Address review comments

Author: david-arm

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -10194,8 +10194,7 @@ static InstructionCost calculateEarlyExitCost(LoopVectorizationCostModel &CM,
       // vector.early.exit block, which may contain work to calculate the exit
       // values of variables used outside the loop.
       if (PredVPBB != Plan.getMiddleBlock())
-        for (auto &R : *(cast<VPBasicBlock>(PredVPBB)))
-          Cost += R.cost(VF, CostCtx);
+        Cost += PredVPBB->cost(VF, CostCtx);
     }
   }
   return Cost;
@@ -10218,10 +10217,9 @@ static bool isOutsideLoopWorkProfitable(GeneratedRTChecks &Checks,
   if (!TotalCost.isValid())
     return false;
 
-  // Add on the cost of work required in the vector early exit block, if one
-  // exists.
-  if (CM.Legal->hasUncountableEarlyExit())
-    TotalCost += calculateEarlyExitCost(CM, Plan, VF.Width);
+  // Add on the cost of any work required in the vector early exit block, if
+  // one exists.
+  TotalCost += calculateEarlyExitCost(CM, Plan, VF.Width);
 
   // When interleaving only scalar and vector cost will be equal, which in turn
   // would lead to a divide by 0. Fall back to hard threshold.

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -752,9 +752,8 @@ InstructionCost VPInstruction::computeCost(ElementCount VF,
     InstructionCost Cost = Ctx.TTI.getIntrinsicInstrCost(Attrs, Ctx.CostKind);
     // Add on the cost of extracting the element.
     auto *VecTy = toVectorTy(Ctx.Types.inferScalarType(getOperand(0)), VF);
-    Cost += Ctx.TTI.getVectorInstrCost(Instruction::ExtractElement, VecTy,
-                                       Ctx.CostKind);
-    return Cost;
+    return Cost + Ctx.TTI.getVectorInstrCost(Instruction::ExtractElement, VecTy,
+                                             Ctx.CostKind);
   }
   default:
     // TODO: Compute cost other VPInstructions once the legacy cost model has

llvm/test/Transforms/LoopVectorize/AArch64/low_trip_memcheck_cost.ll

@@ -8,7 +8,7 @@ define void @no_outer_loop(ptr nocapture noundef %a, ptr nocapture noundef reado
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK-NOT:  We expect runtime memory checks to be hoisted out of the outer loop.
 ; CHECK:      Total cost of runtime checks: 4
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %inner.loop
 
@@ -34,7 +34,7 @@ define void @outer_no_tc(ptr nocapture noundef %a, ptr nocapture noundef readonl
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 3
 ; CHECK:      Total cost of runtime checks: 3
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop
 
@@ -71,7 +71,7 @@ define void @outer_known_tc3(ptr nocapture noundef %a, ptr nocapture noundef rea
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 2
 ; CHECK:      Total cost of runtime checks: 2
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop
 
@@ -108,7 +108,7 @@ define void @outer_known_tc64(ptr nocapture noundef %a, ptr nocapture noundef re
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 1
 ; CHECK:      Total cost of runtime checks: 1
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop
 
@@ -145,7 +145,7 @@ define void @outer_pgo_3(ptr nocapture noundef %a, ptr nocapture noundef readonl
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 2
 ; CHECK:      Total cost of runtime checks: 2
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop
 
@@ -182,7 +182,7 @@ define void @outer_pgo_minus1(ptr nocapture noundef %a, ptr nocapture noundef re
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 3
 ; CHECK:      Total cost of runtime checks: 3
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:16
 entry:
   br label %outer.loop
 
@@ -219,7 +219,7 @@ define void @outer_known_tc3_full_range_checks(ptr nocapture noundef %dst, ptr n
 ; CHECK:      Calculating cost of runtime checks:
 ; CHECK:      We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced from 6 to 2
 ; CHECK:      Total cost of runtime checks: 2
-; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:4
+; CHECK:      LV: Minimum required TC for runtime checks to be profitable:4
 entry:
   br label %outer.loop