Supported by:
Synopsys
Facebook
Facebook
Intel

Wednesday June 16th, 2021 (16:00 to 17:00)

Keynote Talk

Opportunities for Mixed Precision Arithmetic in Numerical Linear Algebra

Théo Mary, CNRS Researcher, Sorbonne Université, CNRS, LIP6, Paris, France

Abstract: The emergence of low precision arithmetic on modern hardware, such as the increasingly supported fp16 and bfloat16 floating-point arithmetics, provides new opportunities to accelerate linear algebra computations. A key challenge in doing so is to preserve the accuracy and stability of the computation. In this talk we will present mixed precision algorithms for the solution of linear systems, that combine low and high precisions in order to achieve both high performance and high accuracy. We will describe recent key advances in making these algorithms effective on modern hardware, in very low precision, and on a wide range of matrices arising in various applications.

Bio: Théo Mary is a CNRS researcher at the LIP6 laboratory of Sorbonne University in Paris, France, since 2019. He earned his PhD degree from the University of Toulouse in 2017. His PhD thesis, which he prepared at the IRIT laboratory under the supervision of Patrick Amestoy and Alfredo Buttari, was awarded an honorable mention for the Householder prize. He then spent two years at The University of Manchester, where he worked as a postdoctoral researcher in Nick Higham's numerical linear algebra group.