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
|
// Comes from
// https://devtalk.nvidia.com/default/topic/1037482/gpu-accelerated-libraries/help-me-help-you-with-modern-cmake-and-cuda-mwe-for-npp/post/5271066/#5271066
#ifdef _WIN32
# define EXPORT __declspec(dllexport)
#else
# define EXPORT
#endif
#include <cstdio>
#include <iostream>
#include <assert.h>
#include <cuda_runtime_api.h>
#include <nppi_filtering_functions.h>
EXPORT int nppif_main()
{
/**
* 8-bit unsigned single-channel 1D row convolution.
*/
const int simgrows = 32;
const int simgcols = 32;
Npp8u *d_pSrc, *d_pDst;
const int nMaskSize = 3;
NppiSize oROI;
oROI.width = simgcols - nMaskSize;
oROI.height = simgrows;
const int simgsize = simgrows * simgcols * sizeof(d_pSrc[0]);
const int dimgsize = oROI.width * oROI.height * sizeof(d_pSrc[0]);
const int simgpix = simgrows * simgcols;
const int dimgpix = oROI.width * oROI.height;
const int nSrcStep = simgcols * sizeof(d_pSrc[0]);
const int nDstStep = oROI.width * sizeof(d_pDst[0]);
const int pixval = 1;
const int nDivisor = 1;
const Npp32s h_pKernel[nMaskSize] = { pixval, pixval, pixval };
Npp32s* d_pKernel;
const Npp32s nAnchor = 2;
cudaError_t err = cudaMalloc((void**)&d_pSrc, simgsize);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
err = cudaMalloc((void**)&d_pDst, dimgsize);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
err = cudaMalloc((void**)&d_pKernel, nMaskSize * sizeof(d_pKernel[0]));
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
// set image to pixval initially
err = cudaMemset(d_pSrc, pixval, simgsize);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
err = cudaMemset(d_pDst, 0, dimgsize);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
err = cudaMemcpy(d_pKernel, h_pKernel, nMaskSize * sizeof(d_pKernel[0]),
cudaMemcpyHostToDevice);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
// copy src to dst
NppStatus ret =
nppiFilterRow_8u_C1R(d_pSrc, nSrcStep, d_pDst, nDstStep, oROI, d_pKernel,
nMaskSize, nAnchor, nDivisor);
assert(ret == NPP_NO_ERROR);
Npp8u* h_imgres = new Npp8u[dimgpix];
err = cudaMemcpy(h_imgres, d_pDst, dimgsize, cudaMemcpyDeviceToHost);
if (err != cudaSuccess) {
fprintf(stderr, "Cuda error %d\n", __LINE__);
return 1;
}
// test for filtering
for (int i = 0; i < dimgpix; i++) {
if (h_imgres[i] != (pixval * pixval * nMaskSize)) {
fprintf(stderr, "h_imgres at index %d failed to match\n", i);
return 1;
}
}
return 0;
}
|
