generated from numpex/deliverable.template
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathreferences.bib
2014 lines (1792 loc) · 114 KB
/
references.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@article{trahay_exa-soft_nodate,
title = {Exa-{SofT} – performance analysis},
language = {en},
author = {Trahay, François},
}
@misc{cardosi_specx_2023,
title = {Specx: a {C}++ task-based runtime system for heterogeneous distributed architectures},
copyright = {Creative Commons Attribution 4.0 International},
shorttitle = {Specx},
url = {https://arxiv.org/abs/2308.15964},
doi = {10.48550/ARXIV.2308.15964},
abstract = {Parallelization is needed everywhere, from laptops and mobile phones to supercomputers. Among parallel programming models, task-based programming has demonstrated a powerful potential and is widely used in high-performance scientific computing. Not only does it allow for efficient parallelization across distributed heterogeneous computing nodes, but it also allows for elegant source code structuring by describing hardware-independent algorithms. In this paper, we present Specx, a task-based runtime system written in modern C++. Specx supports distributed heterogeneous computing by simultaneously exploiting CPUs and GPUs (CUDA/HIP) and incorporating communication into the task graph. We describe the specificities of Specx and demonstrate its potential by running parallel applications.},
urldate = {2024-10-15},
publisher = {arXiv},
author = {Cardosi, Paul and Bramas, Bérenger},
year = {2023},
note = {Version Number: 1},
keywords = {Distributed, Parallel, and Cluster Computing (cs.DC), FOS: Computer and information sciences, Software Engineering (cs.SE)},
}
@misc{Palazollo_Feel_Shape_Optimization,
title = {Feel++ shape optimization toolbox},
copyright = {LGPL-3.0-or-later},
url = {https://github.com/feelpp/feelpp-shapo},
author = {Palazollo, Lucas and Prud'homme, Christophe},
year = {2024},
}
@book{britain_standard_1990,
title = {The {Standard} {NAFEMS} {Benchmarks}},
publisher = {NAFEMS},
author = {Britain), National Agency for Finite Element Methods \& Standards (Great},
year = {1990},
}
@article{nguessan_high_2021,
series = {Numerical {Solution} of {Differential} and {Differential}-{Algebraic} {Equations}. {Selected} {Papers} from {NUMDIFF}-15},
title = {High order time integration and mesh adaptation with error control for incompressible {Navier}–{Stokes} and scalar transport resolution on dual grids},
volume = {387},
issn = {0377-0427},
url = {https://www.sciencedirect.com/science/article/pii/S0377042719305473},
doi = {10.1016/j.cam.2019.112542},
abstract = {Relying on a building block developed by the authors in order to resolve the incompressible Navier–Stokes equation with high order implicit time stepping and dynamic mesh adaptation based on multiresolution analysis with collocated variables, the present contribution investigates the ability to extend such a strategy for scalar transport at relatively large Schmidt numbers using a finer level of refinement compared to the resolution of the hydrodynamic variables, while preserving space adaptation with error control. This building block is a key part of a strategy to construct a low-Mach number code based on a splitting strategy for combustion applications, where several spatial scales are into play. The computational efficiency and accuracy of the proposed strategy is assessed on a well-chosen three-vortex simulation.},
urldate = {2024-10-15},
journal = {Journal of Computational and Applied Mathematics},
author = {N’Guessan, Marc-Arthur and Massot, Marc and Séries, Laurent and Tenaud, Christian},
month = may,
year = {2021},
keywords = {Dual grid with error control, Dynamic mesh adaptation, High order implicit Runge Kutta, Incompressible Navier–Stokes, Multiresolution analysis, Scalar transport},
pages = {112542},
}
@article{lecointre_hydrogen_nodate,
title = {Hydrogen flame acceleration in non-uniform mixtures},
abstract = {This thesis, carried out with the support of the CEA, presents the development of numerical methods dedicated to the simulation of the acceleration process of a hydrogen flame.},
language = {fr},
author = {Lecointre, Luc},
}
@article{duarte_adaptive_nodate,
title = {Adaptive numerical methods in time and space for the simulation of multi-scale reaction fronts.},
language = {fr},
author = {Duarte, Max Pedro},
}
@article{helbecque_parallel_2023,
title = {Parallel distributed productivity‐aware tree‐search using {Chapel}},
volume = {35},
issn = {1532-0626, 1532-0634},
url = {https://onlinelibrary.wiley.com/doi/10.1002/cpe.7874},
doi = {10.1002/cpe.7874},
abstract = {Abstract
With the recent arrival of the exascale era, modern supercomputers are increasingly big making their programming much more complex. In addition to performance, software productivity is a major concern to choose a programming language, such as Chapel, designed for exascale computing. In this paper, we investigate the design of a parallel distributed tree‐search algorithm, namely P3D‐DFS, and its implementation using Chapel. The design is based on the Chapel's
DistBag
data structure, revisited by: (1) redefining the data structure for Depth‐First tree‐Search (DFS), henceforth renamed
DistBag‐DFS
; (2) redesigning the underlying load balancing mechanism. In addition, we propose two instantiations of P3D‐DFS considering the Branch‐and‐Bound (B\&B) and Unbalanced Tree Search (UTS) algorithms. In order to evaluate how much performance is traded for productivity, we compare the Chapel‐based implementations of B\&B and UTS to their best‐known counterparts based on traditional OpenMP (intra‐node) and MPI+X (inter‐node). For experimental validation using 4096 processing cores, we consider the permutation flow‐shop scheduling problem for B\&B and synthetic literature benchmarks for UTS. The reported results show that P3D‐DFS competes with its OpenMP baselines for coarser‐grained shared‐memory scenarios, and with its MPI+X counterparts for distributed‐memory settings, considering both performance and productivity‐awareness. In the context of this work, this makes Chapel an alternative to OpenMP/MPI+X for exascale programming.},
language = {en},
number = {27},
urldate = {2024-10-15},
journal = {Concurrency and Computation: Practice and Experience},
author = {Helbecque, Guillaume and Gmys, Jan and Melab, Nouredine and Carneiro, Tiago and Bouvry, Pascal},
month = dec,
year = {2023},
pages = {e7874},
}
@incollection{franco_pgas_2024,
address = {Cham},
title = {{PGAS} {Data} {Structure} for {Unbalanced} {Tree}-{Based} {Algorithms} at {Scale}},
volume = {14834},
isbn = {978-3-031-63758-2 978-3-031-63759-9},
url = {https://link.springer.com/10.1007/978-3-031-63759-9_13},
language = {en},
urldate = {2024-10-15},
booktitle = {Computational {Science} – {ICCS} 2024},
publisher = {Springer Nature Switzerland},
author = {Helbecque, Guillaume and Carneiro, Tiago and Melab, Nouredine and Gmys, Jan and Bouvry, Pascal},
editor = {Franco, Leonardo and De Mulatier, Clélia and Paszynski, Maciej and Krzhizhanovskaya, Valeria V. and Dongarra, Jack J. and Sloot, Peter M. A.},
year = {2024},
doi = {10.1007/978-3-031-63759-9_13},
note = {Series Title: Lecture Notes in Computer Science},
pages = {103--111},
}
@article{gmys_exactly_2022,
title = {Exactly {Solving} {Hard} {Permutation} {Flowshop} {Scheduling} {Problems} on {Peta}-{Scale} {GPU}-{Accelerated} {Supercomputers}},
volume = {34},
issn = {1091-9856, 1526-5528},
url = {https://pubsonline.informs.org/doi/10.1287/ijoc.2022.1193},
doi = {10.1287/ijoc.2022.1193},
