Preprint
Aug 2026
NUNA: Characterizing and Mitigating Non-Uniform Network Access in Multi-Die GPU Scale-Up Systems
This work highlights the need for NUNA-aware routing (NAR), choosing optimized, spatially-aware inter-GPU paths in large scale-up network topologies and introduces NUNA-aware placement (NAP), placing threadblocks and data near I/O to optimize the inter-GPU traffic.
C. Green, William Won, Ta Tuan et al.
· 1 citation