Understanding Unfulfilled Memory Reuse Potential in Scientific Applications

Abstract

The potential for improving the performance of data-intensive scientific programs by enhancing data reuse in cache is substantial because CPUs are significantly faster than memory. Traditional performance tools typically collect or simulate cache miss counts or rates and attribute them at the function level. While such information identifies program scopes that suffer from poor data locality, it is often insufficient to diagnose the causes for poor data locality and to identify what program transformations would improve memory hierarchy utilization. This paper describes a memory reuse distance based approach that identifies an application’s most significant memory access patterns causing cache misses and provides insight into ways of improving data reuse. We demonstrate the effectiveness of this analysis for two scientific codes: one for simulating neutron transport and a second for simulating turbulent transport in burning plasmas. Our tools pinpointed opportunities for enhancing data reuse. Using this feedback as a guide, we transformed the codes, reducing their misses at various levels of the memory hierarchy by integer factors and reducing their execution time by as much as 60% and 33%, respectively.