Title :
The Effect of Omitted-Variable Bias on the Evaluation of Compiler Optimizations
Author :
Mytkowicz, Todd ; Diwan, Amer ; Hauswirth, Matthias ; Sweeney, Peter F.
Author_Institution :
Univ. of Colorado at Boulder, Boulder, CO, USA
Abstract :
Experiments that do not account for all relevant variables can produce misleading results. The authors identify two variables that compiler optimization evaluations often omit, resulting in significant omittedvariable bias, and discuss how to identify new OVB sources and incorporate them in an experimental design.
Keywords :
optimisation; program compilers; OVB sources; compiler optimizations evaluation; omitted variable bias effect; Cities and towns; Computer performance; Computer science; Design for experiments; Design optimization; Hardware; Nominations and elections; Optimizing compilers; Program processors; Technological innovation; Cache memories; Computer performance; Design and test; Measurement errors; Omitted-variable bias;
DOI :
10.1109/MC.2010.214
