1 % This file was created with JabRef 2.8.1.
4 @INCOLLECTION{ch5:Bajrovic2011,
5 author = {Bajrovic, E. and Traff, J.},
6 title = {Using {MPI} Derived Datatypes in Numerical Libraries},
7 booktitle = {Recent Advances in the Message Passing Interface},
8 publisher = {Springer Berlin / Heidelberg},
10 editor = {Cotronis, Y. and Danalis, A. and Nikolopoulos, D.
13 series = {Lecture Notes in Computer Science},
15 affiliation = {Faculty of Computer Science, University of Vienna, Nordbergstrasse
16 15/3C, A-1090 Vienna, Austria},
17 file = {Bajrovic2011.pdf:Bajrovic2011.pdf:PDF},
18 isbn = {978-3-642-24448-3},
19 keyword = {Computer Science},
21 timestamp = {2012.09.10},
22 url = {http://dx.doi.org/10.1007/978-3-642-24449-0_6}
25 @ARTICLE{ch5:Bell2011,
26 author = {N. Bell and J. Hoberock},
27 title = {Thrust: A Productivity-Oriented Library for {CUDA}},
28 journal = {In GPU Computing Gems, {\rm Jade Edition, Edited by Wen-mei W. Hwu. Elsevier Science}},
34 @ARTICLE{ch5:Engsig-Karup2011,
35 author = {Allan Peter Engsig-Karup and Morten Gorm Madsen and Stefan Lemvig
37 title = {A massively parallel GPU-accelerated model for analysis of fully
38 nonlinear free surface waves},
39 journal = {International Journal for Numerical Methods in Fluids},
42 timestamp = {2011.11.06}
46 title = {Design Patterns--Elements of Reusable Object-Oriented Software},
47 publisher = {Addison-Wesley Professional Computing Series},
49 author = {E. Gamma and R. Helm and R. Johnson and J. Vlissides},
51 timestamp = {2012.09.10}
55 title = {Using {MPI}: Portable Parallel Programming with the Message Passing
56 Interface, {\rm 2nd edition}},
57 publisher = {MIT Press},
59 author = {W. Gropp and E. Lusk and A. Skjellum},
60 address = {Cambridge, MA},
66 title = {Using {MPI-2}: Advanced Features of the Message-Passing Interface},
67 publisher = {MIT Press},
69 author = {William Gropp and Ewing Lusk and Rajeev Thakur},
70 address = {Cambridge, MA},
75 @INCOLLECTION{ch5:Hoefler2011,
76 author = {Hoefler, T. and Snir, M.},
77 title = {Writing Parallel Libraries with {MPI}--{C}ommon Practice, Issues, and
79 booktitle = {Recent Advances in the Message Passing Interface},
80 publisher = {Springer, Berlin/Heidelberg},
82 editor = {Cotronis, Y. and Danalis, A. and Nikolopoulos, D.
85 series = {Lecture Notes in Computer Science},
87 affiliation = {University of Illinois, Urbana, IL 61801, USA},
88 file = {Hoefler2011.pdf:Hoefler2011.pdf:PDF},
89 isbn = {978-3-642-24448-3},
90 keyword = {Computer Science},
92 timestamp = {2012.09.10},
93 url = {http://dx.doi.org/10.1007/978-3-642-24449-0_45}
96 @BOOK{ch5:LeVeque2007,
97 title = {Finite Difference Methods for Ordinary and Partial Differential Equations--Steady-state and Time-dependent Problems},
99 address = {Philadelphia, PA},
101 author = {R. J. LeVeque},
102 pages = {I-XV, 1-341},
103 bibsource = {DBLP, http://dblp.uni-trier.de},
104 ee = {http://www.ec-securehost.com/SIAM/OT98.html},
105 isbn = {978-0-89871-629-0}
108 @TECHREPORT{ch5:Skjellum1994,
109 author = {A. Skjellum and N. E. Doss and P. V. Bangaloret},
110 title = {Writing Libraries in {MPI}},
111 institution = {Department of Computer Science and NSF Engineering Research Center
112 for Computational Fiels Simulation. Mississippi State University},
114 file = {Skjellum1994.pdf:Skjellum1994.pdf:PDF},
115 type = {Technical {R}eport},
119 title = {Domain Decomposition: Parallel Multilevel Methods for Elliptic Partial
120 Differential Equations},
121 publisher = {Cambridge University Press},
123 author = {B. F. Smith and P. E. Bj{\o}rstad and W. D. Gropp},
124 address = {New York},
129 @BOOK{ch5:Vandevoorde2002,
130 title = {C++ Templates: The Complete Guide},
