forked from christophmschaefer/miluphcuda
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtimeintegration.cu
1617 lines (1490 loc) · 80.5 KB
/
timeintegration.cu
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
/**
* @author Christoph Schaefer [email protected] and Thomas I. Maindl
*
* @section LICENSE
* Copyright (c) 2019 Christoph Schaefer
*
* This file is part of miluphcuda.
*
* miluphcuda is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* miluphcuda is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with miluphcuda. If not, see <http://www.gnu.org/licenses/>.
*
*/
#include "boundary.h"
#include "timeintegration.h"
#include "tree.h"
#include "porosity.h"
#include "pressure.h"
#include "plasticity.h"
#include "soundspeed.h"
#include "parameter.h"
#include "io.h"
#include "xsph.h"
#include "miluph.h"
#include "aneos.h"
#include "linalg.h"
#include "density.h"
#include "rhs.h"
#include "viscosity.h"
#include "float.h"
pthread_t fileIOthread;
double L_ini = 0.0;
double *matSml_d;
int *matnoi_d;
int *matEOS_d;
double *matPolytropicK_d;
double *matPolytropicGamma_d;
double *matAlpha_d;
double *matBeta_d;
double *matBulkmodulus_d;
double *matShearmodulus_d;
double *matYieldStress_d;
double *matInternalFriction_d;
double *matInternalFrictionDamaged_d;
double *matRho0_d;
double *matTillRho0_d;
double *matTillEiv_d;
double *matTillEcv_d;
double *matTillE0_d;
double *matTilla_d;
double *matTillb_d;
double *matTillA_d;
double *matTillB_d;
double *matTillAlpha_d;
double *matTillBeta_d;
double *matRhoLimit_d;
double *matN_d;
double *matCohesion_d;
double *matFrictionAngle_d;
double *matFrictionAngleDamaged_d;
double *matAlphaPhi_d;
double *matCohesionCoefficient_d;
// viscosity coefficients for Navier-Stokes
double *matnu_d;
double *matzeta_d;
#if ARTIFICIAL_STRESS
double *matexponent_tensor_d;
double *matepsilon_stress_d;
double *matmean_particle_distance_d;
__constant__ double *matexponent_tensor;
__constant__ double *matepsilon_stress;
__constant__ double *matmean_particle_distance;
// material stress parameters / material specific -> needed for ARTIFICIAL_STRESS
double *exponent_tensor;
double *epsilon_stress;
double *mean_particle_distance;
#endif
double *mat_f_sml_min_d;
double *mat_f_sml_max_d;
__constant__ double *mat_f_sml_min;
__constant__ double *mat_f_sml_max;
//begin ANEOS device variables (in global and constant memory)
int *aneos_n_rho_d;
int *aneos_n_e_d;
double *aneos_bulk_cs_d;
double *aneos_rho_d;
double *aneos_e_d;
double *aneos_p_d;
int *aneos_rho_id_d;
int *aneos_e_id_d;
int *aneos_matrix_id_d;
__constant__ int *aneos_n_rho_c;
__constant__ int *aneos_n_e_c;
__constant__ double *aneos_bulk_cs_c;
__constant__ double *aneos_rho_c;
__constant__ double *aneos_e_c;
__constant__ double *aneos_p_c;
__constant__ int *aneos_rho_id_c;
__constant__ int *aneos_e_id_c;
__constant__ int *aneos_matrix_id_c;
//end ANEOS device variables (in global and constant memory)
/* POROUS_JUTZI device variables */
double *matporjutzi_p_elastic_d;
double *matporjutzi_p_transition_d;
double *matporjutzi_p_compacted_d;
double *matporjutzi_alpha_0_d;
double *matporjutzi_alpha_e_d;
double *matporjutzi_alpha_t_d;
double *matporjutzi_n1_d;
double *matporjutzi_n2_d;
double *matcs_porous_d;
double *matcs_solid_d;
int *matcrushcurve_style_d;
/* POROUS_SIRONO device variables */
double *matporsirono_K_0_d;
double *matporsirono_rho_0_d;
double *matporsirono_rho_s_d;
double *matporsirono_gamma_K_d;
double *matporsirono_alpha_d;
double *matporsirono_pm_d;
double *matporsirono_phimax_d;
double *matporsirono_phi0_d;
double *matporsirono_delta_d;
/* EPSALPHA_POROSITY variables */
double *matporepsilon_kappa_d;
double *matporepsilon_alpha_0_d;
double *matporepsilon_epsilon_e_d;
double *matporepsilon_epsilon_x_d;
double *matporepsilon_epsilon_c_d;
double *matjc_y0_d;
double *matjc_B_d;
double *matjc_n_d;
double *matjc_m_d;
double *matjc_edot0_d;
double *matjc_C_d;
double *matjc_Tref_d;
double *matjc_Tmelt_d;
double *matCp_d;
double *matCV_d;
/* for the predictor corrector integrator */
double Smin;
double rhomin;
double emin;
double damagemin;
double alphamin;
double betamin;
double alpha_epspormin;
double epsilon_vmin;
__device__ double Smin_d;
__device__ double rhomin_d;
__device__ double emin_d;
__device__ double damagemin_d;
__device__ double alphamin_d;
__device__ double betamin_d;
__device__ double alpha_epspormin_d;
__device__ double epsilon_vmin_d;
__device__ double maxpressureDiff = 0.0;
__device__ int pressureChangeSmallEnough = FALSE;
__device__ double scale_height;
__device__ double density_floor_d;
double *matYoungModulus_d;
