CudaFy return value from kernel function

Mar 11, 2015 at 4:16 PM
I want to return a single scalar value (maxValue) from a kernal calll. Most CUDA-C folks just declare a
__device__ long MAX;
And use that in the kernel to get around allocating an array of size one and passing a pointer to that array.. Is there a way to do something simple in CudaFY?