-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathsvm.cpp
More file actions
3579 lines (3124 loc) · 76.4 KB
/
svm.cpp
File metadata and controls
3579 lines (3124 loc) · 76.4 KB
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
#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <float.h>
#include <string.h>
#include <stdarg.h>
#include <limits.h>
#include <locale.h>
#include <time.h> //변경
#include <thread> //변경
#include <mutex> //변경
#include <omp.h> //변경
#include "svm.h"
std::mutex mtx_lock; //변경
int libsvm_version = LIBSVM_VERSION;
typedef float Qfloat;
typedef signed char schar;
#ifndef min
template <class T> static inline T min(T x, T y) { return (x<y) ? x : y; }
#endif
#ifndef max
template <class T> static inline T max(T x, T y) { return (x>y) ? x : y; }
#endif
template <class T> static inline void swap(T& x, T& y) { T t = x; x = y; y = t; }
template <class S, class T> static inline void clone(T*& dst, S* src, int n)
{
dst = new T[n];
memcpy((void *)dst, (void *)src, sizeof(T)*n);
}
static inline double powi(double base, int times)
{
double tmp = base, ret = 1.0;
for (int t = times; t>0; t /= 2)
{
if (t % 2 == 1) ret *= tmp;
tmp = tmp * tmp;
}
return ret;
}
#define INF HUGE_VAL
#define TAU 1e-12
#define Malloc(type,n) (type *)malloc((n)*sizeof(type))
static void print_string_stdout(const char *s)
{
fputs(s, stdout);
fflush(stdout);
}
static void(*svm_print_string) (const char *) = &print_string_stdout;
#if 1
static void info(const char *fmt, ...)
{
char buf[BUFSIZ];
va_list ap;
va_start(ap, fmt);
vsprintf(buf, fmt, ap);
va_end(ap);
(*svm_print_string)(buf);
}
#else
static void info(const char *fmt, ...) {}
#endif
//
// Kernel Cache
//
// l is the number of total data items
// size is the cache size limit in bytes
//
class Cache
{
public:
Cache(int l, long int size); //original
//Cache(int l, long long int size); //변경
~Cache();
// request data [0,len)
// return some position p where [p,len) need to be filled
// (p >= len if nothing needs to be filled)
int get_data(const int index, Qfloat **data, int len);
void swap_index(int i, int j);
private:
int l;
long int size; //original
//long long int size; //변경
struct head_t
{
head_t *prev, *next; // a circular list
Qfloat *data;
int len; // data[0,len) is cached in this entry
};
head_t *head;
head_t lru_head;
void lru_delete(head_t *h);
void lru_insert(head_t *h);
};
Cache::Cache(int l_, long int size_) :l(l_), size(size_) //original
//Cache::Cache(int l_,long int size_) : l(l_), size(size_)
{
head = (head_t *)calloc(l, sizeof(head_t)); // initialized to 0
size /= sizeof(Qfloat);
size -= l * sizeof(head_t) / sizeof(Qfloat);
size = max(size, 2 * (long int)l); // cache must be large enough for two columns //original
lru_head.next = lru_head.prev = &lru_head;
}
Cache::~Cache()
{
for (head_t *h = lru_head.next; h != &lru_head; h = h->next)
free(h->data);
free(head);
}
void Cache::lru_delete(head_t *h)
{
// delete from current location
h->prev->next = h->next;
h->next->prev = h->prev;
}
void Cache::lru_insert(head_t *h)
{
// insert to last position
h->next = &lru_head;
h->prev = lru_head.prev;
h->prev->next = h;
h->next->prev = h;
}
int Cache::get_data(const int index, Qfloat **data, int len)
{
head_t *h = &head[index];
if (h->len) lru_delete(h);
int more = len - h->len; //처음에는 총 길이 에서 인덱스 길이를 뺸다.