__constant__ double *matYoungModulus;
__constant__ double *matporjutzi_p_elastic;
__constant__ double *matporjutzi_p_transition;
__constant__ double *matporjutzi_p_compacted;
__constant__ double *matporjutzi_alpha_0;
__constant__ double *matporjutzi_alpha_e;
__constant__ double *matporjutzi_alpha_t;
__constant__ double *matporjutzi_n1;
__constant__ double *matporjutzi_n2;
__constant__ double *matcs_porous;
__constant__ double *matcs_solid;
__constant__ int *matcrushcurve_style;
__constant__ double *matporsirono_K_0;
__constant__ double *matporsirono_rho_0;
__constant__ double *matporsirono_rho_s;
__constant__ double *matporsirono_gamma_K;
__constant__ double *matporsirono_alpha;
__constant__ double *matporsirono_pm;
__constant__ double *matporsirono_phimax;
__constant__ double *matporsirono_phi0;
__constant__ double *matporsirono_delta;
__constant__ double *matporepsilon_kappa;
__constant__ double *matporepsilon_alpha_0;
__constant__ double *matporepsilon_epsilon_e;
__constant__ double *matporepsilon_epsilon_x;
__constant__ double *matporepsilon_epsilon_c;
__constant__ double *matjc_y0;
__constant__ double *matjc_B;
__constant__ double *matjc_n;
__constant__ double *matjc_m;
__constant__ double *matjc_edot0;
__constant__ double *matjc_C;
__constant__ double *matjc_Tref;
__constant__ double *matjc_Tmelt;
__constant__ double *matCp;
__constant__ double *matCV;
__constant__ double *matnu;
__constant__ double *matzeta;
__constant__ double *matSml;
__constant__ int *matnoi;
__constant__ int *matEOS;
__constant__ double *matPolytropicK;
__constant__ double *matPolytropicGamma;
__constant__ double *matBeta;
__constant__ double *matAlpha;
__constant__ double *matBulkmodulus;
__constant__ double *matShearmodulus;
__constant__ double *matYieldStress;
__constant__ double *matInternalFriction;
__constant__ double *matInternalFrictionDamaged;
__constant__ double *matRho0;
__constant__ double *matTillRho0;
__constant__ double *matTillEiv;
__constant__ double *matTillEcv;
__constant__ double *matTillE0;
__constant__ double *matTilla;
__constant__ double *matTillb;
__constant__ double *matTillA;
__constant__ double *matTillB;
__constant__ double *matTillAlpha;
__constant__ double *matTillBeta;
__constant__ int *materialId;
__constant__ double *matRhoLimit;
__constant__ double *matN;
__constant__ double *matCohesion;
__constant__ double *matFrictionAngle;
__constant__ double *matFrictionAngleDamaged;
__constant__ double *matAlphaPhi;
__constant__ double *matCohesionCoefficient;
__constant__ double *tensorialCorrectionMatrix;
__constant__ double *tensorialCorrectiondWdrr;
__device__ int numParticles;
__device__ int numPointmasses;
__constant__ int maxNumParticles;
__constant__ int numRealParticles;
__constant__ int numChildren;
__constant__ int numNodes;
__constant__ int maxNumFlaws;
__device__ double max_abs_pressure_change;
__constant__ double theta; // tree theta
int *relaxedPerBlock;
// integration parameters
__constant__ double b21 = 0.5;
__constant__ double b31 = -1.0;
__constant__ double b32 = 2.0;
__constant__ double c1 = 1.0;
__constant__ double c2 = 4.0;
__constant__ double c3 = 1.0;
__constant__ double safety = 0.9;
__device__ double maxPosAbsError;
__device__ double maxVelAbsError;
__device__ int treeMaxDepth = 0;
__device__ int movingparticles = 0;
__device__ int reset_movingparticles = 1;
__device__ double dtNewErrorCheck = 0.0;
__device__ double dtNewAlphaCheck = 0.0;
#if INTEGRATE_DENSITY
__device__ double maxDensityAbsError;
#endif
#if INTEGRATE_ENERGY
__device__ double maxEnergyAbsError;
#endif
__device__ double maxPressureAbsChange;
#if FRAGMENTATION
__device__ double maxDamageTimeStep;
#endif
#if PALPHA_POROSITY
__device__ double maxalphaDiff = 0.0;
#endif
__device__ int errorSmallEnough = FALSE;
__constant__ int isRelaxationRun = FALSE;
__constant__ volatile int *childList;
int *childListd;
/* time variables */
void (*integrator)();
int startTimestep = 0;
int numberOfTimesteps = 1;
double timePerStep;
double dt_host;
double dt_grav;
int gravity_index = 0;
int flag_force_gravity_calc = 0;
double currentTime;
double startTime;
double h5time;
__device__ double dt;
__device__ double dtmax;
__device__ double endTimeD, currentTimeD;
__device__ double substep_currentTimeD;
__device__ int blockCount = 0;
__device__ volatile int maxNodeIndex;
int maxNodeIndex_host;
__device__ volatile double radius;
// tree computational domain
double *minxPerBlock, *maxxPerBlock;
__device__ double minx, maxx;
#if DIM > 1
double *minyPerBlock, *maxyPerBlock;
__device__ double miny, maxy;
#endif
#if DIM == 3
double *minzPerBlock, *maxzPerBlock;
__device__ double minz, maxz;
#endif
// map [i][j] to [i*DIM*DIM+j] for the tensors
__device__ int stressIndex(int particleIndex, int row, int col) {
return particleIndex*DIM*DIM+row*DIM+col;
}
#if SOLID
__global__ void symmetrizeStress(void) {
register int i, j, k, inc;
