@INPROCEEDINGS{langou2006,
author = {Julie Langou and Julien Langou and Piotr Luszczek and Jakub Kurzak and Alfredo Buttari and Jack Dongarra},
title = {Exploiting the performance of 32 bit floating point
arithmetic in obtaining 64 bit accuracy (revisiting
iterative refinement for linear systems)},
booktitle = {SC '06: Proceedings of the 2006 ACM/IEEE conference on Supercomputing},
year = {2006},
isbn = {0-7695-2700-0},
pages = {113},
location = {Tampa, Florida},
doi = {10.1145/1188455.1188573},
publisher = {ACM},
address = {New York, NY, USA},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_iterref.pdf}
}
@ARTICLE{Buttari:2008:UMP,
author = {Alfredo Buttari and Jack Dongarra and Jakub Kurzak and Piotr Luszczek and Stanimire Tomov},
title = {Using Mixed Precision for Sparse Matrix Computations to Enhance the Performance while Achieving
64-bit Accuracy},
journal = {{ACM} Transactions on Mathematical Software},
volume = {34},
number = {4},
year = {2008},
accepted = {5 July 2007},
upcoming = {true},
abstract = {By using a combination of 32-bit and 64-bit floating point arithmetic the performance of many
sparse linear algebra algorithms can be significantly enhanced while maintaining the 64-bit
accuracy of the resulting solution. These ideas can be applied to sparse multifrontal and
supernodal direct techniques and sparse iterative techniques such as Krylov subspace methods.
The approach presented here can apply not only to conventional processors but also to exotic
technologies such as Field Programmable Gate Arrays (FPGA), Graphical Processing Units (GPU),
and the Cell BE processor.},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_mumps_toms.pdf}
}
@ARTICLE{fastevpijcse,
author = {Gino Bella and Francesco del Citto and Salvatore Filippone and Alfredo Buttari and Alessandro de Maio},
title = {{FAST-EVP}: Parallel High Performance Computing in Engine Applications},
journal = {International Journal of Computational Science and Engineering (IJCSE)},
year = {2006},
note = {To appear.},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_fastevp2.pdf}
}
@INBOOK{handbook,
author = {J. Demmel et al.},
editor = {Sanguthevar Rajasekaran and John Reif },
title = {Handbook of Parallel Computing: Models, Algorithms and Applications},
chapter = {Prospectus for a Linear Algebra Software Library for Dense Matrix Problems},
publisher = {CRC Press},
isbn = {9781584886235},
year = {2007},
series = {Chapman \& Hall\/CRC Computer \& Information Science},
volume = {17},
edition = {1},
month = {December},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/bookchap_handbook.pdf}
}
@PHDTHESIS{buttari_thesis,
author = {Alfredo Buttari},
title = {Software Tools for Sparse Linear Algebra Computations},
school = {University of Rome Tor Vergata},
year = {2006},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/thesis.pdf}
}
@INPROCEEDINGS{para04,
author = {A. Buttari and P. D'Ambra and D. di Serafino and S. Filippone},
title = {{E}xtending {PSBLAS} to {B}uild {P}arallel {S}chwarz {P}reconditioners},
booktitle = {Applied Parallel Computing. State of the Art in Scientific Computing:
7th International Conference, PARA 2004, Lyngby, Denmark, June 20-23,
2004.},
doi = {10.1007/11558958\_71},
pages = {593-602},
editor = {Springer},
year = {2006},
month = {February},
volume = {3732},
series = {Lecture Notes in Computer Science},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_ext_PSBLAS.pdf}
}
@ARTICLE{twolevdd,
author = {Alfredo Buttari and Pasqua D'Ambra and Daniela di Serafino and Salvatore Filippone},
title = {{2LEV-D2P4}: a package of high-performance preconditioners for scientific and engineering applications},
journal = {Appl. Algebra Eng., Commun. Comput.},
volume = {18},
number = {3},
year = {2007},
issn = {0938-1279},
doi = {10.1007/s00200-007-0035-z},
pages = {223--239},
doi = {http://dx.doi.org/10.1007/s00200-007-0035-z},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_aaecc.pdf}