if (more > 0)
{
// free old space
//사용자 변경
//#pragma omp parallel firstprivate()
{
//#pragma omp single
while (size < more) //original //size가 크면 while문 실행 안됨
//for(more; size < more;more)
{
head_t *old = lru_head.next;
lru_delete(old);
free(old->data);
//#pragma omp task
size += old->len;
old->data = 0;
old->len = 0;
}
}
// allocate new space
h->data = (Qfloat *)realloc(h->data, sizeof(Qfloat)*len);
size -= more;
swap(h->len, len);
}
lru_insert(h);
*data = h->data;
return len;
}
void Cache::swap_index(int i, int j)
{
if (i == j) return;
if (head[i].len) lru_delete(&head[i]);
if (head[j].len) lru_delete(&head[j]);
swap(head[i].data, head[j].data);
swap(head[i].len, head[j].len);
if (head[i].len) lru_insert(&head[i]);
if (head[j].len) lru_insert(&head[j]);
if (i>j) swap(i, j);
for (head_t *h = lru_head.next; h != &lru_head; h = h->next)
{
if (h->len > i)
{
if (h->len > j)
swap(h->data[i], h->data[j]);
else
{
// give up
lru_delete(h);
free(h->data);
size += h->len;
h->data = 0;
h->len = 0;
}
}
}
}
//
// Kernel evaluation
//
// the static method k_function is for doing single kernel evaluation
// the constructor of Kernel prepares to calculate the l*l kernel matrix
// the member function get_Q is for getting one column from the Q Matrix
//
class QMatrix {
public:
virtual Qfloat *get_Q(int column, int len) const = 0;
virtual double *get_QD() const = 0;
virtual void swap_index(int i, int j) const = 0;
virtual ~QMatrix() {}
};
class Kernel : public QMatrix {
public:
Kernel(int l, svm_node * const * x, const svm_parameter& param);
virtual ~Kernel();
static double k_function(const svm_node *x, const svm_node *y,
const svm_parameter& param);
virtual Qfloat *get_Q(int column, int len) const = 0;
virtual double *get_QD() const = 0;
virtual void swap_index(int i, int j) const // no so const...
{
swap(x[i], x[j]);
if (x_square) swap(x_square[i], x_square[j]);
}
protected:
double (Kernel::*kernel_function)(int i, int j) const;
private:
const svm_node **x;
double *x_square;
// svm_parameter
const int kernel_type;
const int degree;
const double gamma;
const double coef0;
static double dot(const svm_node *px, const svm_node *py);
double kernel_linear(int i, int j) const
{
return dot(x[i], x[j]);
}
double kernel_poly(int i, int j) const
{
return powi(gamma*dot(x[i], x[j]) + coef0, degree);
}
double kernel_rbf(int i, int j) const
{
return exp(-gamma*(x_square[i] + x_square[j] - 2 * dot(x[i], x[j])));
}
double kernel_sigmoid(int i, int j) const
{
return tanh(gamma*dot(x[i], x[j]) + coef0);
}
double kernel_precomputed(int i, int j) const
{
return x[i][(int)(x[j][0].value)].value;
}
};
Kernel::Kernel(int l, svm_node * const * x_, const svm_parameter& param)
:kernel_type(param.kernel_type), degree(param.degree),
gamma(param.gamma), coef0(param.coef0)
{
switch (kernel_type)
{
case LINEAR:
kernel_function = &Kernel::kernel_linear;
break;
case POLY:
kernel_function = &Kernel::kernel_poly;
break;
case RBF:
kernel_function = &Kernel::kernel_rbf;
break;
case SIGMOID:
kernel_function = &Kernel::kernel_sigmoid;
break;
case PRECOMPUTED:
kernel_function = &Kernel::kernel_precomputed;
break;
}
clone(x, x_, l);
if (kernel_type == RBF)
{
x_square = new double[l];
for (int i = 0; i<l; i++)
