Data-reuse Optimizations for Pipelined Tiling with Parametric Tile Sizes

Alexandre Isoard 1
1 COMPSYS - Compilation and embedded computing systems
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Loop tiling is a loop transformation widely used to improve spatial and temporal data locality, to increase computation granularity, and to enable blocking algorithms, which are particularly useful when offloading kernels on platforms with small memories. When hardware caches are not available, data transfers and local storage must be software-managed, and some useless external communications can be avoided by exploiting data reuse between tiles. An important parameter of loop tiling is the sizes of the tiles, which impact the size of the required local memory. However, for most analyses involving several tiles, which is the case for inter-tile data reuse, the tile sizes induce non-linear constraints, unless they are numerical constants. This complicates or prevents a parametric analysis with polyhedral optimization techniques. This extended abstract shows that, when tiles are executed in sequence along tile axes, the parametric (with respect to tile sizes) analysis for inter-tile data reuse is nevertheless possible, i.e., one can determine, at compile-time and in a parametric fashion, the copy-in and copy-out data sets for all tiles, with inter-tile reuse, as well as sizes for the induced local memories. Combined with hierarchical tiling, this result opens new perspectives for the automatic generation, guided by parametric cost models, of blocking algorithms, where blocks can be pipelined and/or can contain parallelism. Previous work on FPGAs and GPUs already showed the interest and feasibility of such automation with tiling, but in a non-parametric fashion.
Type de document :
Poster
23rd International Conference on Parallel Architectures and Compilation Techniques (PACT'14), Aug 2014, Edmonton, Canada
Liste complète des métadonnées

https://hal.inria.fr/hal-01111393
Contributeur : Alexandre Isoard <>
Soumis le : vendredi 30 janvier 2015 - 11:53:16
Dernière modification le : vendredi 20 avril 2018 - 15:44:23
Document(s) archivé(s) le : samedi 15 avril 2017 - 23:56:07

Fichier

main.pdf
Fichiers produits par l'(les) auteur(s)

Poster (format A0)

Licence


Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-01111393, version 1

Collections

Citation

Alexandre Isoard. Data-reuse Optimizations for Pipelined Tiling with Parametric Tile Sizes. 23rd International Conference on Parallel Architectures and Compilation Techniques (PACT'14), Aug 2014, Edmonton, Canada. 〈hal-01111393〉

Partager

Métriques

Consultations de la notice

286

Téléchargements de fichiers

121