Semantic Polyhedral Model for Arrays and Lists

Abstract : The polyhedral model is a powerful reasonning framework that permits to optimize intensive computation kernels (piece of mperative code). However in this report we propose to define a “Semantic Polyhedral Model”, a formalisation of the main concepts on which the polyhedral model is built, from the notion of operation to data dependencies. This formulation, which is no longer based on syntactic computations but rather on semantic definitions, enables us to characterize the domain on which the polyhedral domain optimisations will apply. We also propose some extensions on programs with lists and memory sharing.
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01815759
Contributor : Laure Gonnord <>
Submitted on : Thursday, June 14, 2018 - 2:51:38 PM
Last modification on : Saturday, March 30, 2019 - 1:34:39 AM
Document(s) archivé(s) le : Saturday, September 15, 2018 - 2:16:44 PM

File

RR-9183.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01815759, version 1

Citation

Laure Gonnord, Paul Iannetta, Lionel Morel. Semantic Polyhedral Model for Arrays and Lists. [Research Report] RR-9183, Inria Grenoble Rhône-Alpes; UCBL; LIP - ENS Lyon; CEA List. 2018, pp.1-28. ⟨hal-01815759⟩

Share

Metrics

Record views

186

Files downloads

129