libSGM Build for CUDA 6.5

[kapildevkumar-a]

I have the following configurations.

Win32 x86
CUDA 6.5
Visual Studio 12 2013
GeForce 730 with Compute Capability 3.5
OpenCV 3.4.3

I have tried building libSGM but getting errors (like __shfl_down,__shfl_xor,__shfl_up not defined) in horizontal_path_aggregation.cu

Will libSGM build for my configuration ? If so, how do I fix it ?

[sotsuka-fixstars]

@kapildevkumar-a Thank you for letting us know this issue.

We didn't test libSGM in an environment like yours, and it is difficult.
We're afraid that we can't handle this issue.
We will keep in mind that README.md and CMakeLists.txt should be updated.

Your GPU(Compute Capability 3.5) and OpenCV(Version 3.4.3) are acceptable for building/using libSGM.
Please consider using newer version of CUDA and Visual Studio if you don't mind.
We tested libSGM in following Windows' environment.

• Windows 10 64bit (x64 platform)
• CUDA 10.1
• Visual Studio Express 2015

Sincerely,

[kapildevkumar-a]

Thank You @sotsuka-fixstars for your reply. I will consider using a newer version of CUDA.

[kapildevkumar-a]

Finally I got it working for the above said Configurations, after fixing issues related to the NVCC Compiler. Thanks :-)

[yingyinyin]

So,could you tell me how to run in the Visual Studio