GURRR - A GLOBAL UNIFIED RESOURCE REQUIREMENTS REPRESENTATION

When compiling for instruction level parallelism (ILP), the integratio n of the optimization phases can lead to an improvement in the quality of code generated. However, since several different representations o f a program are used in the various phases, only a partial integration has been achieved to date. We present a program representation that c ombines resource requirements and availability information with contro l and data dependence information. The representation enables the inte gration of several optimizing phases, including transformations, regis ter allocation, and instruction scheduling. The basis of this integrat ion is the simultaneous allocation of different types of resources. We define the representation and show how it is constructed. We then for mulate several optimization phases to use the representation to achiev e better integration.