Multi-target C++ implementation of parallel skeletons

Wilfried Kirschenmann (1, 2) , Laurent Plagne (1) , Stéphane Vialle (2, 3)

1 EDF - EDF
2 ALGORILLE - Algorithms for the Grid
3 SUPELEC-Campus Metz

This paper presents the design of an efficient multi-target (CPU+GPU) implementation for the Parallel_for skeleton. Emerging massively parallel architectures promise very high performances for a low cost. However, these architectures change faster than ever. Thus, optimization of codes becomes a very complex and time consumming task. We have identified the data storage as the main difference between the CPU and the GPU implementation of a code. We introduce an abstract data layout in order to adapt the data storage. Based on this layout, the utilization of Parallel_for skeleton allows to compile and execute the same program both on CPU and on GPU. Once compiled, the program runs close to the hardware limits.

Domains: Distributed, Parallel, and Cluster Computing [cs.DC]

Wilfried Kirschenmann, Laurent Plagne, Stéphane Vialle. Multi-target C++ implementation of parallel skeletons. 8th workshop on Parallel/High-Performance Object-Oriented Scientific Computing - POOSC'09, Jul 2009, Genova, Italy. pp.1-10, ⟨10.1145/1595655.1595662⟩. ⟨hal-00437542⟩