register double val;
inc = blockDim.x * gridDim.x;
for (i = threadIdx.x + blockIdx.x * blockDim.x; i < numParticles; i += inc) {
for (j = 0; j < DIM; j ++) {
for (k = 0; k < j; k++) {
val = 0.5 * (p.S[stressIndex(i,j,k)] + p.S[stressIndex(i,k,j)]);
p.S[stressIndex(i,j,k)] = val;
p.S[stressIndex(i,k,j)] = val;
}
}
}
}
#endif
double calculate_angular_momentum(void)
{
int i;
double l_i = 0.0;
double Lx = 0.0;
double Ly = 0.0;
double Lz = 0.0;
double L = 0.0;
#if DIM > 1
for (i = 0; i < numberOfParticles; i++) {
l_i = 0;
#if DIM > 2
l_i = p_host.m[i]*(p_host.y[i]*p_host.vz[i] - p_host.z[i]*p_host.vy[i]);
Lx += l_i;
l_i = p_host.m[i]*(p_host.z[i]*p_host.vx[i] - p_host.x[i]*p_host.vz[i]);
Ly += l_i;
l_i = p_host.m[i]*(p_host.x[i]*p_host.vy[i] - p_host.y[i]*p_host.vx[i]);
Lz += l_i;
#else
l_i = p_host.m[i]*(p_host.x[i]*p_host.vy[i] - p_host.y[i]*p_host.vx[i]);
Lz += l_i;
#endif
}
L = sqrt(Lx*Lx + Ly*Ly + Lz*Lz);
#endif
return L;
}
void initIntegration()
{
L_ini = calculate_angular_momentum();
if (param.verbose) {
fprintf(stdout, "Initial angular momentum is: %.17e\n", L_ini);
}
dt_host = timePerStep;
// copy constants to device
cudaVerify(cudaMemcpyToSymbol(dt, &dt_host, sizeof(double)));
cudaVerify(cudaMemcpyToSymbol(dtmax, ¶m.maxtimestep, sizeof(double)));
cudaVerify(cudaMemcpyToSymbol(theta, &treeTheta, sizeof(double)));
cudaVerify(cudaMemcpyToSymbol(numParticles, &numberOfParticles, sizeof(int)));
cudaVerify(cudaMemcpyToSymbol(numPointmasses, &numberOfPointmasses, sizeof(int)));
cudaVerify(cudaMemcpyToSymbol(maxNumParticles, &maxNumberOfParticles, sizeof(int)));
cudaVerify(cudaMemcpyToSymbol(numRealParticles, &numberOfRealParticles, sizeof(int)));
cudaVerify(cudaMemcpyToSymbol(numChildren, &numberOfChildren, sizeof(int)));
cudaVerify(cudaMemcpyToSymbol(numNodes, &numberOfNodes, sizeof(int)));
#if FRAGMENTATION
cudaVerify(cudaMemcpyToSymbol(maxNumFlaws, &maxNumFlaws_host, sizeof(int)));
#endif
// memory for tree
cudaVerify(cudaMalloc((void**)&minxPerBlock, sizeof(double)*numberOfMultiprocessors));
cudaVerify(cudaMalloc((void**)&maxxPerBlock, sizeof(double)*numberOfMultiprocessors));
#if DIM > 1
cudaVerify(cudaMalloc((void**)&minyPerBlock, sizeof(double)*numberOfMultiprocessors));
cudaVerify(cudaMalloc((void**)&maxyPerBlock, sizeof(double)*numberOfMultiprocessors));
#endif
#if DIM == 3
cudaVerify(cudaMalloc((void**)&minzPerBlock, sizeof(double)*numberOfMultiprocessors));
cudaVerify(cudaMalloc((void**)&maxzPerBlock, sizeof(double)*numberOfMultiprocessors));
#endif
// set the pointer on the gpu to p_device
cudaVerify(cudaMemcpyToSymbol(p, &p_device, sizeof(struct Particle)));
cudaVerify(cudaMemcpyToSymbol(p_rhs, &p_device, sizeof(struct Particle)));
cudaVerify(cudaMemcpyToSymbol(pointmass, &pointmass_device, sizeof(struct Pointmass)));
cudaVerifyKernel((initializeSoundspeed<<<numberOfMultiprocessors*4, NUM_THREADS_512>>>()));
}
void endIntegration(void)
{
int rc = pthread_join(fileIOthread, NULL);
assert(0 == rc);
// free memory
cudaVerify(cudaFree(minxPerBlock));
cudaVerify(cudaFree(maxxPerBlock));
#if DIM > 1
cudaVerify(cudaFree(minyPerBlock));
cudaVerify(cudaFree(maxyPerBlock));
#endif
#if DIM == 3
cudaVerify(cudaFree(minzPerBlock));
cudaVerify(cudaFree(maxzPerBlock));
#endif
cleanupMaterials();
}
double *sml;
double *till_rho_0;
double *bulk_modulus;
double *cs_porous;
int numberOfMaterials;
void transferMaterialsToGPU()
{
double *pc_pointer;
double smallest_rho = 1e30;
double tmp_dens;
double scale_height_host;
config_setting_t *materials;
config_setting_t *disk;
disk = config_lookup(¶m.config, "disk");
// set some stuff for some integrators
set_integration_parameters();
// read disk properties
if (disk != NULL) {
config_setting_lookup_float(disk, "scale_height", &scale_height_host);
fprintf(stdout, "Found disk scale height: %e\n", scale_height_host);
}
materials = config_lookup(¶m.config, "materials");
// read material properties
if (materials != NULL) {
int count = config_setting_length(materials);
int i,j;
int maxId = 0;
config_setting_t *material;
config_setting_t *subset;
// find max ID of materials to allocate enough memory for material struct
for (i = 0; i < count; ++i) {
material = config_setting_get_elem(materials, i);
int ID;
config_setting_lookup_int(material, "ID", &ID);
if (param.verbose) {
fprintf(stdout, "Found material ID: %d\n", ID);
}
maxId = max(ID, maxId);
}
// allocate struct oh god so ugly
// yesssss
int numberOfElements = maxId + 1;
numberOfMaterials = numberOfElements;
sml = (double*)calloc(numberOfElements,sizeof(double));
int *eos = (int*)calloc(numberOfElements,sizeof(int));
int *noi = (int*)calloc(numberOfElements,sizeof(int));
double *f_sml_min = (double *) calloc(numberOfElements, sizeof(double));
