Presenter

Xinyi Li is a Postdoctoral Researcher at the Pacific Northwest
National Laboratory. She obtained her Ph.D. degree at the University of Utah
specializing in the analysis of floating point behaviors within high-performance
systems. She was advised by Prof. Ganesh Gopalakrishnan. Xinyi's expertise
includes floating-point exception detection using GPU Binary
Instrumentation as well as methods to determine the floating-point
characteristics of GPUs and their Matrix Accelerators using
Feature-Target Testing of Numerics (FTTN). She is the author of
publicly released tools GPU-FPX for efficient Floating-Point Exception
Detection within NVIDIA GPUs and the FTTN Testing Suite. Previously,
she obtained her Master's Degree at the UT Dallas where she worked on
Computational Geometry.