Optimization of matrix multiplication based on a multi-core architecture extended with vector units
Weiwu Hu · 2011
Based on the GODSON-3B 8-core processor,an optimized implementation and evaluation of matrix multiplication was proposed.For the memory access characteristic of each matrix in matrix multiplication,different methods were used to optimize the memory access behavior,hiding memory access time.The performance of optimized matrix multiplication achieves 122 Gflops,and an efficiency of 95.3%.