double *f_sml_max = (double *) calloc(numberOfElements, sizeof(double));
// seting some reasonable values for the factor of sml
for (i = 0; i < numberOfMaterials; i++) {
f_sml_min[i] = 1.0;
f_sml_max[i] = 1.0;
}
double *alpha = (double*)calloc(numberOfElements, sizeof(double));
double *beta = (double*)calloc(numberOfElements, sizeof(double));
double *polytropic_K = (double*)calloc(numberOfElements, sizeof(double));
double *polytropic_gamma = (double*)calloc(numberOfElements, sizeof(double));
double *n = (double*)calloc(numberOfElements, sizeof(double));
double *nu = (double *) calloc(numberOfElements, sizeof(double));
double *eta = (double *) calloc(numberOfElements, sizeof(double));
double *zeta = (double *) calloc(numberOfElements, sizeof(double));
double *rho_0 = (double*)calloc(numberOfElements, sizeof(double));
double *rho_limit = (double*)calloc(numberOfElements, sizeof(double));
till_rho_0 = (double*)calloc(numberOfElements, sizeof(double));
double *till_A = (double*)calloc(numberOfElements, sizeof(double));
double *till_B = (double*)calloc(numberOfElements, sizeof(double));
double *till_E_0 = (double*)calloc(numberOfElements, sizeof(double));
double *till_E_iv = (double*)calloc(numberOfElements, sizeof(double));
double *till_E_cv = (double*)calloc(numberOfElements, sizeof(double));
double *till_a = (double*)calloc(numberOfElements, sizeof(double));
double *till_b = (double*)calloc(numberOfElements, sizeof(double));
double *till_alpha = (double*)calloc(numberOfElements, sizeof(double));
double *till_beta = (double*)calloc(numberOfElements, sizeof(double));
// begin of ANEOS allocations in host memory (global variables, defined in 'aneos.cu')
g_eos_is_aneos = (int*)calloc(numberOfElements, sizeof(int));
g_aneos_tab_file = (const char**)calloc(numberOfElements, sizeof(const char*)); // not necessary to allocate (and free) mem for individual strings - this should be managed by libconfig
g_aneos_n_rho = (int*)calloc(numberOfElements, sizeof(int));
g_aneos_n_e = (int*)calloc(numberOfElements, sizeof(int));
g_aneos_rho_0 = (double*)calloc(numberOfElements, sizeof(double));
g_aneos_bulk_cs = (double*)calloc(numberOfElements, sizeof(double));
g_aneos_rho = (double**)calloc(numberOfElements, sizeof(double*));
g_aneos_e = (double**)calloc(numberOfElements, sizeof(double*));
g_aneos_p = (double***)calloc(numberOfElements, sizeof(double**));
#if MORE_ANEOS_OUTPUT
g_aneos_T = (double***)calloc(numberOfElements, sizeof(double**));
g_aneos_cs = (double***)calloc(numberOfElements, sizeof(double**));
g_aneos_entropy = (double***)calloc(numberOfElements, sizeof(double**));
g_aneos_phase_flag = (int***)calloc(numberOfElements, sizeof(int**));
#endif
int n_aneos_mat = 0;
/* arrays to hold 'start indices' for all ANEOS materials and -1 if EOS != ANEOS (e.g. aneos_rho_id = [0,-1,g_aneos_n_rho[0],-1,-1]
if materials no. 0 and 2 use ANEOS), necessary for resolving linearizations of multi-dim arrays on GPU */
int *aneos_rho_id = (int*)calloc(numberOfElements, sizeof(int));
int *aneos_e_id = (int*)calloc(numberOfElements, sizeof(int));
int *aneos_matrix_id = (int*)calloc(numberOfElements, sizeof(int));
for (i = 0; i < numberOfElements; i++)
aneos_rho_id[i] = aneos_e_id[i] = aneos_matrix_id[i] = -1;
/* variables to hold running indices for filling arrays holding 'start indices' */
int run_aneos_rho_id = 0;
int run_aneos_e_id = 0;
int run_aneos_matrix_id = 0;
// end of ANEOS allocations in host memory
double *shear_modulus = (double*)calloc(numberOfElements, sizeof(double));
bulk_modulus = (double*)calloc(numberOfElements, sizeof(double));
double *yield_stress = (double*)calloc(numberOfElements, sizeof(double));
double *internal_friction = (double*)calloc(numberOfElements, sizeof(double));
double *internal_friction_damaged = (double*)calloc(numberOfElements, sizeof(double));
double *cohesion = (double*)calloc(numberOfElements, sizeof(double));
double *friction_angle = (double*)calloc(numberOfElements, sizeof(double));
double *friction_angle_damaged = (double*)calloc(numberOfElements, sizeof(double));
double *alpha_phi = (double*)calloc(numberOfElements, sizeof(double));
double *cohesion_coefficient = (double*)calloc(numberOfElements, sizeof(double));
#if ARTIFICIAL_STRESS
double *exponent_tensor = (double*) calloc(numberOfElements, sizeof(double));
double *epsilon_stress = (double*) calloc(numberOfElements, sizeof(double));
double *mean_particle_distance = (double*) calloc(numberOfElements, sizeof(double));
#endif
#if PALPHA_POROSITY
double *porjutzi_p_elastic = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_p_transition = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_p_compacted = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_alpha_0 = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_alpha_e = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_alpha_t = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_n1 = (double*)calloc(numberOfElements, sizeof(double));
