utk.bib

@inproceedings{dplasma,
  OPTok={yes},
    author = {Bosilca, G. and Bouteiller, A. and Danalis, A. and Faverge, M. and Haidar, A. and Herault, T. and Kurzak, J. and Langou, J. and Lemarinier, P. and Ltaeif, H. and Luszczek, P. and YarKhan, A. and Dongarra, J. },
    title = "Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with {DPLASMA}",
    booktitle = {Proceedings of the Workshops of the 25th IEEE International Symposium on Parallel and Distributed Processing (IPDPSW 2011)}, 
    publisher = {IEEE}, 
    location = {Anchorage, Alaska, USA}, 
    pages = {1432-1441}, 
    month = {16-20 May},
    year = {2011},
}


@article{parsec,
  OPTok={yes},
title = "{DAGuE}: A generic distributed {DAG} engine for High Performance Computing ",
journal = "Parallel Computing ",
volume = "38",
number = "1-2",
pages = "37 - 51",
year = "2012",
note = "Extensions for Next-Generation Parallel Programming Models ",
issn = "0167-8191",
doi = "http://dx.doi.org/10.1016/j.parco.2011.10.003",
url = "http://www.sciencedirect.com/science/article/pii/S0167819111001347",
author = "George Bosilca and Aurelien Bouteiller and Anthony Danalis and Thomas Herault and Pierre Lemarinier and Jack Dongarra",
keywords = "\{HPC\}",
keywords = "Micro-task \{DAG\}",
keywords = "Heterogeneous architectures",
keywords = "Architecture aware scheduling",
}

@article{luszczek2006ctwq,
  OPTok={yes},
  Author = {Piotr Luszczek and Jack Dongarra and Jeremy Kepner},
  Journal = {Cyberinfrastructure Technology Watch, CT Watch Quarterly},
  Month = NOV,
  Number = {4A},
  Title = {Design and Implementation of the {HPCC} Benchmark Suite},
  Volume = 2,
  Year = 2006,
}

@incollection{Dongarra:2013:hpcc_history,
  OPTok={yes},
title={{HPC Challenge}: Design, History, and Implementation Highlights},
author={Jack Dongarra and Piotr Luszczek},
booktitle={Contemporary High Performance Computing: From Petascale Toward Exascale},
editor={Jefferey S. Vetter},
publisher={Taylor and Francis},
address={Boca Raton},
volume=1,
edition=1,
chapter=2,
pages={13-32},
series={CRC Computational Science Series},
year=2013,
}

@inproceedings{luszczek_2011_ppam,
  OPTok={yes},
title={Reducing the time to tune parallel dense linear algebra routines with partial execution and performance modelling},
author={Piotr Luszczek and Jack Dongarra},
booktitle={Proceedings of PPAM 2011 9th International Conference On Parallel Processing and Applied Mathematics},
address={Toru\'n, Poland},
month={September 11-14,},
year=2011,
}

@INPROCEEDINGS{Tomov_2009_iccs,
  OPTok={yes},
    author      = {{Li}, Y. and {Dongarra}, J. and {Tomov}, S.},
    title       = {A Note on Auto-tuning {GEMM} for {GPUs}},
    booktitle   = {Proceedings of the 2009 International Conference on Computational Science, ICCS'09},
    year        = 2009,
    month       = {May 25-27},
    address     = {Baton Roube, LA},
    publisher   = {Lecture Notes in Computer Science 5544},
    pages       = {884-892},
    note        = {\href{http://dx.doi.org/10.1007/978-3-642-01970-8\_89}{DOI:~10.1007/978-3-642-01970-8\_89}},
}

@INPROCEEDINGS{Kurzak_2010_para,
  OPTok={yes},
    author      = {{Kurzak}, J. and {Nath}, R. and {Du}, P. and {Dongarra}, J.~J.},
    title       = {An Implementation of the Tile {QR} Factorization for a {GPU} and Multiple {CPUs}},
    booktitle   = {Proceedings of the State of the Art in Scientific and Parallel Computing Conference, PARA'10},
    year        = 2010,
    month       = {June 6-9},
    address     = {Reykjav\'ik},
    publisher   = {Lecture Notes in Computer Science 7134},
    pages       = {248-257},
    note        = {\href{http://dx.doi.org/10.1007/978-3-642-28145-7}{DOI:~10.1007/978-3-642-28145-7}},
}

@INPROCEEDINGS{Tomov_2010_ipdps,
    author      = {{Tomov}, S. and {Nath}, R. and {Ltaief}, H. and {Dongarra}, J.},
    title       = {Dense Linear Algebra Solvers for Multicore with {GPU} Accelerators},
    booktitle   = {Proceedings of the 2010 IEEE International Parallel \& Distributed Processing Symposium, IPDPS'10},
    year        = 2010,
    month       = {April 19-23},
    address     = {Atlanta, GA},
    publisher   = {IEEE Computer Society},
    pages       = {1-8},
    note        = {\href{http://dx.doi.org/10.1109/IPDPSW.2010.5470941}{DOI:~10.1109/IPDPSW.2010.5470941}}
}

@ARTICLE{Tomov_2010_jhpca,
  OPTok={yes},
    author      = {{Nath}, R. and {Tomov}, S. and {Dongarra}, J.},
    title       = {An Improved {MAGMA} {GEMM} for {Fermi} Graphics Processing Units},
    journal     = {Int. J. High Perf. Comput. Applic.},
    year        = 2010,
    volume      = 24,
    number      = 4,
    pages       = {511-515},
    note        = {\href{http://dx.doi.org/10.1177/1094342010385729}{DOI:~10.1177/1094342010385729}}
}

