C++ C/C+中的双线性插值+;和库达
我想在CPU上模拟CUDA双线性插值的行为,但我发现C++ C/C+中的双线性插值+;和库达,c++,cuda,C++,Cuda,我想在CPU上模拟CUDA双线性插值的行为,但我发现tex2D的返回值似乎不适合该函数 我猜将插值系数从float转换为9-位固定点格式,使用8位的分数值会产生不同的值 根据转换公式,当系数为1/2^n,且n=0,1,…,8时,转换结果将与输入的float相同,但我仍然(并非总是)收到奇怪的值 下面我报告一个奇怪值的例子。在这种情况下,id=2*n+1时总是会出现奇怪的值,有人能告诉我为什么吗 Src数组: Src[0][0] = 38; Src[1][0] = 39; Src[0]
tex2D
的返回值似乎不适合该函数
我猜将插值系数从float
转换为9
-位固定点格式,使用8
位的分数值会产生不同的值
根据转换公式,当系数为1/2^n
,且n=0,1,…,8
时,转换结果将与输入的float
相同,但我仍然(并非总是)收到奇怪的值
下面我报告一个奇怪值的例子。在这种情况下,id=2*n+1
时总是会出现奇怪的值,有人能告诉我为什么吗
Src数组:
Src[0][0] = 38;
Src[1][0] = 39;
Src[0][1] = 118;
Src[1][1] = 13;
static texture<float4, 2, cudaReadModeElementType> texElnt;
texElnt.addressMode[0] = cudaAddressModeClamp;
texElnt.addressMode[1] = cudaAddressModeClamp;
texElnt.filterMode = cudaFilterModeLinear;
texElnt.normalized = false;
static __global__ void kernel_texElnt(float* pdata, int w, int h, int c, float stride/*0.03125f*/) {
const int gx = blockIdx.x*blockDim.x + threadIdx.x;
const int gy = blockIdx.y*blockDim.y + threadIdx.y;
const int gw = gridDim.x * blockDim.x;
const int gid = gy*gw + gx;
if (gx >= w || gy >= h) {
return;
}
float2 pnt;
pnt.x = (gx)*(stride)/*1/32*/;
pnt.y = 0.0625f/*1/16*/;
float4 result = tex2D( texElnt, pnt.x + 0.5, pnt.y + 0.5f);
pdata[gid*3 + 0] = pnt.x;
pdata[gid*3 + 1] = pnt.y;
pdata[gid*3 + 2] = result.x;
}
纹理定义:
Src[0][0] = 38;
Src[1][0] = 39;
Src[0][1] = 118;
Src[1][1] = 13;
static texture<float4, 2, cudaReadModeElementType> texElnt;
texElnt.addressMode[0] = cudaAddressModeClamp;
texElnt.addressMode[1] = cudaAddressModeClamp;
texElnt.filterMode = cudaFilterModeLinear;
texElnt.normalized = false;
static __global__ void kernel_texElnt(float* pdata, int w, int h, int c, float stride/*0.03125f*/) {
const int gx = blockIdx.x*blockDim.x + threadIdx.x;
const int gy = blockIdx.y*blockDim.y + threadIdx.y;
const int gw = gridDim.x * blockDim.x;
const int gid = gy*gw + gx;
if (gx >= w || gy >= h) {
return;
}
float2 pnt;
pnt.x = (gx)*(stride)/*1/32*/;
pnt.y = 0.0625f/*1/16*/;
float4 result = tex2D( texElnt, pnt.x + 0.5, pnt.y + 0.5f);
pdata[gid*3 + 0] = pnt.x;
pdata[gid*3 + 1] = pnt.y;
pdata[gid*3 + 2] = result.x;
}
CUDA的双线性结果
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.0000000