131 publisher = {Addison-Wesley Professional},
133 author = {D. Vandevoorde and N. M. Josuttis},
137 timestamp = {2011.07.15},
138 url = {http://www.amazon.com/Templates-Complete-Guide-David-Vandevoorde/dp/0201734842/ref=sr_1_3?ie=UTF8&qid=1310721621&sr=8-3}
141 @article{ch5:Korson1992,
142 author = {Korson, T. and McGregor, J. D.},
143 title = {Technical criteria for the specification and evaluation of object-oriented libraries},
144 journal = {Softw. Eng. J.},
145 issue_date = {March 1992},
153 url = {http://dx.doi.org/10.1049/sej.1992.0009},
154 doi = {10.1049/sej.1992.0009},
156 publisher = {Michael Faraday House},
157 address = {Herts, UK, UK},
160 @MISC{ch5:Acklam1998,
161 author = {Elizabeth Acklam and Hans Petter Langtangen and Hans Petter Langtangen and Are Magnus Bruaset},
162 title = {Parallelization of Explicit Finite Difference Schemes via Domain Decomposition},
166 @INPROCEEDINGS{ch5:Glimberg2011,
167 AUTHOR = {S. L. Glimberg and A. P. Engsig-Karup and M. G. Madsen},
168 TITLE = {A Fast GPU-accelerated Mixed-precision Strategy for Fully Nonlinear Water Wave Computations},
169 BOOKTITLE = {Numerical Mathematics and Advanced Applications 2011, Proceedings of ENUMATH 2011, the 9th European Conference on Numerical Mathematics and Advanced Applications, Leicester, September 2011},
171 editor = {A. Cangiani and R. L. Davidchack and E. Georgoulis and A.N. Gorban and J. Levesley and M. V. Tretyakov},
172 publisher = {Springer},
175 @techreport{ch5:Asanovic:EECS-2006-183,
176 Author = {Asanovic, K. and Bodik, R. and Catanzaro, B. C. and Gebis, J. J. and Husbands, P. and Keutzer, K. and Patterson, D. A. and Plishker, W. L. and Shalf, J. and Williams, S. W. and Yelick, K. A.},
177 Title = {The Landscape of Parallel Computing Research: A View from {B}erkeley},
178 Institution = {EECS Department, University of California, Berkeley},
181 Number = {UCB/EECS-2006-183},
184 @article{ch5:mooreslaw1965,
185 author = {Gordon E. Moore},
186 title = {Cramming more components onto integrated circuits},
187 journal = {Electronics},
194 @techreport{ch5:Kloeckner2011,
195 title = "{High-Order Discontinuous Galerkin Methods by GPU Metaprogramming}",
196 author = "A. Kloeckner, T. Warburton and J. S. Hesthaven",
197 institution = "Scientific Computing Group, Brown University",
199 address = "Providence, RI",
204 @book{ch5:Ferziger1996,
205 title={Computational Methods for Fluid Dynamics},
206 author={Ferziger, J.H. and Peri{\'c}, M.},
207 isbn={9783540594345},
209 series={Numerical Methods: Research and Development},
210 url={http://books.google.dk/books?id=SJkeAQAAIAAJ},
212 publisher={Springer-Verlag, Berlin Heidelberg New York}
215 @book{ch5:chorin1993,
216 title={A Mathematical Introduction to Fluid Mechanics},
217 author={Chorin, A. J. and Marsden, J. E.},
218 isbn={9780387979182},
220 series={Texts in Applied Mathematics},
221 url={http://books.google.dk/books?id=0Iglq1WA5PQC},
223 publisher={Springer, New York, NY},
230 title = {Iterative Methods for Sparse Linear Systems},
234 publisher = {Society for Industrial and Applied Mathematics},
235 address = {Philadelphia, PA},
238 @book{ch5:Kelley1995,
239 title={Iterative Methods for Linear and Nonlinear Equations},
240 author={Kelley, C. T.},
241 isbn={9780898713527},
243 series={Frontiers in Applied Mathematics Series},
244 url={http://books.google.dk/books?id=3J4XEAooQOoC},
246 publisher={Society for Industrial and Applied Mathematics, Philadelphia, PA,}
249 @techreport{ch5:YMTR08,
251 title = {The parareal in time algorithm},
252 institution = {Universite Pierr\'{e} et Marie Curie, Paris},
254 type = {Technical Report},
259 author = {M. Gander and S. Vandewalle},