x_square[i] = dot(x[i], x[i]);
}
else
x_square = 0;
}
Kernel::~Kernel()
{
delete[] x;
delete[] x_square;
}
double Kernel::dot(const svm_node *px, const svm_node *py)
{
double sum = 0;
while (px->index != -1 && py->index != -1)
{
if (px->index == py->index)
{
sum += px->value * py->value;
++px;
++py;
}
else
{
if (px->index > py->index)
++py;
else
++px;
}
}
return sum;
}
double Kernel::k_function(const svm_node *x, const svm_node *y,
const svm_parameter& param)
{
switch (param.kernel_type)
{
case LINEAR:
return dot(x, y);
case POLY:
return powi(param.gamma*dot(x, y) + param.coef0, param.degree);
case RBF:
{
double sum = 0;
while (x->index != -1 && y->index != -1)
{
if (x->index == y->index)
{
double d = x->value - y->value;
sum += d*d;
++x;
++y;
}
else
{
if (x->index > y->index)
{
sum += y->value * y->value;
++y;
}
else
{
sum += x->value * x->value;
++x;
}
}
}
while (x->index != -1)
{
sum += x->value * x->value;
++x;
}
while (y->index != -1)
{
sum += y->value * y->value;
++y;
}
return exp(-param.gamma*sum);
}
case SIGMOID:
return tanh(param.gamma*dot(x, y) + param.coef0);
case PRECOMPUTED: //x: test (validation), y: SV
return x[(int)(y->value)].value;
default:
return 0; // Unreachable
}
}
// An SMO algorithm in Fan et al., JMLR 6(2005), p. 1889--1918
// Solves:
//
// min 0.5(\alpha^T Q \alpha) + p^T \alpha
//
// y^T \alpha = \delta
// y_i = +1 or -1
// 0 <= alpha_i <= Cp for y_i = 1
// 0 <= alpha_i <= Cn for y_i = -1
//
// Given:
//
// Q, p, y, Cp, Cn, and an initial feasible point \alpha
// l is the size of vectors and matrices
// eps is the stopping tolerance
//
// solution will be put in \alpha, objective value will be put in obj
//
class Solver {
public:
double Gmax; // 사용자 변경
double Gmax2; // 사용자 변경
int Gmin_idx; //사용자 변경
Solver() {};
virtual ~Solver() {};
struct SolutionInfo {
double obj;
double rho;
double upper_bound_p;
double upper_bound_n;
double r; // for Solver_NU
};
void Solve(int l, const QMatrix& Q, const double *p_, const schar *y_,
double *alpha_, double Cp, double Cn, double eps,
SolutionInfo* si, int shrinking);
protected:
int active_size;
schar *y;
double *G; // gradient of objective function ,original
//double *G2; // 변경
enum { LOWER_BOUND, UPPER_BOUND, FREE };
char *alpha_status; // LOWER_BOUND, UPPER_BOUND, FREE
double *alpha;
const QMatrix *Q;
const double *QD;
double eps;
double Cp, Cn;
double *p;
int *active_set;
double *G_bar; // gradient, if we treat free variables as 0 ,original
//double *G_bar2; // 변경
int l;
bool unshrink; // XXX
double get_C(int i)
{
return (y[i] > 0) ? Cp : Cn;
}
void update_alpha_status(int i)
{
if (alpha[i] >= get_C(i))
alpha_status[i] = UPPER_BOUND;
else if (alpha[i] <= 0)
alpha_status[i] = LOWER_BOUND;
else alpha_status[i] = FREE;
}
bool is_upper_bound(int i) { return alpha_status[i] == UPPER_BOUND; }
bool is_lower_bound(int i) { return alpha_status[i] == LOWER_BOUND; }
bool is_free(int i) { return alpha_status[i] == FREE; }
void swap_index(int i, int j);
void reconstruct_gradient();
virtual int select_working_set(int &i, int &j);
void function1(int a, const Qfloat* Q_i, double C_i); //변경 사용자
void function2(int a, const Qfloat* Q_i, double C_i); //변경 사용자
void function3(int a, const Qfloat* Q_j, double C_j); //변경 사용자
