本文说明传统的并行技术可以有效地开发循环中的子字并行性,同时提出一种基于代价子图的子字并行指令自动识别的方法。
This paper shows that the traditional parallelization techniques can be used to exploit subword parallelism, and also proposes a novel method to extract subword parallelism based on the cost subgraph.
本文说明传统的并行技术可以有效地开发循环中的子字并行性,同时提出一种基于代价子图的子字并行指令自动识别的方法。
This paper shows that the traditional parallelization techniques can be used to exploit subword parallelism, and also proposes a novel method to extract subword parallelism based on the cost subgraph.
应用推荐