Data Locality Optimization Based on Comprehensive Knowledge of the Cache Miss Reason: A Case Study with DWT

The overall performance of a computing system increasingly depends on the efficient use of the cache memories. Traditional approaches for cache tuning deploy performance tools to help the user optimize the source program towards a better runtime data locality. Following this conventional way, we developed a set of such toolkits including data profiling, pattern analysis, and performance visualization tools. This paper demonstrates how the toolset can be used step-by-step to understand the cache access behavior of the applications and then achieve optimized program code. The Discrete Wavelet Transform, a common used algorithm for image and video compression, is applied as an example. Our initial experimental results with this sample application show an up to 3.19 speedup in execution time compared to the original implementation.