Automated timer generation for empirical tuning

Abstract. The performance of real world applications often critically depends on a few computationally intensive routines that are either in-voked numerous times by the application and/or include a significant number of loop iterations. It is desirable to separately study the perfor-mance of these critical routines, particularly in the context of automatic performance tuning, where a routine of interest is repetitively trans-formed using varying optimization strategies, and the performance of dif-ferent implementations is gathered to guide further optimizations. This paper presents a framework for automatically generating timing drivers that independently measure the performance of critical routines sepa-rately from their original applications. We show that the timing drivers can accurately replicate the performance of routines when invoked di-rectly within whole applications, thereby allowing critical routines to be correctly optimized in the context of empirical performance tuning.