Predicting Protein Folding on Intel’s Data Center GPU Max Series Architecture (PVC)

Predicting the structure and interactions of proteins and other life molecules has been a grand challenge for over 60 years. Google’s DeepMind AI team leveraged Artificial intelligence (AI) in 2020 to develop AlphaFold and achieved an accuracy above 90 for two-thirds of the proteins in CASP’s global distance test (GDT). AlphaFold has been very successful in biology and medicine. However, a lack of training code and expansive computational requirements created an open-source implementation named OpenFold. OpenFold is fast, memory-efficient, and provides an OpenProtein dataset with five million MSAs. MLCommons added OpenFold to their HPC benchmarks suite in 2023 and was evaluated by four institutions on NVIDIA GPU architectures. This work presents our endeavours to port, run and tune OpenFold on Intel’s GPU Max Series Ponte Vecchio (PVC). To the best of our knowledge, this is the first large-scale study of the distributed implementation of OpenFold application with Intel PVC GPU, presenting the challenges, opportunities and performance of the application on Intel’s Max series architecture.