double *porjutzi_n2 = (double*)calloc(numberOfElements, sizeof(double));
cs_porous = (double*)calloc(numberOfElements, sizeof(double));
double *cs_solid = (double*)calloc(numberOfElements, sizeof(double));
double max_abs_pressure_change_host = DBL_MAX;
int *crushcurve_style = (int*)calloc(numberOfElements, sizeof(int));
#endif
#if SIRONO_POROSITY
double *porsirono_K_0 = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_rho_0 = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_rho_s = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_gamma_K = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_alpha = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_pm = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_phimax = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_phi0 = (double*)calloc(numberOfElements, sizeof(double));
double *porsirono_delta = (double*)calloc(numberOfElements, sizeof(double));
#endif
#if EPSALPHA_POROSITY
double *porepsilon_kappa = (double*)calloc(numberOfElements, sizeof(double));
double *porepsilon_alpha_0 = (double*)calloc(numberOfElements, sizeof(double));
double *porepsilon_epsilon_e = (double*)calloc(numberOfElements, sizeof(double));
double *porepsilon_epsilon_x = (double*)calloc(numberOfElements, sizeof(double));
double *porepsilon_epsilon_c = (double*)calloc(numberOfElements, sizeof(double));
#endif
#if SOLID
double *young_modulus = (double*)calloc(numberOfElements, sizeof(double));
#endif
#if JC_PLASTICITY
double *jc_y0 = (double*)calloc(numberOfElements, sizeof(double));
double *jc_B = (double*)calloc(numberOfElements, sizeof(double));
double *jc_n = (double*)calloc(numberOfElements, sizeof(double));
double *jc_m = (double*)calloc(numberOfElements, sizeof(double));
double *jc_edot0 = (double*)calloc(numberOfElements, sizeof(double));
double *jc_C = (double*)calloc(numberOfElements, sizeof(double));
double *jc_Tref = (double*)calloc(numberOfElements, sizeof(double));
double *jc_Tmelt = (double*)calloc(numberOfElements, sizeof(double));
double *Cp = (double*)calloc(numberOfElements, sizeof(double));
double *CV = (double*)calloc(numberOfElements, sizeof(double));
#endif
// fill struct
for (i = 0; i < count; ++i) {
material = config_setting_get_elem(materials, i);
int ID;
config_setting_lookup_int(material, "ID", &ID);
config_setting_lookup_float(material, "sml", &sml[ID]);
#if VARIABLE_SML
#if FIXED_NOI
config_setting_lookup_int(material, "interactions", &noi[ID]);
#endif
// sml will not get smaller than factor_sml_min * sml
// and not get larger than factor_sml_max * sml
config_setting_lookup_float(material, "factor_sml_min", &f_sml_min[ID]);
config_setting_lookup_float(material, "factor_sml_max", &f_sml_max[ID]);
#endif
#if ARTIFICIAL_VISCOSITY
subset = config_setting_get_member(material, "artificial_viscosity");
config_setting_lookup_float(subset, "alpha", &alpha[ID]);
config_setting_lookup_float(subset, "beta", &beta[ID]);
#endif
#if ARTIFICIAL_STRESS
subset = config_setting_get_member(material, "artificial_stress");
config_setting_lookup_float(subset, "exponent_tensor", &exponent_tensor[ID]);
config_setting_lookup_float(subset, "epsilon_stress", &epsilon_stress[ID]);
config_setting_lookup_float(subset, "mean_particle_distance", &mean_particle_distance[ID]);
#endif // ARTIFICIAL_STRESS
#if NAVIER_STOKES
// params for Navier-Stokes
subset = config_setting_get_member(material, "physical_viscosity");
// note nu and eta depend via density
// nu = eta/rho
config_setting_lookup_float(subset, "eta", &eta[ID]);
config_setting_lookup_float(subset, "zeta", &zeta[ID]);
config_setting_lookup_float(subset, "nu", &nu[ID]);
#endif
subset = config_setting_get_member(material, "eos");
config_setting_lookup_int(subset, "type", &eos[ID]);
config_setting_lookup_float(subset, "polytropic_K", &polytropic_K[ID]);
config_setting_lookup_float(subset, "polytropic_gamma", &polytropic_gamma[ID]);
config_setting_lookup_float(subset, "bulk_modulus", &bulk_modulus[ID]);
config_setting_lookup_float(subset, "shear_modulus", &shear_modulus[ID]);
config_setting_lookup_float(subset, "yield_stress", &yield_stress[ID]);
config_setting_lookup_float(subset, "rho_0", &rho_0[ID]);
config_setting_lookup_float(subset, "till_rho_0", &till_rho_0[ID]);
config_setting_lookup_float(subset, "till_E_0", &till_E_0[ID]);
config_setting_lookup_float(subset, "till_E_iv", &till_E_iv[ID]);
config_setting_lookup_float(subset, "till_E_cv", &till_E_cv[ID]);
config_setting_lookup_float(subset, "till_a", &till_a[ID]);