abstract = {Makespan minimization in permutation flow-shop scheduling is a well-known hard combinatorial optimization problem. Among the 120 standard benchmark instances proposed by E. Taillard in 1993, 23 have remained unsolved for almost three decades. In this paper, we present our attempts to solve these instances to optimality using parallel Branch-and-Bound (BB) on the GPU-accelerated Jean Zay supercomputer. We report the exact solution of 11 previously unsolved problem instances and improved upper bounds for eight instances. The solution of these problems requires both algorithmic improvements and leveraging the computing power of peta-scale high-performance computing platforms. The challenge consists in efficiently performing parallel depth-first traversal of a highly irregular and fine-grained search tree on distributed systems composed of hundreds of massively parallel accelerator devices and multicore processors. We present and discuss the design and implementation of our permutation-based BB and experimentally evaluate its parallel performance on up to 384 V100 GPUs (2 million CUDA cores) and 3840 CPU cores. The optimality proof for the largest solved instance requires about 64 CPU-years of computation—using 256 GPUs and over 4 million parallel search agents, the traversal of the search tree is completed in 13 hours, exploring [Formula: see text] nodes.},
language = {en},
number = {5},
urldate = {2024-10-15},
journal = {INFORMS Journal on Computing},
author = {Gmys, Jan},
month = sep,
year = {2022},
pages = {2502--2522},
}
@article{delorme_novel_nodate,
title = {{NOVEL} {NUMERICAL} {METHODS} {FOR} {SOLAR} {CONVECTION}: {THE} {DYABLO} {WHOLE}-{SUN} {ADAPTATIVE} {MESH} {REFINEMENT} {CODE}},
abstract = {We present a new solar simulation code named Dyablo Whole-Sun (DWS) and the first steps of its validation. DWS is a novel portable high-performance code aiming at making the first holistic simulations of the Sun, from the radiative interior to the corona. We discuss the validation of the development of the code using a solar convection benchmark in Cartesian geometry.},
language = {en},
author = {Delorme, M and Durocher, A and Brun, A S and Strugarek, A},
}
@article{dubey_survey_2014,
series = {Domain-{Specific} {Languages} and {High}-{Level} {Frameworks} for {High}-{Performance} {Computing}},
title = {A survey of high level frameworks in block-structured adaptive mesh refinement packages},
volume = {74},
issn = {0743-7315},
url = {https://www.sciencedirect.com/science/article/pii/S0743731514001178},
doi = {10.1016/j.jpdc.2014.07.001},
abstract = {Over the last decade block-structured adaptive mesh refinement (SAMR) has found increasing use in large, publicly available codes and frameworks. SAMR frameworks have evolved along different paths. Some have stayed focused on specific domain areas, others have pursued a more general functionality, providing the building blocks for a larger variety of applications. In this survey paper we examine a representative set of SAMR packages and SAMR-based codes that have been in existence for half a decade or more, have a reasonably sized and active user base outside of their home institutions, and are publicly available. The set consists of a mix of SAMR packages and application codes that cover a broad range of scientific domains. We look at their high-level frameworks, their design trade-offs and their approach to dealing with the advent of radical changes in hardware architecture. The codes included in this survey are BoxLib, Cactus, Chombo, Enzo, FLASH, and Uintah.},
number = {12},
urldate = {2024-10-14},
journal = {Journal of Parallel and Distributed Computing},
author = {Dubey, Anshu and Almgren, Ann and Bell, John and Berzins, Martin and Brandt, Steve and Bryan, Greg and Colella, Phillip and Graves, Daniel and Lijewski, Michael and Löffler, Frank and O’Shea, Brian and Schnetter, Erik and Van Straalen, Brian and Weide, Klaus},
month = dec,
year = {2014},
keywords = {BoxLib, Cactus, Chombo, Enzo, FLASH, SAMR, Uintah},
pages = {3217--3227},
}
@article{dubey_survey_2014-1,
series = {Domain-{Specific} {Languages} and {High}-{Level} {Frameworks} for {High}-{Performance} {Computing}},
title = {A survey of high level frameworks in block-structured adaptive mesh refinement packages},
volume = {74},
issn = {0743-7315},
url = {https://www.sciencedirect.com/science/article/pii/S0743731514001178},
doi = {10.1016/j.jpdc.2014.07.001},
abstract = {Over the last decade block-structured adaptive mesh refinement (SAMR) has found increasing use in large, publicly available codes and frameworks. SAMR frameworks have evolved along different paths. Some have stayed focused on specific domain areas, others have pursued a more general functionality, providing the building blocks for a larger variety of applications. In this survey paper we examine a representative set of SAMR packages and SAMR-based codes that have been in existence for half a decade or more, have a reasonably sized and active user base outside of their home institutions, and are publicly available. The set consists of a mix of SAMR packages and application codes that cover a broad range of scientific domains. We look at their high-level frameworks, their design trade-offs and their approach to dealing with the advent of radical changes in hardware architecture. The codes included in this survey are BoxLib, Cactus, Chombo, Enzo, FLASH, and Uintah.},
number = {12},
urldate = {2024-10-14},
journal = {Journal of Parallel and Distributed Computing},
author = {Dubey, Anshu and Almgren, Ann and Bell, John and Berzins, Martin and Brandt, Steve and Bryan, Greg and Colella, Phillip and Graves, Daniel and Lijewski, Michael and Löffler, Frank and O’Shea, Brian and Schnetter, Erik and Van Straalen, Brian and Weide, Klaus},
month = dec,
year = {2014},
keywords = {BoxLib, Cactus, Chombo, Enzo, FLASH, SAMR, Uintah},
pages = {3217--3227},
}
@article{cohen_fully_2003,
title = {Fully adaptive multiresolution finite volume schemes for conservation laws},
volume = {72},
issn = {0025-5718, 1088-6842},
url = {https://www.ams.org/mcom/2003-72-241/S0025-5718-01-01391-6/},
doi = {10.1090/S0025-5718-01-01391-6},
abstract = {Advancing research. Creating connections.},
language = {English},
number = {241},
urldate = {2024-10-14},
journal = {Mathematics of Computation},
author = {Cohen, Albert and Kaber, Sidi and Müller, Siegfried and Postel, Marie},
year = {2003},
keywords = {Conservation laws, adaptivity, finite volume schemes, multiresolution, wavelets.},
pages = {183--225},
}
@article{krah_wavelet_2022,
title = {Wavelet adaptive proper orthogonal decomposition for large-scale flow data},
volume = {48},
issn = {1572-9044},
url = {https://doi.org/10.1007/s10444-021-09922-2},
doi = {10.1007/s10444-021-09922-2},
abstract = {The proper orthogonal decomposition (POD) is a powerful classical tool in fluid mechanics used, for instance, for model reduction and extraction of coherent flow features. However, its applicability to high-resolution data, as produced by three-dimensional direct numerical simulations, is limited owing to its computational complexity. Here, we propose a wavelet-based adaptive version of the POD (the wPOD), in order to overcome this limitation. The amount of data to be analyzed is reduced by compressing them using biorthogonal wavelets, yielding a sparse representation while conveniently providing control of the compression error. Numerical analysis shows how the distinct error contributions of wavelet compression and POD truncation can be balanced under certain assumptions, allowing us to efficiently process high-resolution data from three-dimensional simulations of flow problems. Using a synthetic academic test case, we compare our algorithm with the randomized singular value decomposition. Furthermore, we demonstrate the ability of our method analyzing data of a two-dimensional wake flow and a three-dimensional flow generated by a flapping insect computed with direct numerical simulation.},
