The following article covers all three versions: serial, shared-memory, and distributed-memory, with a little more emphasis on users aspects.
@article{li05,
AUTHOR = {Xiaoye S. Li},
TITLE = {An Overview of {SuperLU}: Algorithms, Implementation,
and User Interface},
journal = toms,
volume = {31},
number = {3},
month = {September},
year = {2005},
pages = {302-325},
}
If you use sequential SuperLU, please cite:
@article{superlu99,
author = {James W. Demmel and Stanley C. Eisenstat and
John R. Gilbert and Xiaoye S. Li and Joseph W. H. Liu},
title = {A supernodal approach to sparse partial pivoting},
journal = {SIAM J. Matrix Analysis and Applications},
year = {1999},
volume = {20},
number = {3},
pages = {720-755}
}
If you use SuperLU_MT (for shared-memory parallel machines),
please cite:
@article{superlu_smp99,
author = {James W. Demmel and John R. Gilbert and Xiaoye S. Li},
title = {An Asynchronous Parallel Supernodal Algorithm for
Sparse Gaussian Elimination},
journal = {SIAM J. Matrix Analysis and Applications},
volume = {20},
number = {4},
pages = {915-952},
year = {1999}
}
If you use SuperLU_DIST (for distributed-memory parallel machines),
please cite:
@article{lidemmel03,
author = {Xiaoye S. Li and James W. Demmel},
title = {{SuperLU_DIST}: A Scalable Distributed-Memory Sparse Direct
Solver for Unsymmetric Linear Systems},
journal = {ACM Trans. Mathematical Software},
month = {June},
volume = {29},
number = {2},
pages = {110-140},
year = 2003
}
If you use parallel symbolic factorization functionality in SuperLU_DIST,
please also cite:
@article{grigoridemmelli07,
Author = {Laura Grigori and James W. Demmel and Xiaoye S. Li},
Title = {Parallel Symbolic Factorization for Sparse {LU} with
Static Pivoting},
journal = {SIAM J. Scientific Computing},
volume = 29,
number = 3,
pages = {1289-1314},
year = 2007
}