[llvm] [WIP][Assume] Generic assume-based uniformity optimization (PR #160670)

[Teja Alaghari via llvm-commits]

================
@@ -1341,6 +1336,15 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
       Call->takeName(&II);
       return IC.replaceInstUsesWith(II, Call);
     }
+
+    if (auto *Src = dyn_cast<ConstantInt>(Arg)) {
----------------
TejaX-Alaghari wrote:

The `ballot(false) → 0` optimization moved to execute *after* Wave32 conversion instead of before. This ensures:
1. Wave32 conversion happens first (i64 → i32 ballot + zext)
2. Then constant folding applies
3. More consistent optimization order

Is this the right approach, or should it stay before Wave32 conversion?

https://github.com/llvm/llvm-project/pull/160670