language = {en},
number = {2},
urldate = {2024-10-14},
journal = {Advances in Computational Mathematics},
author = {Krah, Philipp and Engels, Thomas and Schneider, Kai and Reiss, Julius},
month = feb,
year = {2022},
keywords = {Biorthogonal wavelets, Fluid dynamics, Proper orthogonal decomposition, Reduced order models, Wavelet adaptive block-based grids},
pages = {10},
}
@article{gillis_murphy---scalable_2022,
title = {{MURPHY}---{A} {Scalable} {Multiresolution} {Framework} for {Scientific} {Computing} on {3D} {Block}-{Structured} {Collocated} {Grids}},
volume = {44},
issn = {1064-8275},
url = {https://epubs.siam.org/doi/abs/10.1137/21M141676X},
doi = {10.1137/21M141676X},
abstract = {We present the lifting scheme, a simple construction of second generation wavelets; these are wavelets that are not necessarily translates and dilates of one fixed function. Such wavelets can be adapted to intervals, domains, surfaces, weights, and irregular samples. We show how the lifting scheme leads to a faster, in-place calculation of the wavelet transform. Several examples are included.},
number = {5},
urldate = {2024-10-14},
journal = {SIAM Journal on Scientific Computing},
author = {Gillis, Thomas and van Rees, Wim M.},
month = oct,
year = {2022},
note = {Publisher: Society for Industrial and Applied Mathematics},
pages = {C367--C398},
}
@article{zhang_amrex_2021,
title = {{AMReX}: {Block}-structured adaptive mesh refinement for multiphysics applications},
volume = {35},
issn = {1094-3420},
shorttitle = {{AMReX}},
url = {https://doi.org/10.1177/10943420211022811},
doi = {10.1177/10943420211022811},
abstract = {Block-structured adaptive mesh refinement (AMR) provides the basis for the temporal and spatial discretization strategy for a number of Exascale Computing Project applications in the areas of accelerator design, additive manufacturing, astrophysics, combustion, cosmology, multiphase flow, and wind plant modeling. AMReX is a software framework that provides a unified infrastructure with the functionality needed for these and other AMR applications to be able to effectively and efficiently utilize machines from laptops to exascale architectures. AMR reduces the computational cost and memory footprint compared to a uniform mesh while preserving accurate descriptions of different physical processes in complex multiphysics algorithms. AMReX supports algorithms that solve systems of partial differential equations in simple or complex geometries and those that use particles and/or particle–mesh operations to represent component physical processes. In this article, we will discuss the core elements of the AMReX framework such as data containers and iterators as well as several specialized operations to meet the needs of the application projects. In addition, we will highlight the strategy that the AMReX team is pursuing to achieve highly performant code across a range of accelerator-based architectures for a variety of different applications.},
language = {en},
number = {6},
urldate = {2024-10-14},
journal = {The International Journal of High Performance Computing Applications},
author = {Zhang, Weiqun and Myers, Andrew and Gott, Kevin and Almgren, Ann and Bell, John},
month = nov,
year = {2021},
note = {Publisher: SAGE Publications Ltd STM},
pages = {508--526},
}
@article{burstedde_p4est_2011,
title = {p4est: {Scalable} {Algorithms} for {Parallel} {Adaptive} {Mesh} {Refinement} on {Forests} of {Octrees}},
volume = {33},
issn = {1064-8275},
shorttitle = {p4est},
url = {https://epubs.siam.org/doi/abs/10.1137/100791634},
doi = {10.1137/100791634},
abstract = {In this article, we propose new parallel algorithms for the construction and 2:1 balance refinement of large linear octrees on distributed memory machines. Such octrees are used in many problems in computational science and engineering, e.g., object representation, image analysis, unstructured meshing, finite elements, adaptive mesh refinement, and N-body simulations. Fixed-size scalability and isogranular analysis of the algorithms using an MPI-based parallel implementation was performed on a variety of input data and demonstrated good scalability for different processor counts (1 to 1024 processors) on the Pittsburgh Supercomputing Center's TCS-1 AlphaServer. The results are consistent for different data distributions. Octrees with over a billion octants were constructed and balanced in less than a minute on 1024 processors. Like other existing algorithms for constructing and balancing octrees, our algorithms have \${\textbackslash}mathcal\{O\}(N{\textbackslash}log N)\$ work and \${\textbackslash}mathcal\{O\}(N)\$ storage complexity. Under reasonable assumptions on the distribution of octants and the work per octant, the parallel time complexity is \${\textbackslash}mathcal\{O\}({\textbackslash}frac\{N\}\{n\_p\}{\textbackslash}log({\textbackslash}frac\{N\}\{n\_p\})+n\_p{\textbackslash}log n\_p)\$, where N is the size of the final linear octree and \$n\_p\$ is the number of processors.},
number = {3},
urldate = {2024-10-14},
journal = {SIAM Journal on Scientific Computing},
author = {Burstedde, Carsten and Wilcox, Lucas C. and Ghattas, Omar},
month = jan,
year = {2011},
note = {Publisher: Society for Industrial and Applied Mathematics},
pages = {1103--1133},
}
@article{bellotti_numerical_nodate,
title = {Numerical analysis of lattice {Boltzmann} schemes: from fundamental issues to efficient and accurate adaptive methods},
language = {en},
author = {Bellotti, Thomas},
}
@article{bellotti_multiresolution-based_2022,
title = {Multiresolution-{Based} {Mesh} {Adaptation} and {Error} {Control} for {Lattice} {Boltzmann} {Methods} with {Applications} to {Hyperbolic} {Conservation} {Laws}},
volume = {44},
issn = {1064-8275},
url = {https://epubs.siam.org/doi/abs/10.1137/21M140256X},
doi = {10.1137/21M140256X},
abstract = {Lattice Boltzmann methods (LBM) stand out for their simplicity and computational efficiency while offering the possibility of simulating complex phenomena. While they are optimal for Cartesian meshes, adapted meshes have traditionally been a stumbling block since it is difficult to predict the right physics through various levels of meshes. In this work, we design a class of fully adaptive LBM methods with dynamic mesh adaptation and error control relying on multiresolution analysis. This wavelet-based approach allows us to adapt the mesh based on the regularity of the solution and leads to a very efficient compression of the solution without loosing its quality and with the preservation of the properties of the original LBM method on the finest grid. This yields a general approach for a large spectrum of schemes and allows precise error bounds, without the need for deep modifications on the reference scheme. An error analysis is proposed. For the purpose of validating this error analysis, we conduct a series of test cases for various schemes and scalar and systems of conservation laws, where solutions with shocks are to be found and local mesh adaptation is especially relevant. Theoretical estimates are retrieved while a reduced memory footprint is observed. It paves the way to an implementation in a multidimensional framework and high computational efficiency of the method for both parabolic and hyperbolic equations, which is the subject of a companion paper.
