[llvm] [AMDGPU] Fix crash due to missing check for FLAT instructions that dont use vector registers when computing VALU hazard. (PR #123627)

[Chinmay Deshpande via llvm-commits]

================
@@ -858,9 +858,12 @@ int GCNHazardRecognizer::createsVALUHazard(const MachineInstr &MI) {
   }
 
   if (TII->isFLAT(MI)) {
----------------
chinmaydd wrote:

> Is the MIMG case above doing anything? It looks like it's just an assert?

Yes, seems that way. The comment suggests the code exists more as a reminder to include the assert than check anything - 

`All our MIMG definitions use a 256-bit T#, so we can skip checking for them.`

https://github.com/llvm/llvm-project/pull/123627