Rewriting System for Profile-Guided Data Layout Transformations on Binaries

Olivier Aumage (1, 2) , Christopher Haine (1, 2) , Denis Barthou (1, 2, 3)

1 STORM - STatic Optimizations, Runtime Methods
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 Bordeaux INP - Institut Polytechnique de Bordeaux

Careful data layout design is crucial for achieving high performance. However exploring data layouts is time-consuming and error-prone, and assessing the impact of a layout transformation on performance is difficult without performing it. We propose to guide application programmers through data layout restructuring by providing a comprehensive multidimensional description of the initial layout, built from trace analysis, and then by giving a performance evaluation of the transformations tested and an expression of each transformed layout. The programmer can limit the exploration to layouts matching some patterns. We apply this method to two multithreaded applications. The performance prediction of multiple transformations matches within 5% the performance of hand-transformed layout code.

Mots clés: Memory Traces; Performance Tuning; Data Layout Restructuring

Domaines: Calcul parallèle, distribué et partagé [cs.DC]; Performance et fiabilité [cs.PF]

Olivier Aumage, Christopher Haine, Denis Barthou. Rewriting System for Profile-Guided Data Layout Transformations on Binaries. Euro-Par 2017 - 23rd International European Conference on Parallel and Distributed Computing, https://europar2017.usc.es/, Aug 2017, Santiago de Compostela, Spain. pp.260-272, ⟨10.1007/978-3-319-64203-1_19⟩. ⟨hal-01666179⟩