Keywords
lattice Boltzmann method
multiresolution analysis
wavelets
dynamic mesh adaptation
error control
hyperbolic conservation laws
MSC codes
76M28
65M50
42C40
65M12
35L65},
number = {4},
urldate = {2024-10-14},
journal = {SIAM Journal on Scientific Computing},
author = {Bellotti, Thomas and Gouarin, Loïc and Graille, Benjamin and Massot, Marc},
month = aug,
year = {2022},
note = {Publisher: Society for Industrial and Applied Mathematics},
pages = {A2599--A2627},
}
@article{bellotti_multidimensional_2022,
title = {Multidimensional fully adaptive lattice {Boltzmann} methods with error control based on multiresolution analysis},
volume = {471},
issn = {0021-9991},
url = {https://www.sciencedirect.com/science/article/pii/S0021999122007331},
doi = {10.1016/j.jcp.2022.111670},
abstract = {Lattice-Boltzmann methods are known for their simplicity, efficiency and ease of parallelization, usually relying on uniform Cartesian meshes with a strong bond between spatial and temporal discretization. This fact complicates the crucial issue of reducing the computational cost and the memory impact by automatically coarsening the grid where a fine mesh is unnecessary, still ensuring the overall quality of the numerical solution through error control. This work provides a possible answer to this interesting question, by connecting, for the first time, the field of lattice-Boltzmann Methods (LBM) to the adaptive multiresolution (MR) approach based on wavelets. To this end, we employ a MR multi-scale transform to adapt the mesh as the solution evolves in time according to its local regularity. The collision phase is not affected due to its inherent local nature and because we do not modify the speed of the sound, contrarily to most of the LBM/Adaptive Mesh Refinement (AMR) strategies proposed in the literature, thus preserving the original structure of any LBM scheme. Besides, an original use of the MR allows the scheme to resolve the proper physics by efficiently controlling the accuracy of the transport phase. We carefully test our method to conclude on its adaptability to a wide family of existing lattice Boltzmann schemes, treating both hyperbolic and parabolic systems of equations, thus being less problem-dependent than the AMR approaches, which have a hard time guaranteeing an effective control on the error. The ability of the method to yield a very efficient compression rate and thus a computational cost reduction for solutions involving localized structures with loss of regularity is also shown, while guaranteeing a precise control on the approximation error introduced by the spatial adaptation of the grid. The numerical strategy is implemented on a specific open-source platform called SAMURAI with a dedicated data-structure relying on set algebra.},
urldate = {2024-10-14},
journal = {Journal of Computational Physics},
author = {Bellotti, Thomas and Gouarin, Loïc and Graille, Benjamin and Massot, Marc},
month = dec,
year = {2022},
keywords = {Dynamic mesh adaptation, Error control, Hyperbolic systems of conservation laws, Incompressible Navier-Stokes equations, Lattice Boltzmann method, Multiresolution analysis},
pages = {111670},
}
@inproceedings{jamond_manta_2022,
address = {Giens, France},
title = {{MANTA} : un code {HPC} généraliste pour la simulation de problèmes complexes en mécanique},
shorttitle = {{MANTA}},
url = {https://hal.science/hal-03688160},
abstract = {Le code MANTA a l’ambition de permettre la réalisation de simulations complexes en mécanique sur des supercalculateurs actuels et futurs tout en préservant les fondamentaux des codes développés au CEA : adaptabilité au problème posé, robustesse des algorithmes, pérennité des modèles et du code. On expose les principes de développement de ce code de nouvelle génération, et quelques exemples représentatifs de ses capacités actuelles sont également décrits.},
urldate = {2024-10-14},
booktitle = {{CSMA} 2022 15ème {Colloque} {National} en {Calcul} des {Structures}},
author = {Jamond, Olivier and Lelong, Nicolas and Fourmont, Axel and Bluthé, Joffrey and Breuze, Matthieu and Bouda, Pascal and Brooking, Guillaume and Drui, Florence and Epalle, Alexandre and Fandeur, Olivier and Folzan, Gauthier and Helfer, Thomas and Kloss, Francis and Latu, Guillaume and Motte, Antoine and Nahed, Christopher and Picard, Alexis and Prat, Raphael and Ramière, Isabelle and Steins, Morgane and Prabel, Benoit},
month = may,
year = {2022},
keywords = {Code de calcul, Eléments finis, HPC, Implicite - explicite, Mécanique des fluides, Mécanique des structures, Toolbox, Volumes finis},
}
@inproceedings{jamond_manta_2024,
address = {Giens, France},
title = {{MANTA}: an industrial-strength open-source high performance explicit and implicit multi-physics solver},
shorttitle = {{MANTA}},
url = {https://hal.science/hal-04610968},
urldate = {2024-10-14},
booktitle = {16ème {Colloque} {National} en {Calcul} de {Structures}},
publisher = {CNRS, CSMA, ENS Paris-Saclay, CentraleSupélec},
author = {Jamond, Olivier and Lelong, Nicolas and Brooking, Guillaume and Helfer, Thomas and Prabel, Benoit and Prat, Raphael and Jaccon, Adrien},
month = may,
year = {2024},
keywords = {HPC, Industrial applications, PDEs solving, fluid mechanics, multiphysics coupling, structural mechanics},
}
@misc{noauthor_16eme_nodate,
title = {16ème {Colloque} {National} en {Calcul} de {Structures} - {Sciencesconf}.org},
url = {https://csma2024.sciencesconf.org/517460},
urldate = {2024-10-14},
}
@phdthesis{daver2016,
type = {phd},
title = {Reduced basis method applied to large non-linear multi-physics problems : application to high field magnets design},
url = {http://www.theses.fr/2016STRAD019},
author = {Daversin - Catty, Cécile},
year = {2016},
note = {tex.note+duplicate-1: 2016STRAD019},
}
@phdthesis{Hild2020,
type = {phd},
title = {Control and optimization of high magnetic fields},
url = {http://www.theses.fr/2020STRAD031},
author = {Hild, Romain},
year = {2020},
note = {tex.note+duplicate-1: 2020STRAD031},
}
@article{wang_fluid_2016,
title = {Fluid and structure coupling analysis of the interaction between aqueous humor and iris},
volume = {15},
issn = {1475-925X},
url = {http://biomedical-engineering-online.biomedcentral.com/articles/10.1186/s12938-016-0261-3},
doi = {10.1186/s12938-016-0261-3},
language = {en},
number = {S2},
urldate = {2024-10-14},
journal = {BioMedical Engineering OnLine},
author = {Wang, Wenjia and Qian, Xiuqing and Song, Hongfang and Zhang, Mindi and Liu, Zhicheng},
month = dec,
year = {2016},
pages = {133},
}
@book{ansorge_programming_2022,
edition = {1},
title = {Programming in {Parallel} with {CUDA}: {A} {Practical} {Guide}},
copyright = {https://www.cambridge.org/core/terms},
isbn = {978-1-108-85527-3 978-1-108-47953-0},
shorttitle = {Programming in {Parallel} with {CUDA}},
url = {https://www.cambridge.org/core/product/identifier/9781108855273/type/book},
abstract = {CUDA is now the dominant language used for programming GPUs, one of the most exciting hardware developments of recent decades. With CUDA, you can use a desktop PC for work that would have previously required a large cluster of PCs or access to a HPC facility. As a result, CUDA is increasingly important in scientific and technical computing across the whole STEM community, from medical physics and financial modelling to big data applications and beyond. This unique book on CUDA draws on the author's passion for and long experience of developing and using computers to acquire and analyse scientific data. The result is an innovative text featuring a much richer set of examples than found in any other comparable book on GPU computing. Much attention has been paid to the C++ coding style, which is compact, elegant and efficient. A code base of examples and supporting material is available online, which readers can build on for their own projects.},
language = {en},
urldate = {2024-10-11},
publisher = {Cambridge University Press},
author = {Ansorge, Richard},
month = may,
year = {2022},
doi = {10.1017/9781108855273},
}
@article{noauthor_cuda_nodate,
title = {{CUDA} {GRAPHS} in {GROMACS}},
language = {en},
}
@article{schoonover_mpi_nodate,
title = {{MPI}+ {Programming} with {HIP} and {OpenMP}},
language = {en},
author = {Schoonover, Dr Joe},
}
@article{edvalson_readthedocs-breathe_nodate,
title = {{ReadTheDocs}-{Breathe} {Documentation}},
language = {en},
author = {Edvalson, Thomas},
}
@article{maia_rocm_nodate,
title = {{ROCm}™ {Library} {Support} \& {Profiling} {Tools}},
language = {en},
author = {Maia, Julio and Chalmers, Noel and Bauman, Paul T and Curtis, Nicholas and Malaya, Nicholas and McDougall, Damon and van Oostrum, Rene},
}
@article{malavally_amd_nodate,
title = {{AMD} {HIP} {Programming} {Guide}},
language = {en},
author = {Malavally, Roopa},
}
@article{noauthor_use_nodate,
title = {Use {ROCm}™ on {Radeon}™ {GPUs} {Documentation}},
language = {en},
}
@article{edvalson_readthedocs-breathe_nodate-1,
title = {{ReadTheDocs}-{Breathe} {Documentation}},
language = {en},
author = {Edvalson, Thomas},
}
@article{noauthor_cuda_nodate-1,
title = {{CUDA} {C}++ {Programming} {Guide}},
}
@article{parks_recycling_2006,
title = {Recycling {Krylov} {Subspaces} for {Sequences} of {Linear} {Systems}},
volume = {28},
issn = {1064-8275, 1095-7197},
url = {http://epubs.siam.org/doi/10.1137/040607277},
doi = {10.1137/040607277},
language = {en},
number = {5},
urldate = {2024-10-11},
journal = {SIAM Journal on Scientific Computing},
author = {Parks, Michael L. and De Sturler, Eric and Mackey, Greg and Johnson, Duane D. and Maiti, Spandan},
month = jan,
year = {2006},
pages = {1651--1674},
}
@article{robbe_exact_2006,
title = {Exact and inexact breakdowns in the block {GMRES} method},
volume = {419},
copyright = {https://www.elsevier.com/tdm/userlicense/1.0/},
issn = {00243795},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0024379506002230},
doi = {10.1016/j.laa.2006.04.018},
language = {en},
number = {1},
urldate = {2024-10-11},
journal = {Linear Algebra and its Applications},
author = {Robbé, Mickaël and Sadkane, Miloud},
month = nov,
year = {2006},
pages = {265--285},
}
@unpublished{saigre_coupled_2024_paper,
type = {In preparation},
title = {A coupled fluid-dynamics-heat transfer model for {3D} simulations of the aqueous humor flow in the human eye},
abstract = {Understanding human eye behavior involves intricate interactions between physical phenomena such as heat transfer and fluid dynamics. Accurate computational models are vital for comprehending ocular diseases and therapeutic interventions.
