Presenter
Austin Ellis

Biography
Dr. J. Austin Ellis is an APU application architect at AMD and lead on-site staff at Lawrence Livermore National Laboratory helping to deploy AMDʼs next exascale system, El Capitan, powered by the Instinct MI300A APU. He specializes in high performance computing, machine learning, GPU computing, scalable algorithms, and data analytics. As part of AMD's Center of Excellence, he also leads many AI engagements on large language models and leadership class training.
Ellis co-authored the SC21 Best Paper, “Revealing Power, Energy and Thermal Dynamics of a 200PF Pre-Exascale Supercomputer,” which examined 1Hz telemetry data collected from OLCFʼs Summit machine for the year of 2020. He was also part of the OLCF HPL-MxP benchmark team, currently at 10.2 exaflops (FP16), on the Frontier exascale machine, for which he and the team all received the 2022 ORNL Director's Award for Outstanding Team Accomplishment and the ORNL Award for Distinguished Innovation.
Ellis co-authored the SC21 Best Paper, “Revealing Power, Energy and Thermal Dynamics of a 200PF Pre-Exascale Supercomputer,” which examined 1Hz telemetry data collected from OLCFʼs Summit machine for the year of 2020. He was also part of the OLCF HPL-MxP benchmark team, currently at 10.2 exaflops (FP16), on the Frontier exascale machine, for which he and the team all received the 2022 ORNL Director's Award for Outstanding Team Accomplishment and the ORNL Award for Distinguished Innovation.
Presentations
Birds of a Feather
TP
XO/EX