1 0.03125 0.0625 42.6171875
2 0.06250 0.0625 42.6484375
3 0.09375 0.0625 42.2656250
4 0.12500 0.0625 42.2968750
5 0.15625 0.0625 41.9140625
6 0.18750 0.0625 41.9453125
7 0.21875 0.0625 41.5625000
8 0.25000 0.0625 41.5937500
9 0.28125 0.0625 41.2109375
0 0.31250 0.0625 41.2421875
10 0.34375 0.0625 40.8593750
11 0.37500 0.0625 40.8906250
12 0.40625 0.0625 40.5078125
13 0.43750 0.0625 40.5390625
14 0.46875 0.0625 40.1562500
15 0.50000 0.0625 40.1875000
16 0.53125 0.0625 39.8046875
17 0.56250 0.0625 39.8359375
18 0.59375 0.0625 39.4531250
19 0.62500 0.0625 39.4843750
20 0.65625 0.0625 39.1015625
21 0.68750 0.0625 39.1328125
22 0.71875 0.0625 38.7500000
23 0.75000 0.0625 38.7812500
24 0.78125 0.0625 38.3984375
25 0.81250 0.0625 38.4296875
26 0.84375 0.0625 38.0468750
27 0.87500 0.0625 38.0781250
28 0.90625 0.0625 37.6953125
29 0.93750 0.0625 37.7265625
30 0.96875 0.0625 37.3437500
31 1.00000 0.0625 37.3750000
// convert coefficient ((1-α)*(1-β)), (α*(1-β)), ((1-α)*β), (α*β) to fixed point format
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.00000000
1 0.03125 0.0625 43.23046875
2 0.06250 0.0625 42.64843750
3 0.09375 0.0625 42.87890625
4 0.12500 0.0625 42.29687500
5 0.15625 0.0625 42.52734375
6 0.18750 0.0625 41.94531250
7 0.21875 0.0625 42.17578125
8 0.25000 0.0625 41.59375000
9 0.28125 0.0625 41.82421875
0 0.31250 0.0625 41.24218750
10 0.34375 0.0625 41.47265625
11 0.37500 0.0625 40.89062500
12 0.40625 0.0625 41.12109375
13 0.43750 0.0625 40.53906250
14 0.46875 0.0625 40.76953125
15 0.50000 0.0625 40.18750000
16 0.53125 0.0625 40.41796875
17 0.56250 0.0625 39.83593750
18 0.59375 0.0625 40.06640625
19 0.62500 0.0625 39.48437500
20 0.65625 0.0625 39.71484375
21 0.68750 0.0625 39.13281250
22 0.71875 0.0625 39.36328125
23 0.75000 0.0625 38.78125000
24 0.78125 0.0625 39.01171875
25 0.81250 0.0625 38.42968750
26 0.84375 0.0625 38.66015625
27 0.87500 0.0625 38.07812500
28 0.90625 0.0625 38.30859375
29 0.93750 0.0625 37.72656250
30 0.96875 0.0625 37.95703125
31 1.00000 0.0625 37.37500000
tex(x,y)=T[i,j] + frac(α)(T[i+1,j]-T[i,j]) + frac(β)(T[i,j+1]-T[i,j]) + frac(αβ)(T[i,j]+T[i+1,j+1] - T[i+1, j]-T[i,j+1])
// frac(x) turns float to 9-bit fixed point format with 8 bits of fraction values.
