1 @manual{cudabestpractices,
2 TITLE = {{NVIDIA {CUDA C} Best Practices Guide 4.0}},
3 organization = {NVIDIA},
6 howpublished = "\url{http://docs.nvidia.com/cuda/pdf/CUDA_C_Best_Practices_Guide.pdf}",
10 author = {A. Frommer and D. B. Szyld},
12 title = {On Asynchronous Iterations},
13 journal = {J. Comput. and Appl. Math.},
20 author = {D. P. Bertsekas and J. N. Tsitsiklis},
22 title = {Parallel and Distributed Computation},
23 publisher = {Prentice Hall},
25 address = {Englewood Cliffs, New Jersey},
29 author = {Vialle, S. and Contassot-Vivier, S. and Jost, T.},
30 editor = {Sanjay Ranka and Ishfag Ahmad},
31 title = {Handbook of Energy-Aware and Green Computing},
32 chapter = {Optimizing Computing and Energy Performances in Heterogeneous Clusters of CPUs and GPUs},
33 publisher = {Chapman and Hall/CRC},
35 url = {http://www.crcpress.com/product/isbn/9781466501164#},
36 isbn = {9781466501164},
40 series = {Computer \& Information Science Series},
50 author = {S. Vialle and S. Contassot-Vivier},
51 editor = {Magoul\'{e}s, Fr\'{e}d\'{e}ric},
52 title = {Patterns for parallel programming on {G}{P}{U}s},
53 chapter = {Optimization methodology for Parallel Programming of Homogeneous or Hybrid Clusters},
54 publisher = {Saxe-Coburg Publications},
56 isbn = {978-1-874672-57-9},
57 url = {http://www.saxe-coburg.co.uk/pubs/future.htm},
62 author = {Bahi, J. M. and Contassot-Vivier, S. and Couturier, R.},
63 title = {Parallel Iterative Algorithms: From Sequential to Grid Computing},
64 publisher = {Chapman \& Hall/CRC},
66 series = {Numerical Analysis \& Scientific Computing Series},
67 OPTdoi = {http://www.crcpress.com/shopping_cart/products/product_detail.asp?sku=C808X&isbn=9781584888086&parent_id=&pc=},
70 @InProceedings{HPCS2002,
71 author = {Bahi, J. M. and Contassot-Vivier, S. and Couturier, R.},
72 title = {Asynchronism for Iterative Algorithms in a Global Computing Environment},
73 booktitle = {The 16th Annual International Symposium on High Performance
74 Computing Systems and Applications (HPCS'2002)},
77 address = {Moncton, New-Brunswick, Canada},
81 @InProceedings{Vecpar08a,
82 author = {Bahi, J. M. and Contassot-Vivier, S. and Couturier, R.},
83 title = {An efficient and robust decentralized algorithm for detecting the global
84 convergence in asynchronous iterative algorithms},
85 booktitle = {8th International Meeting on High Performance Computing for Computational Science, VECPAR'08},
88 address = {Toulouse, France},
93 author = {Bahi, J. M. and Contassot-Vivier, S. and Couturier, R.},
94 title = {Evaluation of the Asynchronous Iterative Algorithms in the Context of Distant Heterogeneous Clusters},
95 journal = {Parallel Computing},
102 @InProceedings{ECost10,
103 author = {Contassot-Vivier, S. and Vialle, S. and Jost, T.},
104 title = {Optimizing computing and energy performances on {GPU} clusters: experimentation on a {PDE} solver},
105 booktitle = {COST Action IC0804 on Large Scale Distributed Systems,1st Year},
108 editor = {Jean-Marc Pierson and Helmut Hlavacs},
109 organization = {IRIT},
110 note = {ISBN: 978-2-917490-10-5},
114 author = {Bahi, J. M. and Contassot-Vivier, S. and Couturier, R.},
115 title = {Performance comparison of parallel programming environments for implementing {AIAC} algorithms},
116 journal = {Journal of Supercomputing. Special Issue on Performance Modelling and Evaluation of Parallel and Distributed Systems},
123 @InProceedings{Para10,
124 author = {Contassot-Vivier, S. and Jost, T. and Vialle, S.},
125 title = {Impact of asynchronism on {GPU} accelerated parallel iterative computations},
126 booktitle = {PARA 2010 Conference: State of the Art in Scientific and Parallel Computing},
129 address = {Reykjavík, Iceland},
133 @InProceedings{ECost10,
134 author = {Contassot-Vivier, S. and Vialle, S. and Jost, T.},
135 title = {Optimizing computing and energy performances on {GPU} clusters: experimentation on a {PDE} solver},
136 booktitle = {COST Action IC0804 on Large Scale Distributed Systems,1st Year},
139 editor = {Jean-Marc Pierson and Helmut Hlavacs},
140 organization = {IRIT},
141 note = {ISBN: 978-2-917490-10-5},
144 @InCollection{JCVV10,
