摘要
Compared with other stream applications, scientific stream programs are usually bound by memory accesses. Reusing streams across different iterations, i.e. loop-carried stream reuse, can effectively improve the SRF locality, thus reducing memory accesses greatly. In the paper, we first present the algorism identifying loop-carried stream reuse and that exploiting the reuse after analyzing scientific computing applications. We then perform several representative microbenchmarks and scientific stream programs with and without our optimization on Isim, a cycle-accurate stream processor simulator. Experimental results show that our algorithms can effectively exploit loop-carried stream reuse for scientific stream programs and thus greatly improve the performance of memory-bound scientific stream programs.
Compared with other stream applications, scientific stream programs are usually bound by memory accesses. Reusing streams across different iterations, i.e. loop-carried stream reuse, can effectively improve the SRF locality, thus reducing memory accesses greatly. In the paper, we first present the algorism identifying loop-carried stream reuse and that exploiting the reuse after analyzing scientific computing applications. We then perform several representative microbenchmarks and scientific stream programs with and without our optimization on Isim, a cycle-accurate stream processor simulator. Experimental results show that our algorithms can effectively exploit loop-carried stream reuse for scientific stream programs and thus greatly improve the performance of memory-bound scientific stream programs.
