Download from:
http://www.nvidia.com/content/NV_Research/matrices.zip


More information about these matrices is available in the 
following paper by Williams et al.:

S. Williams, L. Oliker, R. Vuduc, J. Shalf, K. Yelick, J. Demmel, 
"Optimization of Sparse Matrix-Vector Multiplication on Emerging Multicore Platforms", 
Supercomputing (SC), 2007.
http://www.cs.berkeley.edu/~samw/research/papers/sc07.pdf



GPU performance results are available in this paper:

N. Bell and M. Garland
"Efficient Sparse Matrix-Vector Multiplication on CUDA"
Technical Report NVR-2008-004, NVIDIA Corporation, Dec. 2008
http://forums.nvidia.com/index.php?showtopic=83825


All matrices are stored in the MatrixMarket file format:
http://math.nist.gov/MatrixMarket/formats.html