Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8
Year: 2025
Type: conference-paper
Abstract: 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.
Authors: Piotr Luszczek, Vijay Gadepally, LaToya Anderson, William Arcand, David Bestor, William Bergeron, Alex Bonn, Daniel J. Burrill, Chansup Byun, Michael Houle, Matthew Hubbell, Michael Jones, Peter Michaleas, Guillermo Morales, Julia Mullen, Andrew Prout, Albert Reuther, Antonio Rosa, Charles Yee, Jeremy Kepner
Institution: MIT Lincoln Laboratory
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415250912