This work focuses on modeling and simulating aqueous humor flow in the anterior and posterior chambers of the eye, coupled with overall heat transfer.
Aqueous humor dynamics regulates intraocular pressure, which is crucial for understanding conditions like glaucoma.
Convective effects from temperature disparities also influence this flow.
Extending prior research, this work develops a comprehensive three-dimensional computational model to simulate a coupled fluid-dynamic-heat transfer model, thus contributing to the understanding of ocular physiology.},
author = {Saigre, Thomas and Chabannes, Vincent and Prud'Homme, Christophe and Szopos, Marcela},
}
@inproceedings{jolivet_block_2016,
address = {Salt Lake City, Utah},
series = {{SC} '16},
title = {Block iterative methods and recycling for improved scalability of linear solvers},
isbn = {9781467388153},
abstract = {Contemporary large-scale Partial Differential Equation (PDE) simulations usually require the solution of large and sparse linear systems. Moreover, it is often needed to solve these linear systems with different or multiple Right-Hand Sides (RHSs). In this paper, various strategies will be presented to extend the scalability of existing multigrid or domain decomposition linear solvers using appropriate recycling strategies or block methods---i.e., by treating multiple right-hand sides simultaneously.The scalability of this work is assessed by performing simulations on up to 8,192 cores for solving linear systems arising from various physical phenomena modeled by Poisson's equation, the system of linear elasticity, or Maxwell's equation.This work is shipped as part of on open-source software, readily available and usable in any C/C++, Python, or Fortran code. In particular, some simulations are performed on top of a well-established library, PETSc, and it is shown how our approaches can be used to decrease time to solution down by 30\%.},
urldate = {2024-10-10},
booktitle = {Proceedings of the {International} {Conference} for {High} {Performance} {Computing}, {Networking}, {Storage} and {Analysis}},
publisher = {IEEE Press},
author = {Jolivet, Pierre and Tournier, Pierre-Henri},
month = nov,
year = {2016},
pages = {1--14},
}
@inproceedings{jolivet_scalable_2013,
address = {Denver Colorado},
title = {Scalable domain decomposition preconditioners for heterogeneous elliptic problems},
isbn = {9781450323789},
url = {https://dl.acm.org/doi/10.1145/2503210.2503212},
doi = {10.1145/2503210.2503212},
language = {en},
urldate = {2024-10-10},
booktitle = {Proceedings of the {International} {Conference} on {High} {Performance} {Computing}, {Networking}, {Storage} and {Analysis}},
publisher = {ACM},
author = {Jolivet, Pierre and Hecht, Frédéric and Nataf, Frédéric and Prud'homme, Christophe},
month = nov,
year = {2013},
pages = {1--11},
}
@article{jolivet_ksphpddm_2021,
title = {{KSPHPDDM} and {PCHPDDM}: {Extending} {PETSc} with advanced {Krylov} methods and robust multilevel overlapping {Schwarz} preconditioners},
volume = {84},
issn = {08981221},
shorttitle = {{KSPHPDDM} and {PCHPDDM}},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0898122121000055},
doi = {10.1016/j.camwa.2021.01.003},
language = {en},
urldate = {2024-10-10},
journal = {Computers \& Mathematics with Applications},
author = {Jolivet, Pierre and Roman, Jose E. and Zampini, Stefano},
month = feb,
year = {2021},
pages = {277--295},
}
@article{al_daas_multilevel_2021,
title = {A {Multilevel} {Schwarz} {Preconditioner} {Based} on a {Hierarchy} of {Robust} {Coarse} {Spaces}},
volume = {43},
issn = {1064-8275, 1095-7197},
url = {https://epubs.siam.org/doi/10.1137/19M1266964},
doi = {10.1137/19M1266964},
language = {en},
number = {3},
urldate = {2024-10-10},
journal = {SIAM Journal on Scientific Computing},
author = {Al Daas, Hussam and Grigori, Laura and Jolivet, Pierre and Tournier, Pierre-Henri},
month = jan,
year = {2021},
pages = {A1907--A1928},
}
@book{bernardi_mathematics_2024,
address = {Philadelphia, PA},
title = {Mathematics and {Finite} {Element} {Discretizations} of {Incompressible} {Navier}—{Stokes} {Flows}},
isbn = {9781611978117 9781611978124},
url = {https://epubs.siam.org/doi/book/10.1137/1.9781611978124},
language = {en},
urldate = {2024-10-09},
publisher = {Society for Industrial and Applied Mathematics},
author = {Bernardi, Christine and Girault, Vivette and Hecht, Frédéric and Raviart, Pierre-Arnaud and Rivière, Beatrice},
month = jan,
year = {2024},
doi = {10.1137/1.9781611978124},
}
@article{dapogny_geometrical_2018,
title = {Geometrical shape optimization in fluid mechanics using {FreeFem}++},
volume = {58},
issn = {1615-147X, 1615-1488},
url = {http://link.springer.com/10.1007/s00158-018-2023-2},
doi = {10.1007/s00158-018-2023-2},
language = {en},
number = {6},
urldate = {2024-10-09},
journal = {Structural and Multidisciplinary Optimization},
author = {Dapogny, Charles and Frey, Pascal and Omnès, Florian and Privat, Yannick},
month = dec,
year = {2018},
pages = {2761--2788},
}
@article{zhu_89-line_2021,
title = {An 89-line code for geometrically nonlinear topology optimization written in {FreeFEM}},
volume = {63},
issn = {1615-147X, 1615-1488},
url = {https://link.springer.com/10.1007/s00158-020-02733-x},
doi = {10.1007/s00158-020-02733-x},
language = {en},
number = {2},
urldate = {2024-10-09},
journal = {Structural and Multidisciplinary Optimization},
author = {Zhu, Benliang and Zhang, Xianmin and Li, Hai and Liang, Junwen and Wang, Rixin and Li, Hao and Nishiwaki, Shinji},
month = feb,
year = {2021},
pages = {1015--1027},
}
@article{sadaka_finite_2024,
title = {A finite element toolbox for the {Bogoliubov}-de {Gennes} stability analysis of {Bose}-{Einstein} condensates},
volume = {294},
issn = {00104655},
url = {https://linkinghub.elsevier.com/retrieve/pii/S001046552300293X},
doi = {10.1016/j.cpc.2023.108948},
language = {en},
urldate = {2024-10-09},
journal = {Computer Physics Communications},
author = {Sadaka, Georges and Kalt, Victor and Danaila, Ionut and Hecht, Frédéric},
month = jan,
year = {2024},
pages = {108948},
}
@article{golse_radiative_2023,
title = {Radiative transfer for variable three-dimensional atmospheres},
volume = {475},
issn = {00219991},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0021999122009275},
doi = {10.1016/j.jcp.2022.111864},
language = {en},
urldate = {2024-10-09},
journal = {Journal of Computational Physics},
author = {Golse, F. and Hecht, F. and Pironneau, O. and Smets, D. and Tournier, P.-H.},
month = feb,
year = {2023},
pages = {111864},
}
@article{li_three-dimensional_2022,
title = {Three-dimensional topology optimization of a fluid–structure system using body-fitted mesh adaption based on the level-set method},
volume = {101},
issn = {0307904X},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0307904X21003966},
doi = {10.1016/j.apm.2021.08.021},
language = {en},
urldate = {2024-10-09},
journal = {Applied Mathematical Modelling},
author = {Li, Hao and Kondoh, Tsuguo and Jolivet, Pierre and Furuta, Kozo and Yamada, Takayuki and Zhu, Benliang and Izui, Kazuhiro and Nishiwaki, Shinji},
month = jan,
year = {2022},
pages = {276--308},
}
@article{nataf_geneo_2024,
title = {A {GenEO} {Domain} {Decomposition} method for {Saddle} {Point} problems},
volume = {351},
issn = {1873-7234},
url = {https://comptes-rendus.academie-sciences.fr/mecanique/articles/10.5802/crmeca.175/},
doi = {10.5802/crmeca.175},
language = {en},
number = {S1},
urldate = {2024-10-09},
journal = {Comptes Rendus. Mécanique},
author = {Nataf, Frédéric and Tournier, Pierre-Henri},