void function4(int a, const Qfloat* Q_j, double C_j); //변경 사용자
void G_function1(int a, const Qfloat* Q_i, const Qfloat* Q_j, double delta_alpha_i, double delta_alpha_j); //변경 사용자
void select_working_function_gmax(double Gmax, int Gmax_idx); //변경 사용자
void select_working_function_gmin(double Gmax, double Gmax2, double obj_diff_min, int Gmin_idx, int i, const Qfloat *Q_i); //변경 사용자
virtual double calculate_rho();
virtual void do_shrinking();
private:
bool be_shrunk(int i, double Gmax1, double Gmax2);
};
void Solver::swap_index(int i, int j)
{
Q->swap_index(i, j);
swap(y[i], y[j]);
swap(G[i], G[j]);
swap(alpha_status[i], alpha_status[j]);
swap(alpha[i], alpha[j]);
swap(p[i], p[j]);
swap(active_set[i], active_set[j]);
swap(G_bar[i], G_bar[j]);
}
void Solver::reconstruct_gradient()
{
// reconstruct inactive elements of G from G_bar and free variables
if (active_size == l) return;
int i, j;
int nr_free = 0;
for (j = active_size; j<l; j++)
G[j] = G_bar[j] + p[j];
for (j = 0; j<active_size; j++)
if (is_free(j))
nr_free++;
if (2 * nr_free < active_size)
info("\nWARNING: using -h 0 may be faster\n");
info("_%lf_", Gmax + Gmax2); //사용자 변경
info("-%d-", Gmin_idx); //사용자 변경
if (nr_free*l > 2 * active_size*(l - active_size))
{
for (i = active_size; i<l; i++)
{
const Qfloat *Q_i = Q->get_Q(i, active_size);
for (j = 0; j<active_size; j++)
if (is_free(j))
G[i] += alpha[j] * Q_i[j];
}
}
else
{
for (i = 0; i<active_size; i++)
if (is_free(i))
{
const Qfloat *Q_i = Q->get_Q(i, l);
double alpha_i = alpha[i];
for (j = active_size; j<l; j++)
G[j] += alpha_i * Q_i[j];
}
}
}
void Solver::Solve(int l, const QMatrix& Q, const double *p_, const schar *y_, /////중요
double *alpha_, double Cp, double Cn, double eps,
SolutionInfo* si, int shrinking) //parameter->shrinking //기본 1
{
this->l = l;
this->Q = &Q;
QD = Q.get_QD();
clone(p, p_, l);
clone(y, y_, l);
clone(alpha, alpha_, l);
this->Cp = Cp;
this->Cn = Cn;
this->eps = eps;
unshrink = false;
// initialize alpha_status
{
alpha_status = new char[l];
for (int i = 0; i<l; i++)
update_alpha_status(i);
}
// initialize active set (for shrinking)
{
active_set = new int[l];
for (int i = 0; i<l; i++)
active_set[i] = i;
active_size = l;
}
// initialize gradient
{
G = new double[l]; //G 초기화 original
G_bar = new double[l]; //G_bar 초기화 original
//G2 = new double[l]; //변경
//G_bar2 = new double[l]; //변경
int i;
for (i = 0; i<l; i++)
{
G[i] = p[i];
G_bar[i] = 0;
//G2[i] = p[i]; //변경
//G_bar2[i] = 0; //변경
}
for (i = 0; i<l; i++)
if (!is_lower_bound(i))
{
const Qfloat *Q_i = Q.get_Q(i, l);
double alpha_i = alpha[i];
int j; //original
//int j = 0; //변경
for (j = 0; j<l; j++) //변경 중요 /100000추가, original
G[j] += alpha_i*Q_i[j]; //original
//G2[l] = { alpha_i*Q_i[j], }; //변경
//G[l] =+ G2[l]; //변경
//G2[l] = NULL; //변경
if (is_upper_bound(i))
for (j = 0; j<l; j++) //변경 중요 , original
G_bar[j] += get_C(i) * Q_i[j]; //original
//G_bar2[l] = { get_C(i) * Q_i[j], }; //변경
//G_bar[l] = +G_bar2[l]; //변경
//G_bar2[l] = NULL; //변경
}
}
// optimization step //중요
////////시간 관련///////////
clock_t start, end;
srand((unsigned int)time(NULL));
start = clock(); //변경, 시간측정
int iter = 0;
//int max_iter = max(10000000, l>INT_MAX / 100 ? INT_MAX : 100 * l); ///횟수 지정, original
int counter = min(l, 1000) + 1;
