Compiler optimization plays a key role in unlocking the performance of the PA-8000, an innovative dynamically-scheduled machine which is the first implementation of the 64-bit PA 2.0 member of the HP PA-RISC architecture family. This wide superscalar, long out-of-order machine provides significant execution bandwidth and automatically hides latency at runtime; however despite its ample hardware resources, many of the optimizing transformations which proved effective for the PA-8000 served to augment its ability to exploit the available bandwidth and to hide latency. Further machine-specific factors influenced all levels of optimization to a degree without precedent in the set of previous PA-RISC processors. While legacy codes benefit from the PA-8000's sophisticated hardware, recompilation of old binaries can be vital to realizing the full potential of the PA-8000, given the impact of new compilers in achieving peak performance for this machine.

Equations representing the execution time performance of noninlined and inlined versions of a program have been developed. The accuracy of the equations' description of inlined program execution time behavior was demonstrated on four computer systems. Using the equations, understanding of how certain factors influence the speed of inlined code was gained. Contrary to a number of published reports in the literature, the increased size of inlined code was not found to affect its execution time performance on demand-paged virtual memory machines. On such systems, neither the use of an inlining algorithm that includes program size constraints nor the substitution of interprocedural data flow analysis for inlining is warranted. A modest improvement in the caching and paging behavior of test programs' inlined versions was also observed.>

Abstract Although the inline expansion of subprograms has often been cited as a method for improving a program's execution time, few available compilers perform the operation, and fewer still perform it without requiring explicit direction from the programmer. The authors have written a tool called INLINER, which is a source‐to‐source filter that automatically performs inline expansion of C functions in a module. With this tool, the effect of inlining was investigated using a set of programs on several machines. The authors' findings are presented, including an instance (unrelated to the size of the inlined executable) in which inlining can diminish a program's performance, and evidence that the size of the inlined executable does not, in practice, prove to cause problems.