month = apr,
year = {2024},
pages = {667--684},
}
@article{tournier_three-dimensional_2022,
title = {Three-dimensional finite-difference finite-element frequency-domain wave simulation with multi-level optimized additive {Schwarz} domain-decomposition preconditioner: {A} tool for {FWI} of sparse node datasets},
issn = {0016-8033, 1942-2156},
shorttitle = {Three-dimensional finite-difference finite-element frequency-domain wave simulation with multi-level optimized additive {Schwarz} domain-decomposition preconditioner},
url = {https://library.seg.org/doi/10.1190/geo2021-0702.1},
doi = {10.1190/geo2021-0702.1},
abstract = {Efficient frequency-domain full-waveform inversion (FWI) of long-offset node data can be designed with a few discrete frequencies, which lead to modest data volumes to be managed during the inversion process. Moreover, attenuation effects can be straightforwardly implemented in the forward problem without the computational overhead. However, 3D frequency-domain seismic modeling is challenging because it requires solving a large and sparse linear indefinite system for each frequency with multiple right-hand sides (RHSs). This linear system can be solved by direct or iterative methods. The former allows efficient processing of multiple RHSs but may suffer from limited scalability for very large problems. Iterative methods equipped with a domain-decomposition preconditioner provide a suitable alternative to process large computational domains for sparse-node acquisition. We have investigated the domain-decomposition preconditioner based on the optimized restricted additive Schwarz (ORAS) method, in which a Robin or perfectly matched layer condition is implemented at the boundaries between the subdomains. The preconditioned system is solved by a Krylov subspace method, whereas a block low-rank lower-upper decomposition of the local matrices is performed at a preprocessing stage. Multiple sources are processed in groups with a pseudoblock method. The accuracy, the computational cost, and the scalability of the ORAS solver are assessed against several realistic benchmarks. In terms of discretization, we compare a compact wavelength-adaptive 27-point finite-difference stencil on a regular Cartesian grid with a P
3
finite-element method on h-adaptive tetrahedral mesh. Although both schemes have comparable accuracy, the former is more computationally efficient, the latter being beneficial to comply with known boundaries such as bathymetry. The scalability of the method, the block processing of multiple RHSs, and the straightforward implementation of attenuation, which further improves the convergence of the iterative solver, make the method a versatile forward engine for large-scale 3D FWI applications from sparse node data sets.},
language = {en},
urldate = {2024-10-09},
journal = {GEOPHYSICS},
author = {Tournier, Pierre-Henri and Jolivet, Pierre and Dolean, Victorita and Aghamiry, Hossein S. and Operto, Stéphane and Riffo, Sebastian},
month = jul,
year = {2022},
pages = {1--84},
}
@article{tournier_numerical_2017,
title = {Numerical {Modeling} and {High}-{Speed} {Parallel} {Computing}: {New} {Perspectives} on {Tomographic} {Microwave} {Imaging} for {Brain} {Stroke} {Detection} and {Monitoring}},
volume = {59},
issn = {1558-4143},
shorttitle = {Numerical {Modeling} and {High}-{Speed} {Parallel} {Computing}},
url = {https://ieeexplore.ieee.org/abstract/document/8014422#:~:text=10.1109/MAP.2017.2731199},
doi = {10.1109/MAP.2017.2731199},
abstract = {This article deals with microwave tomography for brain stroke imaging using state-of-the-art numerical modeling and massively parallel computing. Iterative microwave tomographic imaging requires the solution of an inverse problem based on a minimization algorithm (e.g., gradient based) with successive solutions of a direct problem such as the accurate modeling of a whole-microwave measurement system. Moreover, a sufficiently high number of unknowns is required to accurately represent the solution. As the system will be used for detecting a brain stroke (ischemic or hemorrhagic) as well as for monitoring during the treatment, the running times for the reconstructions should be reasonable. The method used is based on high-order finite elements, parallel preconditioners from the domain decomposition method and domain-specific language with the opensource FreeFEM++ solver.},
number = {5},
urldate = {2024-10-09},
journal = {IEEE Antennas and Propagation Magazine},
author = {Tournier, Pierre-Henri and Bonazzoli, Marcella and Dolean, Victorita and Rapetti, Francesca and Hecht, Frederic and Nataf, Frederic and Aliferis, Iannis and El Kanfoud, Ibtissam and Migliaccio, Claire and de Buhan, Maya and Darbas, Marion and Semenov, Serguei and Pichot, Christian},
month = oct,
year = {2017},
keywords = {Antenna measurements, Boundary conditions, Brain modeling, Computational modeling, Finite element analysis, Tomography},
pages = {98--110},
}
@article{sadaka_parallel_2020,
title = {Parallel finite-element codes for the simulation of two-dimensional and three-dimensional solid–liquid phase-change systems with natural convection},
volume = {257},
issn = {00104655},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0010465520302319},
doi = {10.1016/j.cpc.2020.107492},
language = {en},
urldate = {2024-10-09},
journal = {Computer Physics Communications},
author = {Sadaka, Georges and Rakotondrandisa, Aina and Tournier, Pierre-Henri and Luddens, Francky and Lothodé, Corentin and Danaila, Ionut},
month = dec,
year = {2020},
pages = {107492},
}
@book{dolean_introduction_2015,
address = {Philadelphia, PA},
title = {An {Introduction} to {Domain} {Decomposition} {Methods}: {Algorithms}, {Theory}, and {Parallel} {Implementation}},
isbn = {9781611974058 9781611974065},
shorttitle = {An {Introduction} to {Domain} {Decomposition} {Methods}},
url = {http://epubs.siam.org/doi/book/10.1137/1.9781611974065},
language = {en},
urldate = {2024-10-09},
publisher = {Society for Industrial and Applied Mathematics},
author = {Dolean, Victorita and Jolivet, Pierre and Nataf, Frédéric},
month = nov,
year = {2015},
doi = {10.1137/1.9781611974065},
}
@book{hecht_pde-constrained_2024,
title = {{PDE}-constrained optimization within {FreeFEM}},
url = {https://hal.science/hal-04724788},
abstract = {This book is aimed at students and researchers who want to learn how to efficiently solve constrained optimization problems involving partial differential equations (PDE) using the FreeFEM software.},
urldate = {2024-10-09},
author = {Hecht, Frédéric and Lance, Gontran and Trélat, Emmanuel},
year = {2024},
}
@inproceedings{saigre_coupled_2024_abstract,
address = {Arlington (Virginia), United States},
title = {A coupled fluid-dynamics-heat transfer model for {3D} simulations of the aqueous humor flow in the human eye},
url = {https://hal.science/hal-04558924},
booktitle = {{CMBE24}},
author = {Saigre, Thomas and Prud'Homme, Christophe and Szopos, Marcela and Chabannes, Vincent},
month = jun,
year = {2024},
keywords = {Thermo-fluid dynamics, finite element method, mathematical and computational ophthalmology, thermo-fluid dynamics},
}
@article{giraud_block_2022,
title = {A {Block} {Minimum} {Residual} {Norm} {Subspace} {Solver} with {Partial} {Convergence} {Management} for {Sequences} of {Linear} {Systems}},
volume = {43},
issn = {0895-4798, 1095-7162},
url = {https://epubs.siam.org/doi/10.1137/21M1401127},
doi = {10.1137/21M1401127},
language = {en},
number = {2},
urldate = {2024-10-09},
