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
|
//-*-c-*-
extern "C"
{
__global__ void add(float3 *a, float3 *b, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx] + b[idx];
}
__global__ void addequal(float3 *a, float3 *b)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] += b[idx];
}
__global__ void sub(float3 *a, float3 *b, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx] - b[idx];
}
__global__ void subequal(float3 *a, float3 *b)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] -= b[idx];
}
__global__ void addfloat(float3 *a, float c, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx] + c;
}
__global__ void addfloatequal(float3 *a, float c)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] += c;
}
__global__ void subfloat(float3 *a, float c, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx] - c;
}
__global__ void subfloatequal(float3 *a, float c)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] -= c;
}
__global__ void mulfloat(float3 *a, float c, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx]*c;
}
__global__ void mulfloatequal(float3 *a, float c)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] *= c;
}
__global__ void divfloat(float3 *a, float c, float3 *dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = a[idx]/c;
}
__global__ void divfloatequal(float3 *a, float c)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
a[idx] /= c;
}
__global__ void dot(float3 *a, float3 *b, float* dest)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
dest[idx] = dot(a[idx],b[idx]);
}
} // extern "c"
|
