I/O Lower-Bound Theory and Reinforcement Learning for Efficient Neural Network Inference Optimization
An automated optimization framework with a hierarchical two-layer tuning mechanism that synergizes theoretical I/O constraints with graph-level adaptive fusion while accounting for search overhead, the framework systematically explores high-performance execution patterns.
Rui Xia, Gencheng Liu, Quan-Li Li et al.
· ACM Transactions on Architec... · 0 citations