@INPROCEEDINGS{Tomov_2010_vecpar,
  OPTok={yes},
    author      = {{Nath}, R. and {Tomov}, S. and {Dongarra}, J.},
    title       = {Accelerating {GPU} Kernels for Dense Linear Algebra},
    booktitle   = {Proceedings of the 2010 International Meeting on High Performance Computing
                   for Computational Science, VECPAR'10},
    year        = 2010,
    month       = {June 22-25},
    address     = {Berkeley, CA},
    publisher   = {Lecture Notes in Computer Science 6449},
    pages       = {83-92},
    note        = {\href{http://dx.doi.org/10.1007/978-3-642-19328-6\_10}{DOI:~10.1007/978-3-642-19328-6\_10}}
}

@article{Kurzak_2011_tpds,
author = {Jakub Kurzak and Stanimire Tomov and Jack Dongarra},
title = {Autotuning GEMM Kernels for the Fermi GPU},
journal ={IEEE Transactions on Parallel and Distributed Systems},
volume = {23},
number = {11},
issn = {1045-9219},
year = {2012},
pages = {2045-2057},
doi = {http://doi.ieeecomputersociety.org/10.1109/TPDS.2011.311},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
note        = {\url{www.netlib.org/lapack/lawnspdf/lawn245.pdf} (accepted to IEEE TPDS)}
}

@ARTICLE{Kurzak_2012_tpds,
  OPTok={yes},
    author      = {{Kurzak}, J. and {Luszczek}, P. and {Faverge}, M. and {Dongarra}, J.},
    title       = {{LU} Factorization with Partial Pivoting for a Multicore System with Accelerators},
    journal     = {IEEE Trans. Parallel Distrib. Syst.},
    note        = {\href{http://dx.doi.org/10.1109/TPDS.2012.242}{DOI:~10.1109/TPDS.2012.242}},
    year        = 2013,
    volume = 24,
    number = 8,
    pages = {1613-1621},
    month = aug,

}

@article{jia2012multi,
  OPTok={yes},
  author = {Jia, Yulu and Luszczek, Piotr and Dongarra, Jack},
        title = {Multi-{GPU} Implementation of {LU} Factorization.},
  journal = {Procedia CS},
  pages = {106-115},
  volume = {9},
  year = {2012}
}

@article {blkd:ccpe:08,
  OPTok={yes},
author = {Buttari, Alfredo and Langou, Julien and Kurzak, Jakub and Dongarra, Jack},
title = {Parallel tiled {QR} factorization for multicore architectures},
journal = {Concurrency and Computation: Practice and Experience},
volume = 20,
number = 13,
publisher = {John Wiley \& Sons, Ltd.},
issn = {1532-0634},
url = {http://dx.doi.org/10.1002/cpe.1301},
doi = {10.1002/cpe.1301},
pages = {1573--1590},
keywords = {multicore, linear algebra, QR factorization},
year = 2008,
}

@phdthesis{Petitet:1996:Algorithmic-redistribution,
  OPTok={yes},
        Author = {Petitet, Antoine Paul},
        Isbn = {0-591-45140-9},
        Order_No = {AAI9735349},
        Publisher = {The University of Tennessee},
        Title = {Algorithmic redistribution methods for block cyclic decompositions},
        Year = 1996,
}

@phdthesis{petitet1996,
  OPTok={yes},
        Address = {Knoxville, Tennessee},
        Author = {Petitet, Antoine Paul},
        Month = {December},
        Note = {PhD dissertation, Major Professor-Dongarra, Jack},
        School = {University of Tennessee},
        Title = {Algorithmic Redistribution Methods for Block Cyclic Decompositions},
        Type = {{C}omputer {S}cience {D}epartment},
        Year = 1996,
}

@inproceedings{ma:2011:dist_coll,
  OPTok={yes},
author = {Ma, T. and Herault, T. and Bosilca, G. and Dongarra, J.},
title = {Process Distance-aware Adaptive {MPI} Collective Communications},
booktitle = "IEEE Int'l Conference on Cluster Computing (Cluster 2011)",
address = {Austin, TX},
month = {September},
year = 2011,
}

@inproceedings{pjesivac-grbovic:2007:mpi_coll,
  OPTok={yes},
  author={Pjesivac-Grbovic, J. and Bosilca, G. and Fagg, G. and Angskun, T. and Dongarra, J.},
  title={Decision Trees and {MPI} Collective Algorithm Selection Problem},
  booktitle={Euro-Par 2007},
  publisher={Springer},
  address={Rennes, France},
  pages={105-115},
  month={August},
  year=2007,
}

@Misc{plasmawebsite,
  OPTok={yes},
  key={PLASMA},
  title =        {The {PLASMA} website},
  howpublished = {\url{http://icl.cs.utk.edu/plasma/}}
}

@TECHREPORT{kogge:exascale-hw,
  author = {Peter Kogge and Keren Bergman and Shekhar Borkar and Dan Campbell and William Carlson and William Dally and Monty Denneau and Paul Franzon and William Harrod and Kerry Hill and Jon Hiller and Sherman Karp and Stephen Keckler and Dean Klein and Robert Lucas and Mark Richards and Al Scarpelli and Steven Scott and Allan Snavely and Thomas Sterling and R. Stanley Williams and Katherine Yelick },
  title = {Exascale {C}omputing {S}tudy: Technology {C}hallenges in {A}chieving
	{E}xascale {S}ystems},
  institution = {DARPA},
  year = {2008},
  note = {{Available: }\url{http://users.ece.gatech.edu/mrichard/ExascaleComputingStudyReports/exascale_final_report_100208.pdf}}
}