float frac( float x ) {
float frac, tmp = x - (float)(int)(x);
float frac256 = (float)(int)( tmp*256.0f + 0.5f );
frac = frac256 / 256.0f;
return frac;
}
CPU结果:
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.0000000
1 0.03125 0.0625 42.6171875
2 0.06250 0.0625 42.6484375
3 0.09375 0.0625 42.2656250
4 0.12500 0.0625 42.2968750
5 0.15625 0.0625 41.9140625
6 0.18750 0.0625 41.9453125
7 0.21875 0.0625 41.5625000
8 0.25000 0.0625 41.5937500
9 0.28125 0.0625 41.2109375
0 0.31250 0.0625 41.2421875
10 0.34375 0.0625 40.8593750
11 0.37500 0.0625 40.8906250
12 0.40625 0.0625 40.5078125
13 0.43750 0.0625 40.5390625
14 0.46875 0.0625 40.1562500
15 0.50000 0.0625 40.1875000
16 0.53125 0.0625 39.8046875
17 0.56250 0.0625 39.8359375
18 0.59375 0.0625 39.4531250
19 0.62500 0.0625 39.4843750
20 0.65625 0.0625 39.1015625
21 0.68750 0.0625 39.1328125
22 0.71875 0.0625 38.7500000
23 0.75000 0.0625 38.7812500
24 0.78125 0.0625 38.3984375
25 0.81250 0.0625 38.4296875
26 0.84375 0.0625 38.0468750
27 0.87500 0.0625 38.0781250
28 0.90625 0.0625 37.6953125
29 0.93750 0.0625 37.7265625
30 0.96875 0.0625 37.3437500
31 1.00000 0.0625 37.3750000
// convert coefficient ((1-α)*(1-β)), (α*(1-β)), ((1-α)*β), (α*β) to fixed point format
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.00000000
1 0.03125 0.0625 43.23046875
2 0.06250 0.0625 42.64843750
3 0.09375 0.0625 42.87890625
4 0.12500 0.0625 42.29687500
5 0.15625 0.0625 42.52734375
6 0.18750 0.0625 41.94531250
7 0.21875 0.0625 42.17578125
8 0.25000 0.0625 41.59375000
9 0.28125 0.0625 41.82421875
0 0.31250 0.0625 41.24218750
10 0.34375 0.0625 41.47265625
11 0.37500 0.0625 40.89062500
12 0.40625 0.0625 41.12109375
13 0.43750 0.0625 40.53906250
14 0.46875 0.0625 40.76953125
15 0.50000 0.0625 40.18750000
16 0.53125 0.0625 40.41796875
17 0.56250 0.0625 39.83593750
18 0.59375 0.0625 40.06640625
19 0.62500 0.0625 39.48437500
20 0.65625 0.0625 39.71484375
21 0.68750 0.0625 39.13281250
22 0.71875 0.0625 39.36328125
23 0.75000 0.0625 38.78125000
24 0.78125 0.0625 39.01171875
25 0.81250 0.0625 38.42968750
26 0.84375 0.0625 38.66015625
27 0.87500 0.0625 38.07812500
28 0.90625 0.0625 38.30859375
29 0.93750 0.0625 37.72656250
30 0.96875 0.0625 37.95703125
31 1.00000 0.0625 37.37500000
tex(x,y)=T[i,j] + frac(α)(T[i+1,j]-T[i,j]) + frac(β)(T[i,j+1]-T[i,j]) + frac(αβ)(T[i,j]+T[i+1,j+1] - T[i+1, j]-T[i,j+1])
// frac(x) turns float to 9-bit fixed point format with 8 bits of fraction values.
float frac( float x ) {
float frac, tmp = x - (float)(int)(x);
float frac256 = (float)(int)( tmp*256.0f + 0.5f );
frac = frac256 / 256.0f;
return frac;
}
我保留了一个简单的代码,运行程序后,您将在D:\
中获得两个文件
编辑2014/01/20
我以不同的增量运行程序,发现
tex2D
“当alpha
乘以beta
小于0.00390625
时,tex2D
