generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

fixed several problems with CUDA 5.0

Browse Source 
* gpu::LUT, uses device memory instead of host memory
* gpu::multiply, round mod for CV_8U depth
This commit is contained in:
Vladislav Vinogradov
2012-05-28 12:09:40 +00:00
parent 71625ad458
commit 2582464e51
4 changed files with 88 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
modules/gpu/src/arithm.cpp
View File

@@ -320,12 +320,23 @@ void cv::gpu::LUT(const GpuMat& src, const Mat& lut, GpuMat& dst, Stream& s)
const Npp32s* pLevels3[3];
int nValues3[3];
#if (CUDA_VERSION > 4020)
GpuMat d_pLevels;
#endif
LevelsInit()
{
nValues3[0] = nValues3[1] = nValues3[2] = 256;
for (int i = 0; i < 256; ++i)
pLevels[i] = i;
#if (CUDA_VERSION <= 4020)
pLevels3[0] = pLevels3[1] = pLevels3[2] = pLevels;
#else
d_pLevels.upload(Mat(1, 256, CV_32S, pLevels));
pLevels3[0] = pLevels3[1] = pLevels3[2] = d_pLevels.ptr<Npp32s>();
#endif
}
};
static LevelsInit lvls;
@@ -350,22 +361,48 @@ void cv::gpu::LUT(const GpuMat& src, const Mat& lut, GpuMat& dst, Stream& s)
if (src.type() == CV_8UC1)
{
#if (CUDA_VERSION <= 4020)
nppSafeCall( nppiLUT_Linear_8u_C1R(src.ptr<Npp8u>(), static_cast<int>(src.step),
dst.ptr<Npp8u>(), static_cast<int>(dst.step), sz, nppLut.ptr<Npp32s>(), lvls.pLevels, 256) );
#else
GpuMat d_nppLut(Mat(1, 256, CV_32S, nppLut.data));
nppSafeCall( nppiLUT_Linear_8u_C1R(src.ptr<Npp8u>(), static_cast<int>(src.step),
dst.ptr<Npp8u>(), static_cast<int>(dst.step), sz, d_nppLut.ptr<Npp32s>(), lvls.d_pLevels.ptr<Npp32s>(), 256) );
#endif
}
else
{
Mat nppLut3[3];
const Npp32s* pValues3[3];
Mat nppLut3[3];
if (nppLut.channels() == 1)
{
#if (CUDA_VERSION <= 4020)
pValues3[0] = pValues3[1] = pValues3[2] = nppLut.ptr<Npp32s>();
#else
GpuMat d_nppLut(Mat(1, 256, CV_32S, nppLut.data));
pValues3[0] = pValues3[1] = pValues3[2] = d_nppLut.ptr<Npp32s>();
#endif
}
else
{
cv::split(nppLut, nppLut3);
#if (CUDA_VERSION <= 4020)
pValues3[0] = nppLut3[0].ptr<Npp32s>();
pValues3[1] = nppLut3[1].ptr<Npp32s>();
pValues3[2] = nppLut3[2].ptr<Npp32s>();
#else
GpuMat d_nppLut0(Mat(1, 256, CV_32S, nppLut3[0].data));
GpuMat d_nppLut1(Mat(1, 256, CV_32S, nppLut3[1].data));
GpuMat d_nppLut2(Mat(1, 256, CV_32S, nppLut3[2].data));
pValues3[0] = d_nppLut0.ptr<Npp32s>();
pValues3[1] = d_nppLut1.ptr<Npp32s>();
pValues3[2] = d_nppLut2.ptr<Npp32s>();
#endif
}
nppSafeCall( nppiLUT_Linear_8u_C3R(src.ptr<Npp8u>(), static_cast<int>(src.step),
dst.ptr<Npp8u>(), static_cast<int>(dst.step), sz, pValues3, lvls.pLevels3, lvls.nValues3) );
}