-
Notifications
You must be signed in to change notification settings - Fork 5
/
sptrsv.cpp
178 lines (162 loc) · 5.38 KB
/
sptrsv.cpp
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
//
// Created by george on 2019-10-09.
//
#ifdef ENABLE_OPENMP
#include <omp.h>
#endif
#include "sptrsv.h"
namespace sym_lib {
void sptrsv_csr(int n, int *Lp, int *Li, double *Lx, double *x) {
int i, j;
for (i = 0; i < n; i++) {
for (j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
void sptrsv_csr_levelset(int n, const int *Lp, const int *Li, const double *Lx,
double *x,
int levels, const int *levelPtr,
const int *levelSet) {
#pragma omp parallel
{
for (int l = 0; l < levels; l++) {
//#pragma omp parallel for default(shared) schedule(auto)
#pragma omp for schedule(auto)
for (int k = levelPtr[l]; k < levelPtr[l + 1]; ++k) {
int i = levelSet[k];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
};
}
void sptrsv_csr_levelset_seq(int n, const int *Lp, const int *Li, const double *Lx,
double *x,
int levels, const int *levelPtr,
const int *levelSet) {
for (int l = 0; l < levels; l++) {
for (int k = levelPtr[l]; k < levelPtr[l + 1]; ++k) {
int i = levelSet[k];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
}
void sptrsv_csr_lbc_seq(int n, int *Lp, int *Li, double *Lx, double *x,
int level_no, int *level_ptr,
int *par_ptr, int *partition) {
//#pragma omp parallel
{
for (int i1 = 0; i1 < level_no; ++i1) {
//#pragma omp for schedule(auto)
// printf("len=%d\n", level_ptr[i1+1]-level_ptr[i1]);
for (int j1 = level_ptr[i1]; j1 < level_ptr[i1 + 1]; ++j1) {
for (int k1 = par_ptr[j1]; k1 < par_ptr[j1 + 1]; ++k1) {
int i = partition[k1];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
}
};
}
void sptrsv_csr_lbc(int n, int *Lp, int *Li, double *Lx, double *x,
int level_no, int *level_ptr,
int *par_ptr, int *partition) {
#pragma omp parallel
{
for (int i1 = 0; i1 < level_no; ++i1) {
#pragma omp for schedule(auto)
for (int j1 = level_ptr[i1]; j1 < level_ptr[i1 + 1]; ++j1) {
for (int k1 = par_ptr[j1]; k1 < par_ptr[j1 + 1]; ++k1) {
int i = partition[k1];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
}
};
}
void sptrsv_csr_group_lbc(int n, int *Lp, int *Li, double *Lx, double *x,
int level_no, int *level_ptr,
int *par_ptr, int *partition, int *groupPtr, int *groupSet) {
#pragma omp parallel
{
for (int i1 = 0; i1 < level_no; ++i1) {
#pragma omp for schedule(auto)
for (int j1 = level_ptr[i1]; j1 < level_ptr[i1 + 1]; ++j1) {
for (int k1 = par_ptr[j1]; k1 < par_ptr[j1 + 1]; ++k1) {
int p = partition[k1];
for (int k = groupPtr[p]; k < groupPtr[p+1]; ++k) {
int i = groupSet[k];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++) {
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
}
}
};
}
///=============================================================================
///============================= HDAGG SPARSE BLASS ============================
///=============================================================================
//=========================== Left Looking SpTrSv ==========================
void sptrsv_csr_levelset(int n, const int *Lp, const int *Li, const double *Lx,
int levels, const int *levelPtr, const int *levelSet,
double *x)
{
#pragma omp parallel
{
for (int l = 0; l < levels; l++)
{
#pragma omp for schedule(auto)
for (int k = levelPtr[l]; k < levelPtr[l + 1]; ++k)
{
int i = levelSet[k];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++)
{
x[i] -= Lx[j] * x[Li[j]];//S1
}
x[i] /= Lx[Lp[i + 1] - 1]; //S2
}
}
}
}
void sptrsv_csr_group_levelset(int *Lp, int *Li, double *Lx, double *x,
int level_no, int *level_ptr, int *level_set,
int *groupPtr, int *groupSet)
{
#pragma omp parallel
{
for (int i1 = 0; i1 < level_no; ++i1)
{
#pragma omp for schedule(auto)
for (int j1 = level_ptr[i1]; j1 < level_ptr[i1 + 1]; ++j1)
{
int group_idx = level_set[j1];
for (int k = groupPtr[group_idx]; k < groupPtr[group_idx + 1]; ++k)
{
int i = groupSet[k];
for (int j = Lp[i]; j < Lp[i + 1] - 1; j++)
{
x[i] -= Lx[j] * x[Li[j]];
}
x[i] /= Lx[Lp[i + 1] - 1];
}
}
}
}
}
}