}
@INPROCEEDINGS{fastevp,
author = {G. Bella and A. Buttari and A. De Maio and F. Del Citto and S. Filippone and F. Gasperini},
title = {{FAST-EVP}: an Engine Simulation Tool},
booktitle = {High Perfromance Computing and Communications. First
International Conference, HPCC 2005, Proceedings},
pages = {976-986},
editor = {Springer},
year = {2005},
month = {September},
doi = {10.1007/11557654\_108},
volume = {3726},
series = {Lecture Notes in Computer Science},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_fastevp.pdf}
}
@TECHREPORT{scop3,
title = {{SCOP3}: A Rough Guide to Scientific Computing On the {P}lay{S}tation 3. Version 0.1},
author = {Alfredo Buttari and Piotr Luszczek and Jakub Kurzak and Jack Dongarra and George Bosilca},
institution = {Innovative Computing Laboratory, University of Tennessee Knoxville},
number = {UT-CS-07-595},
month = {April},
year = {2007},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_scop3.pdf}
}
@INPROCEEDINGS{ButtariDKLLT06,
author = {Alfredo Buttari and
Jack Dongarra and
Jakub Kurzak and
Julien Langou and
Piotr Luszczek and
Stanimire Tomov},
title = {The Impact of Multicore on Math Software},
booktitle = {PARA},
year = {2006},
pages = {1-10},
doi = {10.1007/978-3-540-75755-9_1},
bibsource = {DBLP, http://dblp.uni-trier.de},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_para06.pdf}
}
@INBOOK{grandinetti,
altauthor = {J. Buttari and J. Dongarra and J. Kurzak and J. Langou and J. Langou and P. Luszczek and S. Tomov},
title = {High Performance Computing and Grids in Action},
chapter = {Exploiting Mixed Precision Floating Point Hardware in Scientific Computations},
year = {2007},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/bookchap_grandinetti.pdf}
}
@INPROCEEDINGS{lapack-prospectus,
title = {Prospectus for the Next LAPACK and ScaLAPACK Libraries},
address = {Ume\aa, Sweden},
author = {James W. Demmel and Jack Dongarra and Beresford Parlett and
W. Kahan and Ming Gu and David Bindel and Yozo Hida
and Xiaoye S. Li and Osni A. Marques and E. Jason
Riedy and Christof Vömel and Julien Langou and Piotr
Luszczek and Jakub Kurzak and Alfredo Buttari and
Julie Langou and Stanimire Tomov},
booktitle = {PARA'06: State-of-the-Art in Scientific and Parallel Computing},
month = {June},
organization = {High Performance Computing Center North (HPC2N) and the Department of Computing Science, Ume\aa University},
publisher = {Springer},
year = {2006},
doi = {10.1007/978-3-540-75755-9\_2},
abstract = {LAPACK and ScaLAPACK are widely used software libraries
for numerical linear algebra. There have been over
68M web hits at www.netlib.org for the associated
libraries LAPACK, ScaLAPACK, CLAPACK and
LAPACK95. LAPACK and ScaLAPACK are used to solve
leading edge science problems and they have been
adopted by many vendors and software providers as
the basis for their own libraries, including AMD,
Apple (under Mac OS X), Cray, Fujitsu, HP, IBM,
Intel, NEC, SGI, several Linux distributions (such
as Debian), NAG, IMSL, the MathWorks (producers of
MATLAB), Interactive Supercomputing, and PGI. Future
improvements in these libraries will therefore have
a large impact on users.},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_prospectus.pdf}
}
@ARTICLE{chol_cell,
title = {Solving {S}ystems of {L}inear {E}quations on the {CELL} {P}rocessor {U}sing {C}holesky {F}actorization},
author = {Jakub Kurzak and Alfredo Buttari and Jack Dongarra},
journal = {{IEEE} Transactions on Parallel and Distributed Systems},
doi = {10.1109/TPDS.2007.70813},
year = {2007},
note = {To appear.},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/tech_cholcell.pdf}
}
@TECHREPORT{summa_cell,
title = {Limitations of the {P}lay{S}tation 3 for {H}igh {P}erformance {C}luster {C}omputing},
author = {Alfredo Buttari and Jakub Kurzak and Jack Dongarra},
institution = {Innovative Computing Laboratory, University of Tennessee Knoxville},
