Proposition d'un modèle pour l'optimisation automatique de boucles dans le compilateur Tiramisu : cas d'optimisation de déroulage
This work addresses the tedious and error-prone task of code optimization for developers using Tiramisu, though it appears incremental as it focuses on a single optimization case.
The authors tackled the problem of manually optimizing programs for complex computer architectures by proposing a neural network-based approach to automatically select the best loop unrolling factor in the Tiramisu compiler, achieving unspecified performance improvements.
Computer architectures become more and more complex. It requires more effort to develop techniques that improve the programs of performance and allow to exploit material resources efficiently. As a result, many transformations are applied on various levels of code abstraction. The first level is the high level, where the representation is close to the high level language. The second one is the low level, where the presentation is close to the machine code. Those transformations are called code optimizations. Optimizing programs requires deep expertise. On one hand, it is a tedious task, because it requires a lot of tests to find out the best combination of optimizations to apply with their best factors. On the other hand, this task is critical, because it may degrade the performance of the program instead of improving it. The automatization of this task can deal with this problem and permit to obtain good results. Our end of study project consists on proposing a novel approach based on neural networks to automatically optimize loops in Tiramisu. Tiramisu is a new language to create a code of high performance. It allows to separate between the algorithm and its optimizations. We have chosen loop unrolling as a study case. Our contribution aims to automate the choice of the best loop unrolling factor for a program written in Tiramisu.