journal = {SIAM Journal on Matrix Analysis and Applications},
author = {Giraud, Luc and Jing, Yan-Fei and Xiang, Yanfei},
month = jun,
year = {2022},
pages = {710--739},
}
@article{agullo_robust_2019,
title = {Robust {Preconditioners} via {Generalized} {Eigenproblems} for {Hybrid} {Sparse} {Linear} {Solvers}},
volume = {40},
issn = {0895-4798, 1095-7162},
url = {https://epubs.siam.org/doi/10.1137/17M1153765},
doi = {10.1137/17M1153765},
language = {en},
number = {2},
urldate = {2024-10-09},
journal = {SIAM Journal on Matrix Analysis and Applications},
author = {Agullo, Emmanuel and Giraud, Luc and Poirel, Louis},
month = jan,
year = {2019},
pages = {417--439},
}
@article{agullo_resiliency_2022,
title = {Resiliency in numerical algorithm design for extreme scale simulations},
volume = {36},
issn = {1094-3420, 1741-2846},
url = {https://journals.sagepub.com/doi/10.1177/10943420211055188},
doi = {10.1177/10943420211055188},
abstract = {This work is based on the seminar titled ‘Resiliency in Numerical Algorithm Design for Extreme Scale Simulations’ held March 1–6, 2020, at Schloss Dagstuhl, that was attended by all the authors. Advanced supercomputing is characterized by very high computation speeds at the cost of involving an enormous amount of resources and costs. A typical large-scale computation running for 48 h on a system consuming 20 MW, as predicted for exascale systems, would consume a million kWh, corresponding to about 100k Euro in energy cost for executing 10
23
floating-point operations. It is clearly unacceptable to lose the whole computation if any of the several million parallel processes fails during the execution. Moreover, if a single operation suffers from a bit-flip error, should the whole computation be declared invalid? What about the notion of reproducibility itself: should this core paradigm of science be revised and refined for results that are obtained by large-scale simulation? Naive versions of conventional resilience techniques will not scale to the exascale regime: with a main memory footprint of tens of Petabytes, synchronously writing checkpoint data all the way to background storage at frequent intervals will create intolerable overheads in runtime and energy consumption. Forecasts show that the mean time between failures could be lower than the time to recover from such a checkpoint, so that large calculations at scale might not make any progress if robust alternatives are not investigated. More advanced resilience techniques must be devised. The key may lie in exploiting both advanced system features as well as specific application knowledge. Research will face two essential questions: (1) what are the reliability requirements for a particular computation and (2) how do we best design the algorithms and software to meet these requirements? While the analysis of use cases can help understand the particular reliability requirements, the construction of remedies is currently wide open. One avenue would be to refine and improve on system- or application-level checkpointing and rollback strategies in the case an error is detected. Developers might use fault notification interfaces and flexible runtime systems to respond to node failures in an application-dependent fashion. Novel numerical algorithms or more stochastic computational approaches may be required to meet accuracy requirements in the face of undetectable soft errors. These ideas constituted an essential topic of the seminar. The goal of this Dagstuhl Seminar was to bring together a diverse group of scientists with expertise in exascale computing to discuss novel ways to make applications resilient against detected and undetected faults. In particular, participants explored the role that algorithms and applications play in the holistic approach needed to tackle this challenge. This article gathers a broad range of perspectives on the role of algorithms, applications and systems in achieving resilience for extreme scale simulations. The ultimate goal is to spark novel ideas and encourage the development of concrete solutions for achieving such resilience holistically.},
language = {en},
number = {2},
urldate = {2024-10-09},
journal = {The International Journal of High Performance Computing Applications},
author = {Agullo, Emmanuel and Altenbernd, Mirco and Anzt, Hartwig and Bautista-Gomez, Leonardo and Benacchio, Tommaso and Bonaventura, Luca and Bungartz, Hans-Joachim and Chatterjee, Sanjay and Ciorba, Florina M and DeBardeleben, Nathan and Drzisga, Daniel and Eibl, Sebastian and Engelmann, Christian and Gansterer, Wilfried N and Giraud, Luc and Göddeke, Dominik and Heisig, Marco and Jézéquel, Fabienne and Kohl, Nils and Li, Xiaoye Sherry and Lion, Romain and Mehl, Miriam and Mycek, Paul and Obersteiner, Michael and Quintana-Ortí, Enrique S and Rizzi, Francesco and Rüde, Ulrich and Schulz, Martin and Fung, Fred and Speck, Robert and Stals, Linda and Teranishi, Keita and Thibault, Samuel and Thönnes, Dominik and Wagner, Andreas and Wohlmuth, Barbara},
month = mar,
year = {2022},
pages = {251--285},
}
@article{agullo_soft_2020,
title = {On {Soft} {Errors} in the {Conjugate} {Gradient} {Method}: {Sensitivity} and {Robust} {Numerical} {Detection}},
volume = {42},
issn = {1064-8275, 1095-7197},
shorttitle = {On {Soft} {Errors} in the {Conjugate} {Gradient} {Method}},
url = {https://epubs.siam.org/doi/10.1137/18M122858X},
doi = {10.1137/18M122858X},
language = {en},
number = {6},
urldate = {2024-10-09},
journal = {SIAM Journal on Scientific Computing},
author = {Agullo, Emmanuel and Cools, Siegfried and Yetkin, Emrullah Fatih and Giraud, Luc and Schenkels, Nick and Vanroose, Wim},
month = jan,
year = {2020},
pages = {C335--C358},
}
@article{pham_assembling_2024,
title = {Assembling algorithm for {Green}'s tensors and absorbing boundary conditions for {Galbrun}'s equation in radial symmetry},
volume = {519},
issn = {0021-9991},
url = {https://www.sciencedirect.com/science/article/pii/S0021999124006922},
doi = {10.1016/j.jcp.2024.113444},
abstract = {Solar oscillations can be modeled by Galbrun's equation which describes Lagrangian wave displacement in a self-gravitating stratified medium. For spherically symmetric backgrounds, we construct an algorithm to compute efficiently and accurately the coefficients of the Green's tensor of the time-harmonic equation in vector spherical harmonic basis. With only two resolutions, our algorithm provides values of the kernels for all heights of source and receiver, and prescribes analytically the singularities of the kernels. We also derive absorbing boundary conditions (ABC) to model wave propagation in the atmosphere above the cut-off frequency. The construction of ABC, which contains varying gravity terms, is rendered difficult by the complex behavior of the solar potential in low atmosphere and for frequencies below the Lamb frequency. We carry out extensive numerical investigations to compare and evaluate the efficiency of the ABCs in capturing outgoing solutions. Finally, as an application towards helioseismology, we compute synthetic solar power spectra that contain pressure modes as well as internal-gravity (g-) and surface-gravity (f-) ridges which are missing in simpler approximations of the wave equation. For purpose of validation, the locations of the ridges in the synthetic power spectra are compared with observed solar modes.},
urldate = {2024-10-09},
journal = {Journal of Computational Physics},
author = {Pham, Ha and Faucher, Florian and Fournier, Damien and Barucq, Hélène and Gizon, Laurent},
