Extensive Parameterization And Tuning of Architecture-Sensitive Optimizations

The complexity of modern architectures require compilers to apply an increasingly large collection of architecturesensitive optimizations, e.g., parallelization and cache optimizations, which interact with each other in unpredictable ways. We present a framework to support fine-grained parameterization of these optimizations and flexible tuning of their configuration space. Instead of directly generating optimized code, we extend an optimizing compiler to output its optimization decisions in POET, a scripting language designed for extensive parameterization of source-to-source program transformations. We then use a transformation-aware (TA) search algorithm to support flexible tuning of the parameterized transformation scripts to achieve portable high performance. We have used our framework to apply 6 highly interactive optimizations, parallelization via OpenMP, cache blocking, array copying, unroll-and-jam, scalar replacement, and loop unrolling, and present results of exploring their combined configuration space