config_setting_lookup_float(subset, "till_b", &till_b[ID]);
// begin reading ANEOS data from material file to host memory
config_setting_lookup_string(subset, "table_path", &g_aneos_tab_file[ID]);
config_setting_lookup_int(subset, "n_rho", &g_aneos_n_rho[ID]);
config_setting_lookup_int(subset, "n_e", &g_aneos_n_e[ID]);
config_setting_lookup_float(subset, "aneos_rho_0", &g_aneos_rho_0[ID]);
config_setting_lookup_float(subset, "aneos_bulk_cs", &g_aneos_bulk_cs[ID]);
// end reading ANEOS data from material file to host memory, begin reading ANEOS lookup table to host memory
if (eos[ID] == EOS_TYPE_ANEOS) {
g_eos_is_aneos[ID] = TRUE;
aneos_rho_id[ID] = run_aneos_rho_id;
run_aneos_rho_id += g_aneos_n_rho[ID];
aneos_e_id[ID] = run_aneos_e_id;
run_aneos_e_id += g_aneos_n_e[ID];
aneos_matrix_id[ID] = run_aneos_matrix_id;
run_aneos_matrix_id += g_aneos_n_rho[ID]*g_aneos_n_e[ID];
n_aneos_mat++;
if ((g_aneos_rho[ID] = (double*)calloc(g_aneos_n_rho[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
if ((g_aneos_e[ID] = (double*)calloc(g_aneos_n_e[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
if ((g_aneos_p[ID] = (double**)calloc(g_aneos_n_rho[ID], sizeof(double*))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
for (j=0; j<g_aneos_n_rho[ID]; j++)
if ((g_aneos_p[ID][j] = (double*)calloc(g_aneos_n_e[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
#if MORE_ANEOS_OUTPUT
if ((g_aneos_T[ID] = (double**)calloc(g_aneos_n_rho[ID], sizeof(double*))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
for (j=0; j<g_aneos_n_rho[ID]; j++)
if ((g_aneos_T[ID][j] = (double*)calloc(g_aneos_n_e[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
if ((g_aneos_cs[ID] = (double**)calloc(g_aneos_n_rho[ID], sizeof(double*))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
for (j=0; j<g_aneos_n_rho[ID]; j++)
if ((g_aneos_cs[ID][j] = (double*)calloc(g_aneos_n_e[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
if ((g_aneos_entropy[ID] = (double**)calloc(g_aneos_n_rho[ID], sizeof(double*))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
for (j=0; j<g_aneos_n_rho[ID]; j++)
if ((g_aneos_entropy[ID][j] = (double*)calloc(g_aneos_n_e[ID], sizeof(double))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
if ((g_aneos_phase_flag[ID] = (int**)calloc(g_aneos_n_rho[ID], sizeof(int*))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
for (j=0; j<g_aneos_n_rho[ID]; j++)
if ((g_aneos_phase_flag[ID][j] = (int*)calloc(g_aneos_n_e[ID], sizeof(int))) == NULL)
ERRORVAR("ERROR during memory allocation for ANEOS lookup table in '%s'\n", g_aneos_tab_file[ID])
#endif
#if MORE_ANEOS_OUTPUT
initialize_aneos_eos_full(g_aneos_tab_file[ID], g_aneos_n_rho[ID], g_aneos_n_e[ID], g_aneos_rho[ID], g_aneos_e[ID], g_aneos_p[ID], g_aneos_T[ID], g_aneos_cs[ID], g_aneos_entropy[ID], g_aneos_phase_flag[ID]);
#else
initialize_aneos_eos_basic(g_aneos_tab_file[ID], g_aneos_n_rho[ID], g_aneos_n_e[ID], g_aneos_rho[ID], g_aneos_e[ID], g_aneos_p[ID]);
#endif
}
//end reading ANEOS lookup table to host memory
#if PALPHA_POROSITY
config_setting_lookup_float(subset, "porjutzi_p_elastic", &porjutzi_p_elastic[ID]);
if (porjutzi_p_elastic[ID] < max_abs_pressure_change_host) {
max_abs_pressure_change_host = porjutzi_p_elastic[ID];
}
config_setting_lookup_float(subset, "porjutzi_p_transition", &porjutzi_p_transition[ID]);
config_setting_lookup_float(subset, "porjutzi_p_compacted", &porjutzi_p_compacted[ID]);
config_setting_lookup_float(subset, "porjutzi_alpha_0", &porjutzi_alpha_0[ID]);
config_setting_lookup_float(subset, "porjutzi_alpha_e", &porjutzi_alpha_e[ID]);
config_setting_lookup_float(subset, "porjutzi_alpha_t", &porjutzi_alpha_t[ID]);
config_setting_lookup_float(subset, "porjutzi_n1", &porjutzi_n1[ID]);
config_setting_lookup_float(subset, "porjutzi_n2", &porjutzi_n2[ID]);
config_setting_lookup_float(subset, "cs_porous", &cs_porous[ID]);
cs_solid[ID] = sqrt(bulk_modulus[ID] / till_rho_0[ID] / porjutzi_alpha_0[ID]);
config_setting_lookup_int(subset, "crushcurve_style", &crushcurve_style[ID]);
#endif
#if SIRONO_POROSITY
config_setting_lookup_float(subset, "porsirono_K_0", &porsirono_K_0[ID]);
config_setting_lookup_float(subset, "porsirono_rho_0", &porsirono_rho_0[ID]);
config_setting_lookup_float(subset, "porsirono_rho_s", &porsirono_rho_s[ID]);
config_setting_lookup_float(subset, "porsirono_gamma_K", &porsirono_gamma_K[ID]);
config_setting_lookup_float(subset, "porsirono_alpha", &porsirono_alpha[ID]);
config_setting_lookup_float(subset, "porsirono_pm", &porsirono_pm[ID]);
config_setting_lookup_float(subset, "porsirono_phimax", &porsirono_phimax[ID]);
config_setting_lookup_float(subset, "porsirono_phi0", &porsirono_phi0[ID]);
config_setting_lookup_float(subset, "porsirono_delta", &porsirono_delta[ID]);
#endif