month = dec,
year = {2024},
pages = {113444},
}
@book{elman_finite_2014,
address = {Oxford},
edition = {2. ed},
series = {Numerical mathematics and scientific computation},
title = {Finite elements and fast iterative solvers: with applications in incompressible fluid dynamics},
isbn = {978-0-19-967879-2},
shorttitle = {Finite elements and fast iterative solvers},
language = {eng},
publisher = {Oxford Univ. Press},
author = {Elman, Howard C. and Silvester, David J. and Wathen, Andrew J.},
year = {2014},
}
@article{prudhomme_reliable_2002,
title = {Reliable {Real}-{Time} {Solution} of {Parametrized} {Partial} {Differential} {Equations}: {Reduced}-{Basis} {Output} {Bound} {Methods}},
volume = {124},
issn = {0098-2202, 1528-901X},
shorttitle = {Reliable {Real}-{Time} {Solution} of {Parametrized} {Partial} {Differential} {Equations}},
url = {https://asmedigitalcollection.asme.org/fluidsengineering/article/124/1/70/462808/Reliable-RealTime-Solution-of-Parametrized-Partial},
doi = {10.1115/1.1448332},
abstract = {We present a technique for the rapid and reliable prediction of linear-functional outputs of elliptic (and parabolic) partial differential equations with affine parameter dependence. The essential components are (i) (provably) rapidly convergent global reduced-basis approximations—Galerkin projection onto a space WN spanned by solutions of the governing partial differential equation at N selected points in parameter space; (ii) a posteriori error estimation—relaxations of the error-residual equation that provide inexpensive yet sharp and rigorous bounds for the error in the outputs of interest; and (iii) off-line/on-line computational procedures methods which decouple the generation and projection stages of the approximation process. The operation count for the on-line stage in which, given a new parameter value, we calculate the output of interest and associated error bound, depends only on N (typically very small) and the parametric complexity of the problem; the method is thus ideally suited for the repeated and rapid evaluations required in the context of parameter estimation, design, optimization, and real-time control.},
language = {en},
number = {1},
journal = {Journal of Fluids Engineering},
author = {Prud’homme, C. and Rovas, D. V. and Veroy, K. and Machiels, L. and Maday, Y. and Patera, A. T. and Turinici, G.},
month = mar,
year = {2002},
pages = {70--80},
}
@article{Virieux2009,
title = {An overview of full-waveform inversion in exploration geophysics},
volume = {74},
doi = {10.1190/1.3238367},
number = {6},
journal = {Geophysics},
author = {Virieux, Jean and Operto, Stéphane},
year = {2009},
note = {Publisher: Society of Exploration Geophysicists},
pages = {WCC1--WCC26},
}
@article{Pham2020Siam,
title = {Efficient and accurate algorithm for the full modal {Green}'s kernel of the scalar wave equation in helioseismology},
volume = {80},
doi = {10.1137/20M1336709},
number = {6},
journal = {SIAM Journal on Applied Mathematics},
author = {Barucq, Hélène and Faucher, Florian and Fournier, Damien and Gizon, Laurent and Pham, Ha},
year = {2020},
pages = {2657--2683},
}
@article{Pham2019radiationBC,
title = {Outgoing solutions and radiation boundary conditions for the ideal atmospheric scalar wave equation in helioseismology},
volume = {54},
doi = {10.1051/m2an/2019088},
number = {4},
journal = {ESAIM: Mathematical Modelling and Numerical Analysis},
author = {Barucq, Hélène and Faucher, Florian and Pham, Ha},
year = {2020},
pages = {1111--1138},
}
@article{Liu2024,
title = {{WaveBench}: {Benchmarking} data-driven solvers for linear wave propagation {PDEs}},
issn = {2835-8856},
url = {https://openreview.net/forum?id=6wpInwnzs8},
journal = {Transactions on Machine Learning Research},
author = {Liu, Tianlin and Benitez, Jose Antonio Lara and Faucher, Florian and Khorashadizadeh, AmirEhsan and de Hoop, Maarten V. and Dokmanić, Ivan},
year = {2024},
}
@article{Benitez2024,
title = {Out-of-distributional risk bounds for neural operators with applications to the {Helmholtz} equation},
doi = {10.1016/j.jcp.2024.113168},
journal = {Journal of Computational Physics},
author = {Benitez, Jose Antonio Lara and Furuya, Takashi and Faucher, Florian and Kratsios, Anastasis and Tricoche, Xavier and de Hoop, Maarten V},
year = {2024},
note = {Publisher: Elsevier},
pages = {113168},
}
@article{Faucher2023viscoacoustic,
title = {Quantitative inverse problem in visco-acoustic media under attenuation model uncertainty},
volume = {472},
doi = {10.1016/j.jcp.2022.111685},
journal = {Journal of Computational Physics},
author = {Faucher, Florian and Scherzer, Otmar},
year = {2023},
note = {Publisher: Elsevier},
pages = {111685},
}
@article{Faucher2020DAS,
title = {Reciprocity-gap misfit functional for {Distributed} {Acoustic} {Sensing}, combining data from passive and active sources},
volume = {86},
issn = {0016-8033},
doi = {10.1190/geo2020-0305.1},
number = {2},
journal = {Geophysics},
author = {Faucher, Florian and De Hoop, Maarten V and Scherzer, Otmar},
year = {2020},
pages = {1--46},
}
@article{Faucher2020adjoint,
title = {Adjoint-state method for {Hybridizable} {Discontinuous} {Galerkin} discretization, application to the inverse acoustic wave problem},
volume = {372},
issn = {0045-7825},
doi = {10.1016/j.cma.2020.113406},
journal = {Computer Methods in Applied Mechanics and Engineering},
author = {Faucher, Florian and Scherzer, Otmar},
year = {2020},
pages = {113406},
}
@article{Faucher2019FRgWIGeo,
title = {Full {Reciprocity}-{Gap} {Waveform} {Inversion}, enabling sparse-source acquisition},
volume = {85},
doi = {10.1190/geo2019-0527.1},
number = {6},
journal = {Geophysics},
author = {Faucher, Florian and Alessandrini, Giovanni and Barucq, Hélène and de Hoop, Maarten and Gaburro, Romina and Sincich, Eva},
year = {2020},
note = {Publisher: Society of Exploration Geophysicists},
pages = {R461--R476},
}
@article{bonazzoli_domain_2019,
title = {Domain decomposition preconditioning for the high-frequency time-harmonic {Maxwell} equations with absorption},
volume = {88},
copyright = {https://www.ams.org/publications/copyright-and-permissions},
issn = {0025-5718, 1088-6842},
url = {https://www.ams.org/mcom/2019-88-320/S0025-5718-2019-03447-6/},
doi = {10.1090/mcom/3447},
language = {en},
number = {320},
urldate = {2024-10-08},
journal = {Mathematics of Computation},
author = {Bonazzoli, M. and Dolean, V. and Graham, I. G. and Spence, E. A. and Tournier, P.-H.},
month = may,
year = {2019},
pages = {2559--2604},
}
@article{noauthor_benchmarking_nodate,
title = {Benchmarking analysis report},
language = {en},
}
@book{asch_data_2016,
address = {Philadelphia, PA},
title = {Data assimilation},
url = {https://epubs.siam.org/doi/abs/10.1137/1.9781611974546},
publisher = {Society for Industrial and Applied Mathematics},
author = {Asch, Mark and Bocquet, Marc and Nodet, Maëlle},
year = {2016},
note = {Citation Key:
doi:10.1137/1.9781611974546
tex.eprint: https://epubs.siam.org/doi/pdf/10.1137/1.9781611974546},
}
@article{CRMATH_2009__347_7-8_435_0,
title = {Une méthode combinée d'éléments finis à deux grilles/bases réduites pour l'approximation des solutions d'une {E}.{D}.{P}. paramétrique},
volume = {347},
url = {http://www.numdam.org/articles/10.1016/j.crma.2009.02.019/},
doi = {10.1016/j.crma.2009.02.019},
language = {fr},
number = {7-8},
journal = {Comptes Rendus. Mathématique},
author = {Chakir, Rachida and Maday, Yvon},
year = {2009},
note = {Publisher: Elsevier},
pages = {435--440},
}
@article{noauthor_notitle_nodate,