Section: New Results

Code-Bones for Fast and Flexible Runtime Code Generation

Participants : Juan Manuel Martinez Caamaño, Artiom Baloian, Philippe Clauss.

We have developed a new runtime code generation technique for speculative loop optimization and parallelization. The main benefit of this technique, compared to previous approaches, is to enable advanced optimizing loop transformations at runtime with an acceptable time overhead. The loop transformations that may be applied are those handled by the polyhedral model. The proposed code generation strategy is based on the generation of code-bones at compile-time, which are parametrized code snippets either dedicated to speculation management or to computations of the original target program. These code bones are then instantiated and assembled at runtime to constitute the speculatively-optimized code, as soon as an optimizing polyhedral transformation has been determined. Their granularity threshold is sufficient to apply any polyhedral transformation, while still enabling fast runtime code generation. This approach has been implemented in the speculative loop parallelizing framework Apollo, and published at the conference Euro-Par 2016 where it has been selected as best paper [13]. An extended journal version is currently under review. This is also the main contribution of Juan Manuel Martinez Caamaño's PhD thesis which was defended in September 2016 [8].