The benefits and costs of DyC's run-time optimizations

DyC selectively dynamically compiles programs during their execution, utili zing the run-time-computed values of variables and data structures to apply optimizations that are based on partial evaluation. The dynamic optimizati ons are preplanned at static compile time in order to reduce their run-time cost; we call this staging. DyC's staged optimizations include (1) an adva nced binding-time analysis that supports polyvariant specialization (enabli ng both single-way and multiway complete loop unrolling), polyvariant divis ion, static loads, and static calls, (2) low-cost, dynamic versions of trad itional global optimizations, such as zero and copy propagation and dead-as signment elimination, and (3) dynamic peephole optimizations, such as stren gth. reduction. Because of this large suite of optimizations and its low dy namic compilation overhead, DyC achieves good performance improvements on p rograms that are larger and more complex than the kernels previously target ed by other dynamic compilation systems. This paper evaluates the benefits and costs of applying DyC's optimizations. We assess their impact on the pe rformance of a variety of small to medium-sized programs, both for the regi ons of code that are actually transformed and for the entire application as a whole. Our study includes an analysis of the contribution to performance of individual optimizations, the performance effect of changing the applic ations' inputs, and a detailed accounting of dynamic compilation costs.