int max_iter = 6000; ////변경
//int max_iter = 6000; //변경 //original
while (iter < max_iter) //연산 오래 걸리는 부분
{
// show progress and do shrinking
if (--counter == 0)
{
counter = min(l, 1000);
if (shrinking) do_shrinking();
info(".");
info("_%lf_", Gmax + Gmax2); //사용자 변경
info("-%d-", Gmin_idx); //사용자 변경
}
int i, j;
if (select_working_set(i, j) != 0) //중요 i = 0 j = 4 //들어감
{
// reconstruct the whole gradient
reconstruct_gradient();
// reset active set size and check
active_size = l;
info("*");
//info("%d", iter/100);
if (select_working_set(i, j) != 0)
break;
else
counter = 1; // do shrinking next iteration
}
++iter;
// update alpha[i] and alpha[j], handle bounds carefully
const Qfloat *Q_i = Q.get_Q(i, active_size); //original
const Qfloat *Q_j = Q.get_Q(j, active_size); //original
//Qfloat *Q_i = Q.get_Q(i, active_size); //변경
//Qfloat *Q_j = Q.get_Q(j, active_size); //변경
//float *Q_i = Q.get_Q(i, active_size); //변경
//float *Q_j = Q.get_Q(j, active_size); //변경
double C_i = get_C(i);
double C_j = get_C(j);
double old_alpha_i = alpha[i];
double old_alpha_j = alpha[j];
if (y[i] != y[j]) //y[i] //1 //alpha, G업데이트 과정
{
double quad_coef = QD[i] + QD[j] + 2 * Q_i[j];
if (quad_coef <= 0)
quad_coef = TAU;
double delta = (-G[i] - G[j]) / quad_coef;
double diff = alpha[i] - alpha[j];
alpha[i] += delta;
alpha[j] += delta;
if (diff > 0)
{
if (alpha[j] < 0)
{
alpha[j] = 0;
alpha[i] = diff;
}
}
else
{
if (alpha[i] < 0)
{
alpha[i] = 0;
alpha[j] = -diff;
}
}
if (diff > C_i - C_j)
{
if (alpha[i] > C_i)
{
alpha[i] = C_i;
alpha[j] = C_i - diff;
}
}
else
{
if (alpha[j] > C_j)
{
alpha[j] = C_j;
alpha[i] = C_j + diff;
}
}
}
else //y[i] //2
{
double quad_coef = QD[i] + QD[j] - 2 * Q_i[j];
if (quad_coef <= 0)
quad_coef = TAU;
double delta = (G[i] - G[j]) / quad_coef;
double sum = alpha[i] + alpha[j];
alpha[i] -= delta;
alpha[j] += delta;
if (sum > C_i)
{
if (alpha[i] > C_i)
{
alpha[i] = C_i;
alpha[j] = sum - C_i;
}
}
else
{
if (alpha[j] < 0)
{
alpha[j] = 0;
alpha[i] = sum;
}
}
if (sum > C_j)
{
if (alpha[j] > C_j)
{
alpha[j] = C_j;
alpha[i] = sum - C_j;
}
}
else
{
if (alpha[i] < 0)
{
alpha[i] = 0;
alpha[j] = sum;
}
}
}
// update G
double delta_alpha_i = alpha[i] - old_alpha_i;
double delta_alpha_j = alpha[j] - old_alpha_j;
std::thread G_thread1(&Solver::G_function1, this, 0, Q_i, Q_j, delta_alpha_i, delta_alpha_j); //사용자 변경
std::thread G_thread2(&Solver::G_function1, this, 1, Q_i, Q_j, delta_alpha_i, delta_alpha_j); //사용자 변경
std::thread G_thread3(&Solver::G_function1, this, 2, Q_i, Q_j, delta_alpha_i, delta_alpha_j); //사용자 변경
G_thread1.join(); //사용자 변경
G_thread2.join(); //사용자 변경
G_thread3.join(); //사용자 변경
//#pragma omp parallel for
/*
for (int k = 0; k<active_size; k++) /////original G 업그래이드 부분 //병렬 처리
{
G[k] += Q_i[k] * delta_alpha_i + Q_j[k] * delta_alpha_j; //original
}
*/
// update alpha_status and G_bar
{
bool ui = is_upper_bound(i);
bool uj = is_upper_bound(j);
update_alpha_status(i);
update_alpha_status(j);
int k;
if (ui != is_upper_bound(i))
{
Q_i = Q.get_Q(i, l);
if (ui){
std::thread thread1(&Solver::function1, this, 0, Q_i, C_i);
std::thread thread2(&Solver::function1, this, 1, Q_i, C_i);
std::thread thread1_a(&Solver::function1, this, 2, Q_i, C_i);
thread1.join();
thread2.join();
