Jul 2026
Application-Driven Architecture Exploration for Cross-Layer Heterogeneous Systems
AI and HPC infrastructure increasingly serves workload portfolios that combine dense tensor computation, sparse kernels, large memory footprints, and communication-intensive collectives. Supporting these portfolios requires coordinated choices across accelerators, memory tiers, scale-up fabrics, and cluster networks. T...
Yuchen Fan, Minghong Sun, Jikui Ma et al.
· arXiv.org · 0 citations