2 papers
cs.LG2026
TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators
Chang Meng, Hanyu Wang, Yuyang Ye +3
Reducing power consumption in AI accelerators is increasingly important. Approximate computing can reduce power consumption while keeping the accuracy loss small. Since multipliers…
cs.LO2024
Practical Boolean Decomposition for Delay-driven LUT Mapping
Alessandro Tempia Calvino, Alan Mishchenko, Giovanni De Micheli +1
Ashenhurst-Curtis decomposition (ACD) is a decomposition technique used, in particular, to map combinational logic into lookup tables (LUTs) structures when synthesizing hardware d…