利用循环分割和循环展开避免Cache代价

Optimization to Prevent Cache Penalty by Loop Partition and Loop Unrolling

存储系统与处理器之间的速度差距逐渐变大,为此,cache使用了分级机制,但这也带来了额外的存储延迟(cache代价).提出一种利用循环分割和循环展开相结合避免cache代价的PCPLPU(prevent cache penalty by loop partition-unrolling)算法.实验结果表明,PCPLPU算法能够有效避免循环代价,提高程序性能.

Due to the increasing speed gap between memory system and processor, cache hierarchies have been implemented into memory system, but additional latency （cache penalty） is introduced. This paper presents an algorithm named as prevent cache penalty by loop partition-unrolling （PCPLPU）, which can prevent cache penalty in loops by the combination of loop partition and unrolling. Experimental results show that PCPLPU can prevent cache penalty and improve the performance of programs.