[LV] Account for vp_merge in out of loop EVL reductions in legacy cost model

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -6567,6 +6567,16 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I,
                  CmpInst::BAD_ICMP_PREDICATE, CostKind);
     }
 
+    // When tail folding with EVL, if the phi is part of an out of loop
+    // reduction then it will be transformed into a wide vp_merge.
+    if (VF.isVector() && foldTailWithEVL() &&
+        Legal->getReductionVars().contains(Phi) && !isInLoopReduction(Phi)) {
+      IntrinsicCostAttributes ICA(
+          Intrinsic::vp_merge, ToVectorTy(Phi->getType(), VF),
+          {ToVectorTy(Type::getInt1Ty(Phi->getContext()), VF)});
+      return TTI.getIntrinsicInstrCost(ICA, CostKind);
+    }
+
     return TTI.getCFInstrCost(Instruction::PHI, CostKind);
   }
   case Instruction::UDiv:

llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction-cost.ll

@@ -0,0 +1,25 @@
+; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize \
+; RUN: -force-tail-folding-style=data-with-evl \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -S < %s 2>&1 | FileCheck %s
+
+; CHECK: Cost of 2 for VF vscale x 4: WIDEN-INTRINSIC vp<%{{.+}}> = call llvm.vp.merge(ir<true>, ir<%add>, ir<%rdx>, vp<%{{.+}}>)
+; CHECK: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction:   %rdx = phi i32 [ %start, %entry ], [ %add, %loop ]
+
+define i32 @add(ptr %a, i64 %n, i32 %start) {
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %rdx = phi i32 [ %start, %entry ], [ %add, %loop ]
+  %arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
+  %0 = load i32, ptr %arrayidx, align 4
+  %add = add nsw i32 %0, %rdx
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond.not = icmp eq i64 %iv.next, %n
+  br i1 %exitcond.not, label %exit, label %loop
+
+exit:
+  ret i32 %add
+}