The Design of Fast and Energy-Efficient Linear Solvers: On the Potential of Half-Precision Arithmetic and Iterative Refinement Techniques

Lecture Notes in Computer Science - Germany
doi 10.1007/978-3-319-93698-7_45
Full Text
Abstract

Available in full text

Date
Authors
Publisher

Springer International Publishing

Related search

Harnessing GPU Tensor Cores for Fast FP16 Arithmetic to Speed Up Mixed-Precision Iterative Refinement Solvers

2018English

Energy-Efficient Digital Design Through Inexact and Approximate Arithmetic Circuits

2015English

Adaptive Precision Solvers for Sparse Linear Systems

2015English

Accelerating the Solution of Linear Systems by Iterative Refinement in Three Precisions

SIAM Journal of Scientific Computing
Computational MathematicsApplied Mathematics
2018English

On Optimizing the Arithmetic Precision of McMc Algorithms

2013English

On the Arithmetic and Homology of Algebras of Linear Type

Transactions of the American Mathematical Society
MathematicsApplied Mathematics
1984English

A Refinement of the Inequality Between Arithmetic and Geometric Means

Journal of Mathematical Inequalities
Analysis
2008English

Some Factors Affecting the Precision of Polarographic Half-Wave Potential Measurements

Journal of Research of the National Bureau of Standards
1956English

Improved Algorithms for Efficient Arithmetic on Elliptic Curves Using Fast Endomorphisms

Lecture Notes in Computer Science
Computer ScienceTheoretical Computer Science
2003English

Amanote Research

Note-taking for researchers

Follow Amanote

© 2024 Amaplex Software S.P.R.L. All rights reserved.

Privacy PolicyRefund Policy