的返回与双线性插值公式不匹配”UV插值被截断为9位,不是参与的texel值。在CUDA手册的第10章(纹理)中,对1D情况进行了详细描述(包括CPU仿真代码)。这段代码是开源的,可以在中找到。错误的双线性插值公式使得纹理提取的结果很奇怪
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.0000000
1 0.03125 0.0625 42.6171875
2 0.06250 0.0625 42.6484375
3 0.09375 0.0625 42.2656250
4 0.12500 0.0625 42.2968750
5 0.15625 0.0625 41.9140625
6 0.18750 0.0625 41.9453125
7 0.21875 0.0625 41.5625000
8 0.25000 0.0625 41.5937500
9 0.28125 0.0625 41.2109375
0 0.31250 0.0625 41.2421875
10 0.34375 0.0625 40.8593750
11 0.37500 0.0625 40.8906250
12 0.40625 0.0625 40.5078125
13 0.43750 0.0625 40.5390625
14 0.46875 0.0625 40.1562500
15 0.50000 0.0625 40.1875000
16 0.53125 0.0625 39.8046875
17 0.56250 0.0625 39.8359375
18 0.59375 0.0625 39.4531250
19 0.62500 0.0625 39.4843750
20 0.65625 0.0625 39.1015625
21 0.68750 0.0625 39.1328125
22 0.71875 0.0625 38.7500000
23 0.75000 0.0625 38.7812500
24 0.78125 0.0625 38.3984375
25 0.81250 0.0625 38.4296875
26 0.84375 0.0625 38.0468750
27 0.87500 0.0625 38.0781250
28 0.90625 0.0625 37.6953125
29 0.93750 0.0625 37.7265625
30 0.96875 0.0625 37.3437500
31 1.00000 0.0625 37.3750000
// convert coefficient ((1-α)*(1-β)), (α*(1-β)), ((1-α)*β), (α*β) to fixed point format
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.00000000
1 0.03125 0.0625 43.23046875
2 0.06250 0.0625 42.64843750
3 0.09375 0.0625 42.87890625
4 0.12500 0.0625 42.29687500
5 0.15625 0.0625 42.52734375
6 0.18750 0.0625 41.94531250
7 0.21875 0.0625 42.17578125
8 0.25000 0.0625 41.59375000
9 0.28125 0.0625 41.82421875
0 0.31250 0.0625 41.24218750
10 0.34375 0.0625 41.47265625
11 0.37500 0.0625 40.89062500
12 0.40625 0.0625 41.12109375
13 0.43750 0.0625 40.53906250
14 0.46875 0.0625 40.76953125
15 0.50000 0.0625 40.18750000
16 0.53125 0.0625 40.41796875
17 0.56250 0.0625 39.83593750
18 0.59375 0.0625 40.06640625
19 0.62500 0.0625 39.48437500
20 0.65625 0.0625 39.71484375
21 0.68750 0.0625 39.13281250
22 0.71875 0.0625 39.36328125
23 0.75000 0.0625 38.78125000
24 0.78125 0.0625 39.01171875
25 0.81250 0.0625 38.42968750
26 0.84375 0.0625 38.66015625
27 0.87500 0.0625 38.07812500
28 0.90625 0.0625 38.30859375
29 0.93750 0.0625 37.72656250
30 0.96875 0.0625 37.95703125
31 1.00000 0.0625 37.37500000
tex(x,y)=T[i,j] + frac(α)(T[i+1,j]-T[i,j]) + frac(β)(T[i,j+1]-T[i,j]) + frac(αβ)(T[i,j]+T[i+1,j+1] - T[i+1, j]-T[i,j+1])
// frac(x) turns float to 9-bit fixed point format with 8 bits of fraction values.
float frac( float x ) {
float frac, tmp = x - (float)(int)(x);
float frac256 = (float)(int)( tmp*256.0f + 0.5f );
frac = frac256 / 256.0f;
return frac;
}
公式-1:您可以在cuda附录或wiki中轻松找到它
tex(x,y)=(1−α)(1−β)T[i,j] + α(1−β)T[i+1,j] + (1−α)βT[i,j+1] + αβT[i+1,j+1]
公式-2:减少乘法次数
tex(x,y)=T[i,j] + α(T[i+1,j]-T[i,j]) + β(T[i,j+1]-T[i,j]) + αβ(T[i,j]+T[i+1,j+1] - T[i+1, j]-T[i,j+1])
如果对公式1使用9位定点格式,将得到纹理获取的不匹配结果,但公式2可以正常工作
