From e375d5786b3f31834d6fcc058cd6dee187bba240 Mon Sep 17 00:00:00 2001
From: cudawarped <12133430+cudawarped@users.noreply.github.com>
Date: Wed, 2 Oct 2024 13:52:37 +0300
Subject: [PATCH] cuda - update npp calls to use the new NppStreamContext API
 if available

---
 .../include/opencv2/core/private.cuda.hpp     | 32 ++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/modules/core/include/opencv2/core/private.cuda.hpp b/modules/core/include/opencv2/core/private.cuda.hpp
index 36edd8ab31..39f2ddcdeb 100644
--- a/modules/core/include/opencv2/core/private.cuda.hpp
+++ b/modules/core/include/opencv2/core/private.cuda.hpp
@@ -134,6 +134,36 @@ namespace cv { namespace cuda
     template<> struct NPPTypeTraits<CV_32F> { typedef Npp32f 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
     {
     public:
@@ -157,9 +187,9 @@ namespace cv { namespace cuda
     private:
         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)
 
 #endif // HAVE_CUDA