C Language Extensions for Hybrid CPU/GPU Programming with StarPU
Inria, Bordeaux, France
arXiv:1304.0878 [cs.MS], 3 Apr 2013
@article{2013arXiv1304.0878C,
author={Court{‘e}s}, L.},
title={"{C Language Extensions for Hybrid CPU/GPU Programming with StarPU}"},
journal={ArXiv e-prints},
archivePrefix={"arXiv"},
eprint={1304.0878},
primaryClass={"cs.MS"},
keywords={Computer Science – Mathematical Software, Computer Science – Computational Engineering, Finance, and Science},
year={2013},
month={apr},
adsurl={http://adsabs.harvard.edu/abs/2013arXiv1304.0878C},
adsnote={Provided by the SAO/NASA Astrophysics Data System}
}
Modern platforms used for high-performance computing (HPC) include machines with both general-purpose CPUs, and "accelerators", often in the form of graphical processing units (GPUs). StarPU is a C library that addresses this problem by providing users with ways to define "tasks" to be executed on CPUs or GPUs, along with the dependencies among them, and by automatically scheduling them over all the available processing units. In doing so, it also relieves programmers from the need to know the underlying architecture details: it adapts to the available CPUs and GPUs, and automatically transfers data between main memory and GPUs as needed. While StarPU’s approach is successful at addressing run-time scheduling issues, being a C library makes for a poor and error-prone programming interface. This paper presents an effort started in 2011 to promote some of the concepts exported by the library as C language constructs, by means of an extension of the GCC compiler suite. Our main contribution is the design and implementation of language extensions that map to StarPU’s task programming paradigm. We argue that the proposed extensions make it easier to get started with StarPU,eliminate errors that can occur when using the C library, and help diagnose possible mistakes. We conclude on future work.
April 4, 2013 by hgpu
