HPC中的光子协处理器:使用LightOn OPU进行随机数值线性代数计算
机器学习
2021-05-10 v2 机器学习
摘要
随机数值线性代数(RandNLA)是一类强大的方法,广泛应用于高性能计算(HPC)中。RandNLA以更低的计算成本,为应用于大型信号的线性代数函数提供近似解。然而,在传统硬件上,用于降维的随机化步骤本身可能成为计算瓶颈。利用LightOn光学处理单元提供的近常数时间线性随机投影,我们表明在广泛的具有重要意义的RandNLA算法(如RandSVD或迹估计器)中,随机化可在精度损失可忽略的情况下显著加速。
引用
@article{arxiv.2104.14429,
title = {Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra},
author = {Daniel Hesslow and Alessandro Cappelli and Igor Carron and Laurent Daudet and Raphaël Lafargue and Kilian Müller and Ruben Ohana and Gustave Pariente and Iacopo Poli},
journal= {arXiv preprint arXiv:2104.14429},
year = {2021}
}
备注
Add "This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 860830"