Fast matrix multiplies using graphics hardware
Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599-3175 USA
In Supercomputing 01: Proceedings of the 2001 ACM/IEEE conference on Supercomputing (CDROM) (2001), pp. 55-55
@conference{larsen2001fast,
title={Fast matrix multiplies using graphics hardware},
author={Larsen, E.S. and McAllister, D.},
booktitle={Proceedings of the 2001 ACM/IEEE conference on Supercomputing (CDROM)},
pages={55},
isbn={158113293X},
year={2001},
organization={ACM}
}
We present a technique for large matrix-matrix multiplies using low cost graphics hardware. The result is computed by literally visualizing the computations of a simple parallel processing algorithm. Current graphics hardware technology has limited precision and thus limits immediate applicability of our algorithm. We include results demonstrating proof of concept, correctness, speedup, and a simple application. This is therefore forward looking research: a technique ready for technology on the horizon.
November 24, 2010 by hgpu
