Dimitrios Gourounas received a Best Paper nomination at the 33rd IEEE International Symposium on Field-Programmable Custom Computing Machines in Fayetteville, Arkansas this May.
Gourounas’s paper discusses “HighWave,” a scalable FPGA-based architecture designed to accelerate wave simulations by efficiently leveraging high-bandwidth memory (HBM) through specialized processing and memory optimizations, resulting in superior performance and energy efficiency compared to state-of-the-art GPU solutions. Gourounas summarized on his LinkedIn page, “In this paper, I propose an efficient, HBM-enabled and generic FPGA accelerator for highly memory-bound wave simulations.”
Gourounas also thanked his collaborators: “many thanks to Austin James and Bagus Hanindhito for all the hard work, as well as Arash Fathi and my advisor Andreas Gerstlauer for their valuable feedback and insights.”
You can read Gourounas’s paper in full here.