Sublimation AI processor-based batch matrix multiplier optimization method

The invention discloses a method for optimizing a batch matrix multiplier based on a mercuric chloride (AI) processor, and the method comprises the steps: obtaining first input data and second input data, and carrying the first input data and the second input data to an AI Core; obtaining a loading line number of the second input data, and dividing the first input data and the second input data according to the loading line number and a double-cache mechanism of a preset buffer area; loading the divided first input data and second input data into the buffer area for calculation to obtain output data; and carrying the output data to an external storage for outputting. According to the invention, a double-buffering mechanism can be utilized, the operation time for multiplying the first matrix and the second matrix can be shortened, and thus the data processing efficiency is improved. 本发明公开了一种基于昇腾AI处理器的批量矩阵乘算子的优化方法，所述方法包括：获取第一输入数据与第二输入数据，并将所述第一输入数据与所述第二输入数据搬运到AI Core；获取所述第二输入数据的加载行数，并根据所述加载行数以及预设的缓冲区的双缓存机制对所述第一输