#if EPSALPHA_POROSITY
config_setting_lookup_float(subset, "porepsilon_kappa", &porepsilon_kappa[ID]);
config_setting_lookup_float(subset, "porepsilon_alpha_0", &porepsilon_alpha_0[ID]);
config_setting_lookup_float(subset, "porepsilon_epsilon_e", &porepsilon_epsilon_e[ID]);
config_setting_lookup_float(subset, "porepsilon_epsilon_x", &porepsilon_epsilon_x[ID]);
config_setting_lookup_float(subset, "porepsilon_epsilon_c", &porepsilon_epsilon_c[ID]);
#endif
config_setting_lookup_float(subset, "till_A", &till_A[ID]);
config_setting_lookup_float(subset, "till_B", &till_B[ID]);
config_setting_lookup_float(subset, "till_alpha", &till_alpha[ID]);
config_setting_lookup_float(subset, "till_beta", &till_beta[ID]);
config_setting_lookup_float(subset, "rho_limit", &rho_limit[ID]);
config_setting_lookup_float(subset, "n", &n[ID]);
config_setting_lookup_float(subset, "cohesion", &cohesion[ID]);
config_setting_lookup_float(subset, "friction_angle", &friction_angle[ID]);
config_setting_lookup_float(subset, "friction_angle_damaged", &friction_angle_damaged[ID]);
#if DIM == 2
alpha_phi[ID] = tan(friction_angle[ID]) / sqrt(9 + 12*tan(friction_angle[ID])*tan(friction_angle[ID]));
cohesion_coefficient[ID] = 3*(cohesion[ID]) / sqrt(9 + 12*tan(friction_angle[ID])*tan(friction_angle[ID]));
#else
alpha_phi[ID] = 2*sin(friction_angle[ID]) / (sqrt(3.)*(3-sin(friction_angle[ID])));
cohesion_coefficient[ID] = 6*(cohesion[ID]) * cos(friction_angle[ID]) / (sqrt(3.)*(3-sin(friction_angle[ID])));
#endif
/* internal friction coefficient (normally \mu) is tan of angle of internal friction */
internal_friction[ID] = tan(friction_angle[ID]);
internal_friction_damaged[ID] = tan(friction_angle_damaged[ID]);
#if SOLID
young_modulus[ID] = 9.0*bulk_modulus[ID]*shear_modulus[ID]/(3.0*bulk_modulus[ID]+shear_modulus[ID]);
#endif
#if JC_PLASTICITY
config_setting_lookup_float(subset, "jc_y0", &jc_y0[ID]);
config_setting_lookup_float(subset, "jc_B", &jc_B[ID]);
config_setting_lookup_float(subset, "jc_n", &jc_n[ID]);
config_setting_lookup_float(subset, "jc_m", &jc_m[ID]);
config_setting_lookup_float(subset, "jc_edot0", &jc_edot0[ID]);
config_setting_lookup_float(subset, "jc_C", &jc_C[ID]);
config_setting_lookup_float(subset, "jc_Tref", &jc_Tref[ID]);
config_setting_lookup_float(subset, "jc_Tmelt", &jc_Tmelt[ID]);
config_setting_lookup_float(subset, "Cp", &Cp[ID]);
config_setting_lookup_float(subset, "CV", &CV[ID]);
#endif
#if DENSITY_FLOOR
switch (eos[ID]) {
case (EOS_TYPE_MURNAGHAN):
tmp_dens = rho_0[ID];
break;
case (EOS_TYPE_JUTZI_MURNAGHAN):
tmp_dens = rho_0[ID];
break;
case (EOS_TYPE_TILLOTSON):
tmp_dens = till_rho_0[ID];
break;
case (EOS_TYPE_JUTZI):
tmp_dens = till_rho_0[ID];
break;
#if SIRONO_POROSITY
case (EOS_TYPE_SIRONO):
tmp_dens = porsirono_rho_s[ID];
break;
#endif
case (EOS_TYPE_EPSILON):
tmp_dens = till_rho_0[ID];
break;
case (EOS_TYPE_ANEOS):
tmp_dens = g_aneos_rho_0[ID];
break;
case (EOS_TYPE_VISCOUS_REGOLITH):
tmp_dens = rho_0[ID];
break;
case (EOS_TYPE_IDEAL_GAS):
tmp_dens = IDEAL_GAS_REFERENCE_RHO;
break;
case (EOS_TYPE_LOCALLY_ISOTHERMAL_GAS):
tmp_dens = IDEAL_GAS_REFERENCE_RHO;
break;
case (EOS_TYPE_IGNORE):
fprintf(stdout, ".oOo. Happily ignoring EOS_TYPE_IGNORE .oOo.");
break;
default:
fprintf(stderr, "Error: Cannot determine rho0 for material ID %d with EOS_TYPE %d\n",
ID, eos[ID]);
exit(1);
}
if (tmp_dens < smallest_rho) {
smallest_rho = tmp_dens;
}
#endif
}
#if PALPHA_POROSITY
cudaVerify(cudaMalloc((void **)&matporjutzi_p_elastic_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_p_transition_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_p_compacted_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_alpha_0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_alpha_e_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_alpha_t_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_n1_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporjutzi_n2_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matcs_porous_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matcs_solid_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matcrushcurve_style_d, numberOfElements*sizeof(int)));
#endif
#if VARIABLE_SML
cudaVerify(cudaMalloc((void **)&mat_f_sml_max_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&mat_f_sml_min_d, numberOfElements*sizeof(double)));
#endif
#if SIRONO_POROSITY
cudaVerify(cudaMalloc((void **)&matporsirono_K_0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_rho_0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_rho_s_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_gamma_K_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_alpha_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_pm_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_phimax_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_phi0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporsirono_delta_d, numberOfElements*sizeof(double)));
