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
|
//-*-c-*-
#include "linalg.h"
extern "C"
{
__global__ void add(int n, float3 *a, float3 *b, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i] + b[i];
}
__global__ void addequal(int n, float3 *a, float3 *b)
{
int i;
for (i=0; i < n; i++)
a[i] += b[i];
}
__global__ void sub(int n, float3 *a, float3 *b, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i] - b[i];
}
__global__ void subequal(int n, float3 *a, float3 *b)
{
int i;
for (i=0; i < n; i++)
a[i] -= b[i];
}
__gloabl__ void addfloat(int n, float3 *a, float c, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i] + c;
}
__global__ void addfloatequal(int n, float3 *a, float c)
{
int i;
for (i=0; i < n; i++)
a += c;
}
__global__ void subfloat(int n, float3 *a, float c, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i] - c;
}
__global__ void subfloatequal(int n, float3 *a, float c)
{
int i;
for (i=0; i < n; i++)
a[i] -= c;
}
__global__ void mulfloat(int n, float3 *a, float c, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i]*c;
}
__global__ void mulfloatequal(int n, float3 *a, float c)
{
int i;
for (i=0; i < n; i++)
a *= c;
}
__global__ void divfloat(int n, float3 *a, float c, float3 *out)
{
int i;
for (i=0; i < n; i++)
out[i] = a[i]/c;
}
__global__ void divfloatequal(int n, float3 *a, float c)
{
int i;
for (i=0; i < n; i++)
a /= c;
}
__global__ void dot(int n, float3 *a, float3 *b, float* out)
{
int i;
for (i=0; i < n; i++)
out[i] = dot(a,b);
}
} // extern "c"
|