260 title = {Analysis of the parareal time-parallel time-integration method},
261 journal = {SIAM Journal of Scientific Computing},
269 author = {J.-L. Lions and Y. Maday and G. Turinici},
270 title = {R\'{e}solution d'EDP par un sch\'{e}ma en temps parar\'{e}el},
271 journal = {C.R. Acad. Sci. Paris S\'{e}r. I Math},
278 title = {Parallel-in-time molecular-dynamics simulations},
279 author = {Baffico, L. and Bernard, S. and Maday, Y. and Turinici, G. and Z\'erah, G.},
280 journal = {Phys. Rev. E},
287 doi = {10.1103/PhysRevE.66.057701},
288 url = {http://link.aps.org/doi/10.1103/PhysRevE.66.057701},
289 publisher = {American Physical Society}
292 @mastersthesis{ch5:ASNP12,
293 author = {A. S. Nielsen},
294 title = {Feasibility study of the Parareal algorithm},
295 school = {Technical University of Denmark, Department of Informatics and Mathematical Modeling, Lyngby},
297 type = {Master Thesis}
301 author = {Aubanel, E.},
302 title = {Scheduling of tasks in the Parareal algorithm},
303 journal = {Parallel Computing},
309 @BOOK{ch5:Barrett1994,
310 AUTHOR = {R. Barrett and M. Berry and T. F. Chan and J. Demmel and J. Donato and J. Dongarra and V. Eijkhout and R. Pozo and C. Romine and H. Van der Vorst },
311 TITLE = {Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods},
315 ADDRESS = {Philadelphia, PA}
318 @TECHREPORT{ch5:ScientificGrandChallenges2010,
319 author = {D. L. Brown, P. Messina et. al},
320 title = {Scientific Grand Challenges, Crosscutting technologies for computing at the exascale},
321 institution = {U.S. Department of Energy},
324 address = {Washington, D.C.},
325 type = {Technical {R}eport},
328 @article{ch5:Keyes2011,
329 author = {D. E. Keyes},
330 title = {{Exaflop/s: The why and the how}},
331 journal = {Comptes Rendus Mecanique},
336 doi = {10.1016/j.crme.2010.11.002},
340 @ARTICLE{ch5:Cai2005,
341 author = {X. Cai and G.K. Pedersen and H.P. Langtangen},
342 title = {A parallel multi-subdomain strategy for solving Boussinesq water wave equations},
343 journal = {Elsevier - Advances in Water Resources},
349 @ARTICLE{ch5:GlimbergEtAl2012,
350 AUTHOR = {Stefan L. Glimberg and Allan P. Engsig-Karup},
351 TITLE = {On a Multi-GPU Implementation of a Free Surface Water Wave Model for Large-scale Simulations},
352 JOURNAL = {Submitted to: Special Issue of the Journal Parallel Computing},
354 volume = {7th Special Issue devoted to PMAA 2012},
358 author = {{NVIDIA Corporation}},
359 title = {{CUDA C} {P}rogramming {G}uide},
360 publisher = {NVIDIA Corporation},
362 url = {http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html}
365 @misc{ch5:cudapractice,
366 author = {{NVIDIA Corporation}},
367 title = {\rm {CUDA C} {B}est {P}ractices {G}uide},
368 publisher = {NVIDIA Corporation},
370 url = {http://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html}
373 @inproceedings{ch5:Bell2009,
374 author = {Bell, N. and Garland, M.},
375 title = {Implementing sparse matrix-vector multiplication on throughput-oriented processors},
376 booktitle = {SC '09: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis},
378 isbn = {978-1-60558-744-8},
380 location = {Portland, Oregon},
381 doi = {http://doi.acm.org/10.1145/1654059.1654078},
383 address = {New York, NY},
387 author = {Kirk, D. B. and Hwu, W.-M. W.},
388 title = {Programming Massively Parallel Processors: A Hands-on Approach},
390 isbn = {0123814723, 9780123814722},
391 publisher = {Morgan Kaufmann Publishers Inc.},
392 address = {San Francisco, CA},
395 @book{ch5:Trottenberg2001,
397 author={Trottenberg, U. and Oosterlee, C. W. and Sch{\"u}ller, A.},
398 isbn={9780127010700},
400 url={http://books.google.dk/books?id=9ysyNPZoR24C},
402 publisher={Elsevier Academic Press},