mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-07-29 00:33:40 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #26245 from cudawarped:cuda_update_to_npp_stream_ctx

Browse Source 
cuda - update npp calls to use the new NppStreamContext API if available
This commit is contained in:
Alexander Smorkalov 2024-10-22 14:44:42 +03:00 committed by GitHub
commit 57ccbee25d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 31 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
modules/core/include/opencv2/core/private.cuda.hpp
View File

@ -134,6 +134,36 @@ namespace cv { namespace cuda
template<> struct NPPTypeTraits<CV_32F> { typedef Npp32f npp_type; }; template<> struct NPPTypeTraits<CV_32F> { typedef Npp32f npp_type; };
template<> struct NPPTypeTraits<CV_64F> { typedef Npp64f npp_type; }; template<> struct NPPTypeTraits<CV_64F> { typedef Npp64f npp_type; };
#define nppSafeCall(expr) cv::cuda::checkNppError(expr, __FILE__, __LINE__, CV_Func)
// NppStreamContext is introduced in NPP version 10100 included in CUDA toolkit 10.1 (CUDA_VERSION == 10010) however not all of the NPP functions called internally by OpenCV
// - have an NppStreamContext argument (e.g. nppiHistogramEvenGetBufferSize_8u_C1R_Ctx in CUDA 12.3) and/or
// - have a corresponding function in the supplied library (e.g. nppiEvenLevelsHost_32s_Ctx is not present in nppist.lib or libnppist.so as of CUDA 12.6)
// Because support for these functions has gradually been introduced without being mentioned in the release notes this flag is set to a version of NPP (version 12205 included in CUDA toolkit 12.4) which is known to work.
#define USE_NPP_STREAM_CTX NPP_VERSION >= 12205
#if USE_NPP_STREAM_CTX
class NppStreamHandler
{
public:
inline explicit NppStreamHandler(cudaStream_t newStream)
{
nppStreamContext = {};
nppSafeCall(nppGetStreamContext(&nppStreamContext));
nppStreamContext.hStream = newStream;
cudaSafeCall(cudaStreamGetFlags(nppStreamContext.hStream, &nppStreamContext.nStreamFlags));
}
inline explicit NppStreamHandler(Stream& newStream) : NppStreamHandler(StreamAccessor::getStream(newStream)) {}
inline operator NppStreamContext() const {
return nppStreamContext;
}
inline NppStreamContext get() { return nppStreamContext; }
private:
NppStreamContext nppStreamContext;
};
#else
class NppStreamHandler class NppStreamHandler
{ {
public: public:
@ -157,9 +187,9 @@ namespace cv { namespace cuda
private: private:
cudaStream_t oldStream; cudaStream_t oldStream;
}; };
#endif
}} }}
#define nppSafeCall(expr) cv::cuda::checkNppError(expr, __FILE__, __LINE__, CV_Func)
#define cuSafeCall(expr) cv::cuda::checkCudaDriverApiError(expr, __FILE__, __LINE__, CV_Func) #define cuSafeCall(expr) cv::cuda::checkCudaDriverApiError(expr, __FILE__, __LINE__, CV_Func)
#endif // HAVE_CUDA #endif // HAVE_CUDA