145 author = {T. Jost and S. Contassot-Vivier and S. Vialle},
146 title = {An efficient multi-algorithm sparse linear solver for {GPU}s},
147 booktitle = {Parallel Computing : From Multicores and GPU's to Petascale},
149 publisher = {IOS Press},
154 series = {Advances in Parallel Computing},
161 OPTannote = {Extended version of EuroGPU symposium article, in the International Conference on Parallel Computing (ParCo) 2009}
164 @InProceedings{ParCo09,
165 author = {T. Jost and S. Contassot-Vivier and S. Vialle},
166 title = {An efficient multi-algorithms sparse linear solver for {GPU}s},
167 booktitle = {EuroGPU mini-symposium of the International Conference on Parallel Computing, ParCo'2009},
174 @InProceedings{BCVG11,
175 author = {Bahi, J. M. and Contassot-Vivier, S. and Giersch, A.},
176 title = {Load Balancing in Dynamic Networks by Bounded Delays Asynchronous Diffusion},
177 booktitle = {VECPAR 2010},
180 editor = {J.M.L.M. Palma et al.},
184 publisher = {Springer, Heidelberg},
185 note = "\url{DOI:~10.1007/978-3-642-19328-6\33}"
189 title = {{NVIDIA {CUDA} C Programming Guide 4.0}},
190 organization = {NVIDIA},
191 howpublished = "\url{http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf}",
197 title = {Open Source High Performance Computing},
198 howpublished = {\url{http://www.open-mpi.org}}
202 title = {Message Passing Interface},
203 howpublished = {\url{http://www.mpi-forum.org/docs}}
207 title = {Open{M}{P} multi-threaded programming {API}},
208 howpublished = {\url{http://www.openmp.org}}
211 @inproceedings{Hoefler08a,
212 author = {T. Hoefler and A. Lumsdaine},
213 title = {Overlapping Communication and Computation with High Level Communication Routines},
214 booktitle = {IEEE International Symposium on Cluster Computing and the Grid},
217 note = "\url{http://doi.ieeecomputersociety.org/10.1109/CCGRID.2008.15}",
218 publisher = {IEEE Computer Society},
219 address = {Lyon, France},
220 isbn = {978-0-7695-3156-4},
223 @Article{Valiant:BSP,
224 author = {Valiant, L. G.},
225 title = {A bridging model for parallel computation},
226 journal = {Communications of the ACM},
233 @inproceedings{gustedt:hal-00639289,
234 AUTHOR = {Gustedt, J. and Jeanvoine, E.},
235 TITLE = {{Relaxed synchronization with ordered read-write locks}},
236 BOOKTITLE = {{Euro-Par 2011: Parallel Processing Workshops}},
240 EDITOR = {Michael Alexander and others},
241 PUBLISHER = {Springer},
244 ADDRESS = {Bordeaux, France},
245 X-INTERNATIONAL-AUDIENCE = {yes},
246 X-PROCEEDINGS = {yes},
247 URL = {http://hal.inria.fr/hal-00639289},
248 X-ID-HAL = {hal-00639289},
251 @article{clauss:2010:inria-00330024:1,
252 AUTHOR = {Clauss, P.-N. and Gustedt, J.},
253 TITLE = {{Iterative computations with ordered read-write locks}},
254 JOURNAL = {{Journal of Parallel and Distributed Computing}},
255 PUBLISHER = {Elsevier},
260 DOI = {10.1016/j.jpdc.2009.09.002},
261 X-INTERNATIONAL-AUDIENCE = {yes},
262 X-EDITORIAL-BOARD = {yes},
263 URL = {http://hal.inria.fr/inria-00330024/en},
264 X-ID-HAL = {inria-00330024},
267 @inproceedings{GUSTEDT:2007:HAL-00280094:1,
268 TITLE = {The par{X}{X}{L} Environment: Scalable Fine Grained Development for Large Coarse Grained Platforms},
270 X-INTERNATIONAL-AUDIENCE = {yes},
271 AUTHOR = {Gustedt, J. AND Vialle, S. AND De Vivo, A.},
272 BOOKTITLE = {PARA 06},
273 LONG-BOOKTITLE = {PARA 06: Worshop on state-of-the-art in scientific and parallel computing },
274 EDITOR = {Bo K{\aa}gstr{\"o}m and others},
275 PAGES = {1094-1104 },
276 ADDRESS = {Ume{\aa}, Sweden},
278 PUBLISHER = {Springer},
281 URL = {http://hal-supelec.archives-ouvertes.fr/hal-00280094/en/},
282 X-PROCEEDINGS = {yes},
285 @InProceedings{suss04:users_exper,
286 author = {S\"{u}{\ss}, Michael and Leopold, Claudia},
287 title = {A User's Experience with Parallel Sorting and {O}pen{M}{P}},
288 booktitle = {Proceedings of the 6th European Workshop on OpenMP (EWOMP)},
291 editor = {Eduard Ayguad\'{e} and others},
292 address = {Stockholm, Sweden}}
296 editor = {International standardization working group for the programming language C},
297 title = {Programming Languages -- C},
298 publisher = {ISO/IEC},
301 edition = {Cor. 1:2012}