Abstract

Intel Data Center GPU Max 1550, known as Ponte Vecchio (PVC), is a new Intel GPU architecture for high-performance computing. It is the basis of two systems on the June 2024 Top 500 list, Dawn (#51) and Aurora (#2). This work provides micro-benchmarking data on PVCs from which application developers may benefit, shows how the micro-benchmarking results are indicative of mini-app performance on PVC, and demonstrates real applications on large-scale Intel GPU systems. We quantify the obtainable performance from PVC systems through micro-benchmarking fundamental architectural properties. We evaluate the performance of four mini-apps with known performance characteristics, and two full applications, comparing performance on a node of Aurora and Dawn with a node of NVIDIA H100 GPUs and a node of AMD MI250 GPUs. We show the figure-of-merit of the mini-apps on a single PVC ranges from 0.6–1.8X the performance of a H100, and 0.8–7.5X of an MI250.

@inproceedings{pmbs24-pvc,
  author = {Applencourt, Thomas and Sadawarte, Aditya and Muralidharan, Servesh and Bertoni, Colleen and Kwack, JaeHyuk and Luo, Ye and Rangel, Esteban and Tramm, John and Ghadar, Yasaman and Tamerus, Arjen and Edsall, Chris and Deakin, Tom},
  title = {{Ponte Vecchio Across the Atlantic: Single-Node Benchmarking of Two Intel GPU Systems}},
  booktitle = {{International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems held in conjunction with Supercomputing (PMBS)}},
  year = {2024},
  publisher = {{IEEE}},
  keywords = {Conferences and Workshops},
  doi = {10.1109/SCW63240.2024.00184}
}