Low precision arithmetic, in particular half precision floating point arithmetic, is now available in commercial hardware. Using lower precision can offer significant savings in computation and communication costs with proportional savings in energy. Motivated by this, there has been a renewed interest in mixed precision iterative refinement for solving linear systems $Ax=b$, and new variants of GMRES-based iterative refinement have been developed. Each particular variant with a given combination of precisions leads to different condition number-based constraints for convergence of the backward and forward errors, and each has different performance costs. The constraints for convergence given in the literature are, as an artifact of the analyses, often overly strict in practice, and thus could lead a user to select a more expensive variant when a less expensive one would have sufficed.
In this work, we develop a multistage mixed precision iterative refinement solver which aims to combine existing mixed precision approaches to balance performance and accuracy and improve usability. For an initial combination of precisions, the algorithm begins with the least expensive approach and convergence is monitored via inexpensive computations with quantities produced during the iteration. If slow convergence or divergence is detected using particular stopping criteria, the algorithm switches to use a more expensive, but more reliable variant. A novel aspect of our approach is that, unlike existing implementations, our algorithm first attempts to use ``stronger'' solvers for the solution update before resorting to increasing the precision(s). In some scenarios, this can avoid the need to refactorize the matrix in higher precision. We perform extensive numerical experiments on random dense problems and problems from real applications which confirm the benefits of the multistage approach.
Iterative Refinement for a Subset of Eigenvectors of Symmetric Matrices via Matrix Multiplications
Research Institute for Science and Engineering, Waseda University（早稻田大学理工学研究科）；Department of Mathematical Sciences, Shibaura Institute of Technology（埼玉工业大学数学科学系）；RIKEN Center for Computational Science（理化学研究所计算科学中心）；Department of Applied Mathematics, Faculty of Science and Engineering, Waseda University（早稻田大学理工学部应用数学系）
Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Hunan Key Laboratory for Computation and Simulation in Science and Engineering, School of Mathematics and Computational Science, Xiangtan University（湘潭大学数学与计算科学学院）
An analysis of iterative refinement for quantum linear system solvers
Pacific Northwest National Laboratory（太平洋西北国家实验室）；Lehigh University（利哈伊大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Quantum Science Institute（量子科学研究所）；University of Southern California（南加州大学）