number = {{UT}-{CS}-07-597},
month = {April},
year = {2007},
note = {LAPACK Working Note 185.},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/tech_summacell.pdf}
}
@ARTICLE{blk_qr,
title = {{P}arallel {T}iled {QR} {F}actorization for {M}ulticore {A}rchitectures},
author = {Alfredo Buttari and Julien Langou and Jakub Kurzak and Jack Dongarra},
journal = {Concurrency and Computation: Practice and Experience},
year = {2007},
note = {To appear. LAPACK Working Note 190.},
pdf = {http://www.netlib.org/lapack/lawnspdf/lawn190.pdf}
}
@TECHREPORT{blk_algs,
title = {A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures.},
author = {Alfredo Buttari and Julien Langou and Jakub Kurzak and Jack Dongarra},
institution = {Innovative Computing Laboratory, University of Tennessee Knoxville},
number = {{UT}-{CS}-07-600},
month = {September},
year = {2007},
note = {{\bf Submitted to {\it \bf Parallel Computing journal}.} LAPACK Working Note 191.},
pdf = {http://www.netlib.org/lapack/lawnspdf/lawn191.pdf}
}
@ARTICLE{1297653,
author = {Alfredo Buttari and Jack Dongarra and Julie Langou and Julien Langou and Piotr Luszczek and Jakub Kurzak},
title = {Mixed Precision Iterative Refinement Techniques for the Solution of Dense Linear Systems},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {21},
number = {4},
year = {2007},
issn = {1094-3420},
pages = {457--466},
doi = {10.1177/1094342007084026},
publisher = {Sage Publications, Inc.},
address = {Thousand Oaks, CA, USA},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_pc_itref.pdf}
}
@ARTICLE{1297655,
author = {Alfredo Buttari and Victor Eijkhout and Julien Langou and Salvatore Filippone},
title = {Performance Optimization and Modeling of Blocked Sparse Kernels},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {21},
number = {4},
year = {2007},
issn = {1094-3420},
pages = {467--484},
doi = {10.1177/1094342007083801},
publisher = {Sage Publications, Inc.},
address = {Thousand Oaks, CA, USA},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_accels.pdf}
}
@INPROCEEDINGS{paper3,
author = {Alfredo Buttari and Jack Dongarra and Parry Husbands and Jakub Kurzak and Katherine Yelick},
authorurls = { and http://cscads.rice.edu/Members/dongarra and and and http://cscads.rice.edu/Members/yelick},
title = {Multithreading for Synchronization Tolerance in Matrix Factorization},
year = {2007},
doi = {10.1088/1742-6596/78/1/012028},
abstract = {Physical constraints such as power, leakage and pin
bandwidth are currently driving the HPC industry to
produce systems with unprecedented levels of
concurrency. In these parallel systems,
synchronization and memory operations are becoming
considerably more expensive than before. In this
work we study parallel matrix factorization codes
and conclude that they need to be re-engineered to
avoid unnecessary (and expensive)
synchronization. We propose the use of
multithreading combined with intelligent schedulers
and implement representative algorithms in this
style. Our results indicate that this strategy can
significantly outperform traditional codes.},
booktitle = {Proceedings of the SciDAC 2007 Conference},
publisher = {Journal of Physics: Conference Series},
address = {Boston, Massachusetts},
pdf = {http://icl.cs.utk.edu/~buttari/mypapers/paper_scidac.pdf}
}
@MANUAL{psbman,
title = {PSBLAS-2.0 User's Manual},
author = {A. Buttari and S. Filippone},
organization = {University of Rome Tor Vergata},
year = {2005},
pdf = {http://www.ce.uniroma2.it/psblas/userguide-2.1.pdf}
}
@MISC{cse,
author = {Jaku Kurzak and Alfredo Buttari and Piotr Luszczek and Jack Dongarra},
title = {The PlayStation 3 for High Performance Scientific Computing},
note = {to appear in Computing in Science and Engineering},
pdf = {http://www.netlib.org/netlib/utk/people/JackDongarra/PAPERS/ut-cs-08-608.pdf}
}
This file has been generated by bibtex2html 1.86.