Performance-Energy Optimizations for Shared Vector Accelerators in Multicores
For multicore processors with a private Vector Coprocessor (VP) per core, VP resources may not be highly utilized due to limited Data-Level Parallelism (DLP) in applications. Also, under low VP utilization static power dominates the total energy consumption. The authors enhance here their previously proposed VP sharing framework for multicores in order to increase VP utilization while reducing the static energy. They describe two Power-Gating (PG) techniques to dynamically control the VP’s width based on utilization figures.