Automated Phase-Ordering of Loop Optimizations Based on Polyhedron Model

Computer architectural complexity is growing so dramatically that auto-tuning application´s performance becomes an important approach to take full advantage of hardware´s computational potential. In this paper we present a polyhedron model based approach to improve program performance by automatically finding a good sequence of loop optimizations for each program respectively. This approach performs any legal sequence of loop optimizations outside existing compilers based on polyhedral model for program or its part. It evaluates program performance using hardware performance counters and a simplified cache miss equation. It finally produces a sequence to perform loop optimization for a program, or different sequences for different parts of a program. Experiments for SPEC CPU 2006 show that LI data cache miss rate can be decreased by 5%-21% while performance improved by up to 26% when compared with Open64 -03.