Register Deprivation Measurements

The development of register deprivation measurements was motivated by the desire to study the effect that register demand has on code improvement and register allocation strategies. In addition to the obvious application of testing the spill mechanism used by the compiler’s register allocator, the register deprivation strategy can be used to determine the relationship between the number of allocable registers and the effectiveness of a code improver as a whole or its optimization phases individually, enhance the coverage of validation suites, evaluate the register demands of benchmark suites and help machine designers determine the optimal number of registers needed to support existing compiler technologies. This paper contains a description of register deprivation techniques, presents some of their most useful applications, and discusses issues that must be addressed in order to incorporate this technique into a compiler. Also included are register deprivation measurement results obtained using a modest set of benchmarks that provide interesting and somewhat unexpected insights pertaining to optimizations, benchmark programs and architectures.