[llvm] [AMDGPU] Improve combining on v_ldexp (PR #190236)

[Petar Avramovic via llvm-commits]

petar-avramovic wrote:

@vangthao95 for awareness.
For example look at https://github.com/llvm/llvm-project/pull/179817
you will need to do similar but for intrinsics, something like
```
    addRulesForIOpcs({amdgcn_exp2}, Standard)
      .Uni(S32, {{Sgpr32}, {IntrId, Sgpr32}}, hasPST);
```
but might have to cover more opcodes, types etc
 

https://github.com/llvm/llvm-project/pull/190236