Investigating half precision arithmetic to accelerate dense linear system solvers-Reference-Cited by-同舟云学术

Investigating half precision arithmetic to accelerate dense linear system solvers

Published:2017-11-12 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems
language:
Short-container-title:

Author:

Haidar Azzam¹,Wu Panruo¹,Tomov Stanimire¹,Dongarra Jack²

Affiliation:

1. University of Tennessee

2. University of Tennessee and University of Manchester, UK

Funder

Nvidia

U.S. Department of Energy

National Science Foundation

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3148226.3148237

Reference17 articles.

1. Accelerating scientific computations with mixed precision algorithms

2. Erin Carson and Nicholas J Higham. 2017. Accelerating the solution of linear systems by iterative refinement in three precisions. MIMS EPrint 2017.24 University of Manchester (2017). Erin Carson and Nicholas J Higham. 2017. Accelerating the solution of linear systems by iterative refinement in three precisions. MIMS EPrint 2017.24 University of Manchester (2017).

3. Erin Carson and Nicholas J Higham. 2017. A New Analysis of Iterative Refinement and its Application to Accurate Solution of Ill-Conditioned Sparse Linear Systems. MIMS EPrint 2017.12 University of Manchester (2017). Erin Carson and Nicholas J Higham. 2017. A New Analysis of Iterative Refinement and its Application to Accurate Solution of Ill-Conditioned Sparse Linear Systems. MIMS EPrint 2017.12 University of Manchester (2017).

4. Error bounds from extra-precise iterative refinement

5. J. W. Demmel. 1997. Applied Numerical Linear Algebra. SIAM. J. W. Demmel. 1997. Applied Numerical Linear Algebra . SIAM.

Cited by 25 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Enhancing computational efficiency in 3-D seismic modelling with half-precision floating-point numbers based on the curvilinear grid finite-difference method;Geophysical Journal International;2024-07-05

2. Universal Numbers Library: Multi-format Variable Precision Arithmetic Library;Journal of Open Source Software;2023-03-15

3. Mixed precision algorithms in numerical linear algebra;Acta Numerica;2022-05

4. Summary of Investigations into Finite Volume Methods on GPUs;AIAA SCITECH 2022 Forum;2022-01-03

5. Universal: Reliable, Reproducible, and Energy-Efficient Numerics;Next Generation Arithmetic;2022