Closed ancahamuraru closed 9 years ago
The CUDA kernels use the __any warp vote function.
The OpenCL kernels have implemented this function using local memory. Search for: warp_any
Verify the OpenCL implementation, test it and fix it, if any problems are found.
Done. See the implementation and comments for __any warp vote function here 72458c9c7bdd641ee02e2e6ca6cbeb031977ddb7
The CUDA kernels use the __any warp vote function.
The OpenCL kernels have implemented this function using local memory. Search for: warp_any
Verify the OpenCL implementation, test it and fix it, if any problems are found.