Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

Abstract: A solar generator capable of power tracking and electric characteristic curve measurement and a method for realizing the same is disclosed. The solar generator of the present invention comprises at least one solar panel receiving solar energy, converting the solar energy into electric energy, and outputting the electric energy; an electric tracking-measuring circuit connected with the solar panel and the external load; and a processor connected with the electric tracking-measuring circuit, controlling the electric tracking-measuring circuit to receive the electric energy and output the electric energy to the external load at the highest power. When the illumination on the solar panel is greater than a preset value, the processor controls the electric tracking-measuring circuit to measure the I-V characteristic curve of the electric energy to determine the operation status of the solar panel.