[llvm] [VPlan] Add support for in-loop AnyOf reductions (PR #131830)

[Luke Lau via llvm-commits]

================
@@ -1184,15 +1184,15 @@ RecurrenceDescriptor::getReductionOpChain(PHINode *Phi, Loop *L) const {
   // more expensive than out-of-loop reductions, and need to be costed more
   // carefully.
   unsigned ExpectedUses = 1;
-  if (RedOp == Instruction::ICmp || RedOp == Instruction::FCmp)
+  if (isMinMaxRecurrenceKind(getRecurrenceKind()))
     ExpectedUses = 2;
 
   auto getNextInstruction = [&](Instruction *Cur) -> Instruction * {
     for (auto *User : Cur->users()) {
       Instruction *UI = cast<Instruction>(User);
       if (isa<PHINode>(UI))
         continue;
-      if (RedOp == Instruction::ICmp || RedOp == Instruction::FCmp) {
+      if (isMinMaxRecurrenceKind(Kind)) {
----------------
lukel97 wrote:

Good point, done in #132025

https://github.com/llvm/llvm-project/pull/131830