Automatically generating and tuning GPU code for sparse matrix-vector multiplication from a high-level representation
Institute for Computing Systems Architecture, School of Informatics, University of Edinburgh, UK
In Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units (GPGPU2011) (March 2011)
@conference{grewe2011automatically,
title={Automatically generating and tuning GPU code for sparse matrix-vector multiplication from a high-level representation},
author={Grewe, D. and Lokhmotov, A.},
booktitle={Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units},
pages={12},
year={2011},
organization={ACM}
}
We propose a system-independent representation of sparse matrix formats that allows a compiler to generate efficient, system-specific code for sparse matrix operations. To show the viability of such a representation we have developed a compiler that generates and tunes code for sparse matrix-vector multiplication (SpMV) on GPUs. We evaluate our framework on six state-of-the-art matrix formats and show that the generated code performs similar to or better than hand-optimized code.
April 21, 2011 by hgpu