#endif
#if EPSALPHA_POROSITY
cudaVerify(cudaMalloc((void **)&matporepsilon_kappa_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporepsilon_alpha_0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporepsilon_epsilon_e_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporepsilon_epsilon_x_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matporepsilon_epsilon_c_d, numberOfElements*sizeof(double)));
#endif
#if NAVIER_STOKES
cudaVerify(cudaMalloc((void **)&matnu_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matzeta_d, numberOfElements*sizeof(double)));
#endif
#if ARTIFICIAL_STRESS
cudaVerify(cudaMalloc((void **)&matexponent_tensor_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matepsilon_stress_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matmean_particle_distance_d, numberOfElements*sizeof(double)));
#endif
//begin of ANEOS allocations in (global) device memory (everything linearized)
cudaVerify(cudaMalloc((void **)&aneos_n_rho_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&aneos_n_e_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&aneos_bulk_cs_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&aneos_rho_d, run_aneos_rho_id*sizeof(double)));
cudaVerify(cudaMalloc((void **)&aneos_e_d, run_aneos_e_id*sizeof(double)));
cudaVerify(cudaMalloc((void **)&aneos_p_d, run_aneos_matrix_id*sizeof(double)));
cudaVerify(cudaMalloc((void **)&aneos_rho_id_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&aneos_e_id_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&aneos_matrix_id_d, numberOfElements*sizeof(int)));
//end of ANEOS allocations in (global) device memory
cudaVerify(cudaMalloc((void **)&matSml_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matnoi_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&matEOS_d, numberOfElements*sizeof(int)));
cudaVerify(cudaMalloc((void **)&matPolytropicK_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matPolytropicGamma_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matAlpha_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matBeta_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matBulkmodulus_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matShearmodulus_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matYieldStress_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matInternalFriction_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matInternalFrictionDamaged_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matRho0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillRho0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillE0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillEiv_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillEcv_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTilla_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillb_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillA_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillB_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillAlpha_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matTillBeta_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matRhoLimit_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matN_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matCohesion_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matFrictionAngle_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matFrictionAngleDamaged_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matAlphaPhi_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matCohesionCoefficient_d, numberOfElements*sizeof(double)));
#if JC_PLASTICITY
cudaVerify(cudaMalloc((void **)&matjc_y0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_B_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_n_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_m_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_edot0_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_C_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_Tref_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matjc_Tmelt_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matCp_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMalloc((void **)&matCV_d, numberOfElements*sizeof(double)));
#endif
#if SOLID
cudaVerify(cudaMalloc((void **)&matYoungModulus_d, numberOfElements*sizeof(double)));
cudaVerify(cudaMemcpy(matYoungModulus_d, young_modulus, numberOfElements*sizeof(double), cudaMemcpyHostToDevice));
cudaVerify(cudaMemcpyToSymbol(matYoungModulus, &matYoungModulus_d, sizeof(void*)));
#endif