An Analytical Model for Matrix Multiplication on Many Threaded Vector Processors

作者:Wang Yongwen*; Gao Jun; Sui Bingcai; Zhang Chengyi; Xu Weixia
来源:18th CCF Annual Conference on Computer Engineering and Technology (NCCET), 2014-07-29 to 2014-08-01.

摘要

Vector can enhance peak performance while multi-threading can improve efficiency. MTV is a new architecture that combines the two to achieve both high computing performance and high throughput. Matrix multiplication is the kernel of many scientific applications. A parallel matrix multiplication algorithm is presented and an analytical performance model is built. Based on the model, the performance of MTV was evaluated and critical configurations are given to guide the design of MTV processors..