• Vladislav Vinogradov's avatar
    fix CUDA LUT implementation · eaaa2d27
    Vladislav Vinogradov authored
    In CUDA 6.0 there was a bug in NPP LUT implementation (invalid results when
    src == 255). In CUDA 6.5 the bug was fixed.
    
    Replaced NPP LUT call with own implementation (ported from master branch) 
    to be independant from CUDA Toolkit version.
    eaaa2d27
arithm.cpp 18.9 KB