[llvm] [AMDGCN][SIWholeQuadMode] Handle case when SI_KILL_I1_TERMINATOR -1,0 is not the only terminator (PR #122922)

[Jay Foad via llvm-commits]

jayfoad wrote:

I don't understand this. How can it be correct to remove an unconditional branch? (I understand that it was followed by some other terminator, but that other terminator should never be reached.)

https://github.com/llvm/llvm-project/pull/122922