[llvm] [clang] [clang-tools-extra] Improve selection of conditional branch on amdgcn.ballot!=0 condition in SelectionDAG. (PR #68714)

[Valery Pykhtin via cfe-commits]

vpykhtin wrote:

With the latest commit I added a guard to skip _ballot.i64_ in wave32 mode because it's lowered with _i64 AMDGPUISD::SETCC_ - this should be fixed with i32 result similar to ICMP/FCMP intrinsics. After a fix that follows this PR I'm going to turn the guard into assert - TODO is added for this.

https://github.com/llvm/llvm-project/pull/68714