[llvm] [AMDGPU] Improve uniform argument handling in InstCombineIntrinsic (PR #105812)

[Jay Foad via llvm-commits]

================
@@ -440,6 +440,22 @@ static bool canContractSqrtToRsq(const FPMathOperator *SqrtOp) {
          SqrtOp->getType()->isHalfTy();
 }
 
+/// Return true if we can easily prove that use U is uniform.
+static bool isTriviallyUniform(const Use &U) {
+  Value *V = U.get();
+  if (isa<Constant>(V))
+    return true;
+  if (auto *I = dyn_cast<Instruction>(V)) {
+    // If I and U are in different blocks then there is a possibility of
+    // temporal divergence.
+    if (I->getParent() != cast<Instruction>(U.getUser())->getParent())
+      return false;
+    if (const auto *II = dyn_cast<IntrinsicInst>(I))
----------------
jayfoad wrote:

Yeah, fair enough. I was trying to leave the door open for extending this code to handle other `Instruction` types, but I don't actually have a use case in mind for that.

https://github.com/llvm/llvm-project/pull/105812