[llvm] [LV] Use wide lane masks as the canonical form when tail-folding & interleaving (PR #209484)

[Kerry McLaughlin via llvm-commits]

================
@@ -2037,103 +2037,44 @@ static bool isConditionTrueViaVFAndUF(VPValue *Cond, VPlan &Plan,
   return SE.isKnownPredicate(CmpInst::ICMP_EQ, VectorTripCount, C);
 }
 
-/// Try to replace multiple active lane masks used for control flow with
-/// a single, wide active lane mask instruction followed by multiple
-/// extract subvector intrinsics. This applies to the active lane mask
-/// instructions both in the loop and in the preheader.
-/// Incoming values of all ActiveLaneMaskPHIs are updated to use the
-/// new extracts from the first active lane mask, which has it's last
-/// operand (multiplier) set to UF.
-static bool tryToReplaceALMWithWideALM(VPlan &Plan, ElementCount VF,
-                                       unsigned UF) {
-  if (!EnableWideActiveLaneMask || !VF.isVector() || UF == 1)
+// Replaces ExtractVectorForPart instructions with ICMP when the VF is scalar
+// and the source is a WideActiveLaneMask. The unused mask is removed later
+// when removing dead recipes.
+static bool replaceMaskWithCompare(VPlan &Plan, ElementCount BestVF) {
----------------
kmclaughlin-arm wrote:

I've opened https://github.com/llvm/llvm-project/pull/216340 to change the name of this function & update the comments in VPlan.h

https://github.com/llvm/llvm-project/pull/209484