Skip to Main content Skip to Navigation
Journal articles

Polyhedral Parallel Code Generation for CUDA

Sven Verdoolaege 1 Juan Carlos Juega 2 Albert Cohen 1 José Ignacio Gómez 2 Christian Tenllado 2 Francky Catthoor 3 
1 Parkas - Parallélisme de Kahn Synchrone
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR 8548
Abstract : This paper addresses the compilation of a sequential program for parallel execution on a modern GPU. To this end, we present a novel source-to-source compiler called PPCG. PPCG singles out for its ability to accelerate computations from any static control loop nest, generating multiple CUDA kernels when necessary. We introduce a multilevel tiling strategy and a code generation scheme for the parallelization and locality optimization of imperfectly nested loops, managing memory and exposing concurrency according to the constraints of modern GPUs. We evaluate our algorithms and tool on the entire PolyBench suite.
Document type :
Journal articles
Complete list of metadata
Contributor : Albert Cohen Connect in order to contact the contributor
Submitted on : Sunday, February 10, 2013 - 1:40:19 AM
Last modification on : Thursday, March 17, 2022 - 10:08:45 AM

Links full text




Sven Verdoolaege, Juan Carlos Juega, Albert Cohen, José Ignacio Gómez, Christian Tenllado, et al.. Polyhedral Parallel Code Generation for CUDA. ACM Transactions on Architecture and Code Optimization, Association for Computing Machinery, 2013, 9 (4), 54:1-23. ⟨10.1145/2400682.2400713⟩. ⟨hal-00786677⟩



Record views