[llvm-branch-commits] [llvm] [AArch64] Prepare for split ZPR and PPR area allocation (NFCI) (PR #142391)

[Sander de Smalen via llvm-branch-commits]

================
@@ -19,6 +19,11 @@
 
 namespace llvm {
 
+struct SVEStackSizes {
----------------
sdesmalen-arm wrote:

Ah yes, those use the same data storage so there will be a conversion required in that function. In that case, I'm happy with an explicit cast as in:
```
unsigned &Offset = OffsetForObject(FI, ZPROffset, PPROffset);
Offset += MFI.getObjectSize(FI);
Offset = alignTo(Offset, MFI.getObjectAlign(FI));
if (AssignOffsets) {
  LLVM_DEBUG(dbgs() << "FI: " << FI << ", Offset: " << -int64_t(Offset) << "\n");
  Assign(FI, -int64_t(Offset));
}
```

(tangentially related; the double LLVM_DEBUG (the one above and the one in `Assign`) look almost identical, can we remove one?)

https://github.com/llvm/llvm-project/pull/142391