In the fundamental operations of large scale matrice, computing speed of GPU can be 50 times faster than CPU on the suitable matrix blocking.
在基本的矩阵运算中，运用适当的矩阵分块，GPU的计算速度比CPU快50倍左右。
The graph analysis method for topological equivalence of interconnection networks, and the concept of logical name matrice for describing logical name structure are proposed.
本文提出了互连网络拓扑等价的图分析法和描述网络逻辑名结构的逻辑名矩阵。
The graph analysis method for topological equivalence of interconnection networks, and the concept of logical name matrice for describing logical name structure are proposed.
本文提出了互连网络拓扑等价的图分析法和描述网络逻辑名结构的逻辑名矩阵。
应用推荐