[LV] Ignore some costs when loop gets fully unrolled

When VF has a fixed width and equals the number of iterations, and we are not
tail folding by masking, comparison instruction and induction operation will
be DCEed later.
Ignoring the costs of these instructions improves the cost model.

Author: igogo-x86

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7248,6 +7248,26 @@ LoopVectorizationPlanner::precomputeCosts(VPlan &Plan, ElementCount VF,
         continue;
       IVInsts.push_back(CI);
     }
+
+    // If the given VF loop gets fully unrolled, ignore the costs of comparison
+    // and increment instruction, as they'll get simplified away
+    auto TC = CM.PSE.getSE()->getSmallConstantTripCount(OrigLoop);
+    auto *Cmp = OrigLoop->getLatchCmpInst();
+    if (Cmp && VF.isFixed() && VF.getFixedValue() == TC) {
+      CostCtx.SkipCostComputation.insert(Cmp);
+      for (Instruction *IVInst : IVInsts) {
+        bool IsSimplifiedAway = true;
+        for (auto *UIV : IVInst->users()) {
+          if (!Legal->isInductionVariable(UIV) && UIV != Cmp) {
+            IsSimplifiedAway = false;
+            break;
+          }
+        }
+        if (IsSimplifiedAway)
+          CostCtx.SkipCostComputation.insert(IVInst);
+      }
+    }
+
     for (Instruction *IVInst : IVInsts) {
       if (CostCtx.skipCostComputation(IVInst, VF.isVector()))
         continue;