b6179
OpenCL: add initial FA support (#14987) * add F16/F16 fa support * fix kernel init * use mad instead of fma * use inline function * mark FA with sinks as unsupported for now * add pragma unroll to loops
OpenCL: add initial FA support (#14987) * add F16/F16 fa support * fix kernel init * use mad instead of fma * use inline function * mark FA with sinks as unsupported for now * add pragma unroll to loops