结论:如果要模拟cuda纹理实现的双线性插值,应使用公式3。试试看 公式-3:
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.0000000
1 0.03125 0.0625 42.6171875
2 0.06250 0.0625 42.6484375
3 0.09375 0.0625 42.2656250
4 0.12500 0.0625 42.2968750
5 0.15625 0.0625 41.9140625
6 0.18750 0.0625 41.9453125
7 0.21875 0.0625 41.5625000
8 0.25000 0.0625 41.5937500
9 0.28125 0.0625 41.2109375
0 0.31250 0.0625 41.2421875
10 0.34375 0.0625 40.8593750
11 0.37500 0.0625 40.8906250
12 0.40625 0.0625 40.5078125
13 0.43750 0.0625 40.5390625
14 0.46875 0.0625 40.1562500
15 0.50000 0.0625 40.1875000
16 0.53125 0.0625 39.8046875
17 0.56250 0.0625 39.8359375
18 0.59375 0.0625 39.4531250
19 0.62500 0.0625 39.4843750
20 0.65625 0.0625 39.1015625
21 0.68750 0.0625 39.1328125
22 0.71875 0.0625 38.7500000
23 0.75000 0.0625 38.7812500
24 0.78125 0.0625 38.3984375
25 0.81250 0.0625 38.4296875
26 0.84375 0.0625 38.0468750
27 0.87500 0.0625 38.0781250
28 0.90625 0.0625 37.6953125
29 0.93750 0.0625 37.7265625
30 0.96875 0.0625 37.3437500
31 1.00000 0.0625 37.3750000
// convert coefficient ((1-α)*(1-β)), (α*(1-β)), ((1-α)*β), (α*β) to fixed point format
id pnt.x pnt.y tex2D
0 0.00000 0.0625 43.00000000
1 0.03125 0.0625 43.23046875
2 0.06250 0.0625 42.64843750
3 0.09375 0.0625 42.87890625
4 0.12500 0.0625 42.29687500
5 0.15625 0.0625 42.52734375
6 0.18750 0.0625 41.94531250
7 0.21875 0.0625 42.17578125
8 0.25000 0.0625 41.59375000
9 0.28125 0.0625 41.82421875
0 0.31250 0.0625 41.24218750
10 0.34375 0.0625 41.47265625
11 0.37500 0.0625 40.89062500
12 0.40625 0.0625 41.12109375
13 0.43750 0.0625 40.53906250
14 0.46875 0.0625 40.76953125
15 0.50000 0.0625 40.18750000
16 0.53125 0.0625 40.41796875
17 0.56250 0.0625 39.83593750
18 0.59375 0.0625 40.06640625
19 0.62500 0.0625 39.48437500
20 0.65625 0.0625 39.71484375
21 0.68750 0.0625 39.13281250
22 0.71875 0.0625 39.36328125
23 0.75000 0.0625 38.78125000
24 0.78125 0.0625 39.01171875
25 0.81250 0.0625 38.42968750
26 0.84375 0.0625 38.66015625
27 0.87500 0.0625 38.07812500
28 0.90625 0.0625 38.30859375
29 0.93750 0.0625 37.72656250
30 0.96875 0.0625 37.95703125
31 1.00000 0.0625 37.37500000
tex(x,y)=T[i,j] + frac(α)(T[i+1,j]-T[i,j]) + frac(β)(T[i,j+1]-T[i,j]) + frac(αβ)(T[i,j]+T[i+1,j+1] - T[i+1, j]-T[i,j+1])
// frac(x) turns float to 9-bit fixed point format with 8 bits of fraction values.
float frac( float x ) {
float frac, tmp = x - (float)(int)(x);
float frac256 = (float)(int)( tmp*256.0f + 0.5f );
frac = frac256 / 256.0f;
return frac;
}
已经提供了满意的答案,所以现在我只想给出一个关于双线性插值有用的信息的概要,它如何在C++中实现,以及它在CUDA中可以做的不同的方式。p> 双线性插值背后的数学
假设原始函数
T(x,y)
在点的笛卡尔规则网格(i,j)
中使用0进行采样,你能添加其他人可以编译和运行的最短完整示例吗?谢谢你的建议@Talonmes,我提供了示例代码的链接。谢谢你的回复,我以前也读过代码(与文章中的链接2相同)。根据链接,如果x=1/2^n(n=1,2,…8),那么frac应该等于x。我得到了与tex2D不匹配的结果,所以我在这里发布了我的问题。