Mixing precisions for performance has been an ongoing trend as the modern hardware accelerators started including new, and mostly lower-precision, data formats. The advantage of using them is a great potential of performance gain and energy savings. The disadvantage are the numerical issues not present in the standard-mandated floating-point formats. Split integer emulation of FP64 takes this to an extreme with the computation performed only by fixed-point tensor core units. We present the new issues the emulation faces for practical cases involving dense linear solver. We show extensive numerical tests indicating the effect of extended numerical range of matrix entries. We also scaled the input sizes to study the performance and numerical profiles on the NVIDIA Hopper GPUs.
@article{arxiv.2509.23565,
title = {Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8},
author = {Piotr Luszczek and Vijay Gadepally and LaToya Anderson and William Arcand and David Bestor and William Bergeron and Alex Bonn and Daniel J. Burrill and Chansup Byun and Michael Houle and Matthew Hubbell and Hayden Jananthan and Michael Jones and Peter Michaleas and Guillermo Morales and Julia Mullen and Andrew Prout and Albert Reuther and Antonio Rosa and Charles Yee and Jeremy Kepner},
journal= {arXiv preprint arXiv:2509.23565},
year = {2025}
}