[LV] Stop using the legacy cost model for udiv + friends

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -4278,6 +4278,26 @@ VectorizationFactor LoopVectorizationPlanner::selectVectorizationFactor() {
           if (!VPI)
             continue;
           switch (VPI->getOpcode()) {
+          // Selects are not modelled in the legacy cost model if they are
+          // inserted for reductions.
+          case Instruction::Select: {
+            VPValue *V =
+                R.getNumDefinedValues() == 1 ? R.getVPSingleValue() : nullptr;
+            if (V && V->getNumUsers() == 1) {
+              if (auto *UR = dyn_cast<VPWidenRecipe>(*V->user_begin())) {
+                switch (UR->getOpcode()) {
+                case Instruction::UDiv:
+                case Instruction::SDiv:
+                case Instruction::URem:
+                case Instruction::SRem:
+                  continue;
+                default:
+                  break;
+                }
+              }
+            }
+            [[fallthrough]];
+          }
           case VPInstruction::ActiveLaneMask:
           case VPInstruction::ExplicitVectorLength:
             C += VPI->cost(VF, CostCtx);

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -1029,6 +1029,19 @@ InstructionCost VPInstruction::computeCost(ElementCount VF,
   }
 
   switch (getOpcode()) {
+  case Instruction::Select: {
+    // TODO: It may be possible to improve this by analyzing where the
+    // condition operand comes from.
+    CmpInst::Predicate Pred = CmpInst::BAD_ICMP_PREDICATE;
+    auto *CondTy = Ctx.Types.inferScalarType(getOperand(0));
+    auto *VecTy = Ctx.Types.inferScalarType(getOperand(1));
+    if (!vputils::onlyFirstLaneUsed(this)) {
+      CondTy = toVectorTy(CondTy, VF);
+      VecTy = toVectorTy(VecTy, VF);
+    }
+    return Ctx.TTI.getCmpSelInstrCost(Instruction::Select, VecTy, CondTy, Pred,
+                                      Ctx.CostKind);
+  }
   case Instruction::ExtractElement:
   case VPInstruction::ExtractLane: {
     // Add on the cost of extracting the element.
@@ -2099,8 +2112,10 @@ InstructionCost VPWidenRecipe::computeCost(ElementCount VF,
   case Instruction::SDiv:
   case Instruction::SRem:
   case Instruction::URem:
-    // More complex computation, let the legacy cost-model handle this for now.
-    return Ctx.getLegacyCost(cast<Instruction>(getUnderlyingValue()), VF);
+    // If the div/rem operation isn't safe to speculate and requires
+    // predication, then the only way we can even create a vplan is to insert
+    // a select on the second input operand to ensure we use the value of 1
+    // for the inactive lanes. The select will be costed separately.
   case Instruction::FNeg:
   case Instruction::Add:
   case Instruction::FAdd: