Description: We explore how to optimally deploy different types of machine-learned surrogate models used in rotorcraft aerodynamics on HPC. We first developed three different rotorcraft models at three different orders of magnitude (2M, 44M, and 212M trainable parameters) to use as test models. We tested three different types of inference server deployments: (1) a Flask-based HTTP inference server, (2) TensorFlow Serving with gRPC protocol, and (3) RedisAI server with RESP protocol. We investigated deployments on both DoD HPCMP's SCOUT and DoE OLCF's Summit POWER9 supercomputers, demonstrated the ability to inference a million samples per second using 192 GPUs, and studied multiple scenarios on both Nvidia T4 and V100 GPUs. We studied a range of concurrency levels both on the client-side and the server-side, and provide optimal configuration advice based on the type of deployment. Finally, we provide a simple Python-based framework for benchmarking machine-learned surrogate models using the various inference servers.

Presenter(s): Dr. Wesley Brewer, GDIT/PET
Location: SC21, St. Louis, MO
Date & Time: November 15, 2021, 4:20p - 4:45p CT

Distribution Statement D. Distribution limited to the Department of Defense and U.S. DoD contractors only, for administrative or operational use, 15 November 2021.  Other requests for this document shall be referred to the High Performance Computing Modernization Office, 3909 Halls Ferry Road, Vicksburg, MS 39180.