diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3286,7 +3286,13 @@
   // If we can't emit a vector call for this function, then the currently found
   // cost is the cost we need to return.
   NeedToScalarize = true;
-  if (!TLI || CI->isNoBuiltin() || VFDatabase::getMappings(*CI).empty())
+  bool NoMappingForVF = true;
+  auto VectorMappings = VFDatabase::getMappings(*CI);
+  for (auto &VFI : VectorMappings)
+    if (VFI.Shape.VF == VF)
+      NoMappingForVF = false;
+
+  if (!TLI || CI->isNoBuiltin() || VectorMappings.empty() || NoMappingForVF)
     return Cost;
 
   // If the corresponding vector cost is cheaper, return its cost.
diff --git a/llvm/test/Transforms/LoopVectorize/widened-massv-call.ll b/llvm/test/Transforms/LoopVectorize/widened-massv-call.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/widened-massv-call.ll
@@ -0,0 +1,59 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -vector-library=MASSV -force-vector-interleave=1 \
+; RUN:   -vectorizer-maximize-bandwidth -O2 -loop-vectorize \
+; RUN:   -mtriple=powerpc64le-unknown-linux -S -mcpu=pwr9 2>&1 | FileCheck %s
+
+define dso_local double @test(float* %Arr) #0 {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <2 x double> [ zeroinitializer, [[ENTRY]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[INDEX]] to i64
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[ARR:%.*]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast float* [[TMP1]] to <2 x float>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, <2 x float>* [[TMP2]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = fpext <2 x float> [[WIDE_LOAD]] to <2 x double>
+; CHECK-NEXT:    [[TMP4:%.*]] = call fast <2 x double> @__sind2_massv(<2 x double> [[TMP3]])
+; CHECK-NEXT:    [[TMP5]] = fadd fast <2 x double> [[TMP4]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], 128
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[DOTLCSSA:%.*]] = phi <2 x double> [ [[TMP5]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[RDX_SHUF:%.*]] = shufflevector <2 x double> [[DOTLCSSA]], <2 x double> undef, <2 x i32> <i32 1, i32 undef>
+; CHECK-NEXT:    [[BIN_RDX:%.*]] = fadd fast <2 x double> [[DOTLCSSA]], [[RDX_SHUF]]
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[BIN_RDX]], i32 0
+; CHECK-NEXT:    ret double [[TMP7]]
+;
+entry:
+  br label %for.cond
+
+for.cond:
+  %Sum.0 = phi double [ 0.000000e+00, %entry ], [ %add, %for.inc ]
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
+  %cmp = icmp slt i32 %i.0, 128
+  br i1 %cmp, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+  br label %for.end
+
+for.body:
+  %idxprom = sext i32 %i.0 to i64
+  %arrayidx = getelementptr inbounds float, float* %Arr, i64 %idxprom
+  %0 = load float, float* %arrayidx, align 4
+  %conv = fpext float %0 to double
+  %1 = call fast double @llvm.sin.f64(double %conv)
+  %add = fadd fast double %Sum.0, %1
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.0, 1
+  br label %for.cond
+
+for.end:
+  ret double %Sum.0
+}
+
+declare double @llvm.sin.f64(double) #2