8. Loop Transformations

To obtain better performance on a platform, code may need to be restructured relative to the way it is written (which is often for best readability). User-directed loop transformations accomplish this goal by providing a means to separate code semantics and its optimization.

A loop transformation construct states that a transformation operation is to be performed on set of nested loops. This directive approach can target specific loops for transformation, rather than applying more time-consuming general compiler heuristics methods with compiler options that may not be able to discover optimal transformations.

Loop transformations can be augmented by preprocessor support or OpenMP metadirective directives, to select optimal dimension and size parameters for specific platforms, facilitating a single code base for multiple platforms. Moreover, directive-based transformations make experimenting easier: whereby specific hot spots can be affected by transformation directives.