Skip to content

Try to Fix #3725: cudaarithm: fix the compile faiure of CUDA 12. #3726

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 22, 2024
Merged

Try to Fix #3725: cudaarithm: fix the compile faiure of CUDA 12. #3726

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions modules/cudaarithm/src/reductions.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,12 @@ void cv::cuda::meanStdDev(InputArray src, OutputArray dst, Stream& stream)
sz.width = gsrc.cols;
sz.height = gsrc.rows;

#if (CUDA_VERSION >= 12040)
size_t bufSize;
#else
int bufSize;
#endif

#if (CUDA_VERSION <= 4020)
nppSafeCall( nppiMeanStdDev8uC1RGetBufferHostSize(sz, &bufSize) );
#else
Expand All @@ -162,7 +167,8 @@ void cv::cuda::meanStdDev(InputArray src, OutputArray dst, Stream& stream)
#endif

BufferPool pool(stream);
GpuMat buf = pool.getBuffer(1, bufSize, gsrc.type());
CV_Assert(bufSize <= std::numeric_limits<int>::max());
GpuMat buf = pool.getBuffer(1, static_cast<int>(bufSize), gsrc.type());

// detail: https://github.com/opencv/opencv/issues/11063
//NppStreamHandler h(StreamAccessor::getStream(stream));
Expand Down Expand Up @@ -227,7 +233,12 @@ void cv::cuda::meanStdDev(InputArray src, OutputArray dst, InputArray mask, Stre
sz.width = gsrc.cols;
sz.height = gsrc.rows;

#if (CUDA_VERSION >= 12040)
size_t bufSize;
#else
int bufSize;
#endif

#if (CUDA_VERSION <= 4020)
nppSafeCall( nppiMeanStdDev8uC1MRGetBufferHostSize(sz, &bufSize) );
#else
Expand All @@ -238,7 +249,8 @@ void cv::cuda::meanStdDev(InputArray src, OutputArray dst, InputArray mask, Stre
#endif

BufferPool pool(stream);
GpuMat buf = pool.getBuffer(1, bufSize, gsrc.type());
CV_Assert(bufSize <= std::numeric_limits<int>::max());
GpuMat buf = pool.getBuffer(1, static_cast<int>(bufSize), gsrc.type());

if(gsrc.type() == CV_8UC1)
nppSafeCall( nppiMean_StdDev_8u_C1MR(gsrc.ptr<Npp8u>(), static_cast<int>(gsrc.step), gmask.ptr<Npp8u>(), static_cast<int>(gmask.step),
Expand Down