thread1_a.join();
//#pragma omp parallel for
/*
for (k = 0; k<l; k++) ///original, G_bar 업그레이드 부분 //병
G_bar[k] -= C_i * Q_i[k]; //original*/
}
else{
//#pragma omp parallel for
/*
for (k = 0; k<l; k++) ///original, G_bar 업그레이드 부분 //병
G_bar[k] += C_i * Q_i[k]; //original
*/
std::thread thread3(&Solver::function2, this, 0, Q_i, C_i);
std::thread thread4(&Solver::function2, this, 1, Q_i, C_i);
std::thread thread3_a(&Solver::function2, this, 2, Q_i, C_i);
thread3.join();
thread4.join();
thread3_a.join();
}
//thread1.detach();
//thread2.detach();
//thread3.detach();
//thread4.detach();
}
if (uj != is_upper_bound(j))
{
Q_j = Q.get_Q(j, l);
if (uj){
//#pragma omp parallel for
/*
for (k = 0; k<l; k++) ///original, G_bar 업그레이드 부분 //병
G_bar[k] -= C_j * Q_j[k]; //original
*/
std::thread thread5(&Solver::function3, this, 0, Q_j, C_j);
std::thread thread6(&Solver::function3, this, 1, Q_j, C_j);
std::thread thread5_a(&Solver::function3, this, 2, Q_j, C_j);
thread5.join();
thread6.join();
thread5_a.join();
}
else{
//#pragma omp parallel for
/*
for (k = 0; k < l; k++) //original
G_bar[k] += C_j * Q_j[k]; ///original, G_bar 업그레이드 부분 //병
*/
std::thread thread7(&Solver::function4, this, 0, Q_j, C_j);
std::thread thread8(&Solver::function4, this, 1, Q_j, C_j);
std::thread thread7_a(&Solver::function4, this, 2, Q_j, C_j);
thread7.join();
thread8.join();
thread7_a.join();
}
}
}
}
if (iter >= max_iter)
{
if (active_size < l)
{
// reconstruct the whole gradient to calculate objective value
reconstruct_gradient();
active_size = l;
info("*");
}
fprintf(stderr, "\nWARNING: reaching max number of iterations\n");
}
// calculate rho
si->rho = calculate_rho();
// calculate objective value
{
double v = 0;
int i;
for (i = 0; i<l; i++)
v += alpha[i] * (G[i] + p[i]);
si->obj = v / 2;
}
// put back the solution
{
for (int i = 0; i<l; i++)
alpha_[active_set[i]] = alpha[i];
}
// juggle everything back
/*{
for(int i=0;i<l;i++)
while(active_set[i] != i)
swap_index(i,active_set[i]);
// or Q.swap_index(i,active_set[i]);
}*/
end = clock(); //변경, 추가
si->upper_bound_p = Cp;
si->upper_bound_n = Cn;
info("\noptimization finished, #iter = %d\n", iter);
info("\ntime = %.3lf sec\n", (end-start)/(double)1000); //변경, 추가
delete[] p;
delete[] y;
delete[] alpha;
delete[] alpha_status;
delete[] active_set;
delete[] G;
delete[] G_bar;
//delete[] G2; //변경
//delete[] G_bar2; //변경
}
void Solver::G_function1(int a, const Qfloat* Q_i, const Qfloat* Q_j, double delta_alpha_i, double delta_alpha_j)
{
//#pragma omp parallel
//#pragma omp parallel for reduction(+:G[k])
for (int k = a; k < active_size;) /////G 업그래이드 부분 //병렬 처리
{
G[k] += Q_i[k] * delta_alpha_i + Q_j[k] * delta_alpha_j;
k = 3 + k; //사용자 변경
}
}
void Solver::function1(int a, const Qfloat* Q_i, double C_i)
{
//#pragma omp parallel
//#pragma omp for //reduction(+:G_bar[k])
for (int k = a; k < l;){ ///G_bar 업그레이드 부분 //병
//mtx_lock.lock();
G_bar[k] -= C_i * Q_i[k];
k = 3 + k; //사용자 변경
//mtx_lock.unlock();
}
}
void Solver::function2(int a, const Qfloat* Q_i, double C_i)
{
//#pragma omp parallel
//#pragma omp for //reduction(+:G_bar[k])
for (int k = a; k < l;){ ///G_bar 업그레이드 부분 //병
//mtx_lock.lock();
G_bar[k] += C_i * Q_i[k];
k = 3 + k; //사용자 변경
//mtx_lock.unlock();
}