fix bug announced in #52

If the miner is compiled in debug mode the assert condition results in a compile time error.

use `__shffl_snyc` if CUDA 9+ is avalable

- use always a multiple of the number of compute units
- add more device information to the config file

Early returns within a kernel can have unexpected behavior, this strongly depends on the opencl
runtime compiler. To avoid errors all early returns are removed.
There is no negative effect(e.g.performance) if the threads stay alive up to the end of the kernel.

One source for the early return is: http://al-key-opencl.blogspot.de/2014/09/be-careful-not-to-mix-early-return-and.html

This pull request also fix a race condition where all fill the shared memory.
Also a bug introduced with #16 is fixed, because of the early return not was possible that
the last block works with an wrong initilized shared memory (result should be a wrong hash if the result target size is valid).

Is is possible that the number of results are greater than the result output array,
in this case invalid memory can be access within the device and on the host side.

check that the number of global threads is a multiple of the workgroup size

The number of threads within a kernel must be a multiple of the worksize.
If not it can crash on some systems.

Platform index zero was always used to search for the device detection.

Fix: use correct detected AMD platform index

- add nicehash flag back to `miner_work`

- Add a proper UAC manifest requesting elevation when we start
- Fix self_test() - this is integral part of initialisation

use nicehash start nonce in all backends if nicehash is enabled

- string literal can only be 16kbyte

- add clang compile section
- cleanup CMake file
- fix missing return value