Numerical Optimization Targeting Energy-Efficient Scientific Computing
Date and Time: July 18th at 09:00, LSTM Seminar Room
Speaker: Dr. Roman Iakymchuk, Uppsala University, Sweden
Topic: Numerical Optimization Targeting Energy-Efficient Scientific Computing
Abstract: Mixed-precision computing has the potential to significantly reduce the cost of exascale computations, but determining when and how to implement it in programs can be challenging. We propose a methodology for enabling mixed-precision with the help of a computer arithmetic tool called Verificarlo, roofline model, and computer arithmetic techniques. As case studies, we consider Nekbone, a mini-application for the Computational Fluid Dynamics (CFD) solver Nek5000, and a modern Neko CFD application. With the help of VerifiCarlo and computer arithmetic techniques, we introduce a strategy to address stagnation issues in the preconditioned Conjugate Gradient method in Nekbone and apply these insights to implement a mixed-precision version of Neko. We evaluate the derived mixed-precision versions of these codes by combining metrics in three dimensions: accuracy, time-to-solution, and energy-to-solution. Notably, mixed-precision in Nekbone reduces time-to-solution by roughly 1.62x and energy-to-solution by 2.43x on MareNostrum 5, while in the real-world Neko application, the gain is up to 1.3x in both time and energy, with the accuracy that matches double-precision results. This talk is based on our recently published article at FGCS: doi.org/10.1016/j.future.2025.107990
This project and the talk is part of the EuroHPC Centre of Excellence CEEC: https://ceec-coe.eu/