Similar to
cudaFuncSetCacheConfig(fooKernel, cudaFuncCachePreferL1)
I cannot find any example on how to do this. Is it possible?
It is certainly possible, but it is not currently something exposed by CUDAdrv.jl
If you feel up to it that would be great first contribution to CUDAdrv.jl you would need to wrap and expose the functions documented here:
http://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__EXEC.html