阵分解[J].计算机工程与科学,2025,47(5):761-774,14.基金项目
国家重点研发计划(2020YFA0709803) （2020YFA0709803）
