As far as I remember these cards have only 64KB of shared memory.
Set JMP_CNT to 512 and change 17 to 16 in this line in KernelB:
u64* table = LDS + 8 * JMP_CNT + 17 * THREAD_X;
and recalculate LDS_SIZE_ constants.
I think it's enough, though may be I forgot something...
The main issue is not in compiling, but in optimizations, my code is not for 20xx and 30xx cards, so it won't work with good speed there.
That's why I don't want to support old cards: if I support them officially but not optimize you will blame me that they have bad speed.
But feel free to modify/optimize sources for your hardware