diff --git a/llvm/include/llvm/Analysis/VectorUtils.h b/llvm/include/llvm/Analysis/VectorUtils.h
--- a/llvm/include/llvm/Analysis/VectorUtils.h
+++ b/llvm/include/llvm/Analysis/VectorUtils.h
@@ -224,6 +224,9 @@
   /// a vector Function ABI.
   static void getVFABIMappings(const CallInst &CI,
                                SmallVectorImpl<VFInfo> &Mappings) {
+    if (CI.isIndirectCall())
+      return;
+
     const StringRef ScalarName = CI.getCalledFunction()->getName();
 
     SmallVector<std::string, 8> ListOfStrings;
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3022,36 +3022,48 @@
       return;
     }
     case Instruction::Call: {
-      // Check if the calls are all to the same vectorizable intrinsic.
+      // Check if the calls are all to the same vectorizable intrinsic or library function.
       CallInst *CI = cast<CallInst>(VL0);
-      // Check if this is an Intrinsic call or something that can be
-      // represented by an intrinsic call
+
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
-      if (!isTriviallyVectorizable(ID)) {
+
+      auto Shape =
+          VFShape::get(*CI, {static_cast<unsigned int>(VL.size()), false},
+                       false /*HasGlobalPred*/);
+      Function *VecFunc = VFDatabase(*CI).getVectorizedFunction(Shape);
+
+      if (!VecFunc && !isTriviallyVectorizable(ID))
+      {
         BS.cancelScheduling(VL, VL0);
         newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                      ReuseShuffleIndicies);
         LLVM_DEBUG(dbgs() << "SLP: Non-vectorizable call.\n");
         return;
       }
-      Function *Int = CI->getCalledFunction();
+
+      Function *F = CI->getCalledFunction();
       unsigned NumArgs = CI->getNumArgOperands();
       SmallVector<Value*, 4> ScalarArgs(NumArgs, nullptr);
+
       for (unsigned j = 0; j != NumArgs; ++j)
         if (hasVectorInstrinsicScalarOpd(ID, j))
           ScalarArgs[j] = CI->getArgOperand(j);
+
       for (Value *V : VL) {
         CallInst *CI2 = dyn_cast<CallInst>(V);
-        if (!CI2 || CI2->getCalledFunction() != Int ||
+
+        if (!CI2 || CI2->getCalledFunction() != F ||
             getVectorIntrinsicIDForCall(CI2, TLI) != ID ||
+            (VecFunc && VecFunc != VFDatabase(*CI2).getVectorizedFunction(Shape)) ||
             !CI->hasIdenticalOperandBundleSchema(*CI2)) {
           BS.cancelScheduling(VL, VL0);
           newTreeEntry(VL, None /*not vectorized*/, S, UserTreeIdx,
                        ReuseShuffleIndicies);
-          LLVM_DEBUG(dbgs() << "SLP: mismatched calls:" << *CI << "!=" << *V
-                            << "\n");
+          LLVM_DEBUG(dbgs()
+                     << "SLP: mismatched calls:" << *CI << "!=" << *V << "\n");
           return;
         }
+
         // Some intrinsics have scalar arguments and should be same in order for
         // them to be vectorized.
         for (unsigned j = 0; j != NumArgs; ++j) {
@@ -3068,6 +3080,7 @@
             }
           }
         }
+
         // Verify that the bundle operands are identical between the two calls.
         if (CI->hasOperandBundles() &&
             !std::equal(CI->op_begin() + CI->getBundleOperandsStartIndex(),
@@ -4507,7 +4520,8 @@
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
 
       auto VecCallCosts = getVectorCallCosts(CI, VecTy, TTI, TLI);
-      bool UseIntrinsic = VecCallCosts.first <= VecCallCosts.second;
+      bool UseIntrinsic = ID != Intrinsic::not_intrinsic &&
+                          VecCallCosts.first <= VecCallCosts.second;
 
       Value *ScalarArg = nullptr;
       std::vector<Value *> OpVecs;
@@ -4527,15 +4541,16 @@
         OpVecs.push_back(OpVec);
       }
 
-      Module *M = F->getParent();
-      Type *Tys[] = {FixedVectorType::get(CI->getType(), E->Scalars.size())};
-      Function *CF = Intrinsic::getDeclaration(M, ID, Tys);
-
+      Function *CF;
       if (!UseIntrinsic) {
         VFShape Shape = VFShape::get(
             *CI, {static_cast<unsigned>(VecTy->getNumElements()), false},
             false /*HasGlobalPred*/);
         CF = VFDatabase(*CI).getVectorizedFunction(Shape);
+      } else {
+        Module *M = F->getParent();
+        Type *Tys[] = {FixedVectorType::get(CI->getType(), E->Scalars.size())};
+        CF = Intrinsic::getDeclaration(M, ID, Tys);
       }
 
       SmallVector<OperandBundleDef, 1> OpBundles;
@@ -5080,6 +5095,18 @@
   return true;
 }
 
+static bool isSideeffectIntrinsic(Instruction *I) {
+  auto *II = dyn_cast<IntrinsicInst>(I);
+
+  return II && II->getIntrinsicID() == Intrinsic::sideeffect;
+}
+
+static bool isVectorizableLibFunctionCall(Instruction *I) {
+  auto *CI = dyn_cast<CallInst>(I);
+
+  return CI && !VFDatabase::getMappings(*CI).empty();
+}
+
 void BoUpSLP::BlockScheduling::initScheduleData(Instruction *FromI,
                                                 Instruction *ToI,
                                                 ScheduleData *PrevLoadStore,
@@ -5096,9 +5123,8 @@
            "new ScheduleData already in scheduling region");
     SD->init(SchedulingRegionID, I);
 
-    if (I->mayReadOrWriteMemory() &&
-        (!isa<IntrinsicInst>(I) ||
-         cast<IntrinsicInst>(I)->getIntrinsicID() != Intrinsic::sideeffect)) {
+    if (I->mayReadOrWriteMemory() && !isSideeffectIntrinsic(I) &&
+        !isVectorizableLibFunctionCall(I)) {
       // Update the linked list of memory accessing instructions.
       if (CurrentLoadStore) {
         CurrentLoadStore->NextLoadStore = SD;
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll
@@ -9,11 +9,846 @@
 
 
 ; Accelerate provides sin() for <4 x float>
+define <4 x float> @int_sin_4x(<4 x float>* %a) {
+; CHECK-LABEL: @int_sin_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @int_sin_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @llvm.sin.f32(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @llvm.sin.f32(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @llvm.sin.f32(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @llvm.sin.f32(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+
+declare float @ceilf(float) #1
+define <4 x float> @ceil_4x(<4 x float>* %a) {
+; CHECK-LABEL: @ceil_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vceilf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @ceil_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @ceilf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @ceilf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @ceilf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @ceilf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @ceilf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @ceilf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @ceilf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @ceilf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+
+declare float @fabsf(float) #1
+define <4 x float> @fabs_4x(<4 x float>* %a) {
+; CHECK-LABEL: @fabs_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vfabsf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @fabs_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @fabsf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @fabsf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @fabsf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @fabsf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @fabsf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @fabsf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @fabsf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @fabsf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @llvm.fabs.f32(float) #1
+define <4 x float> @int_fabs_4x(<4 x float>* %a) {
+; CHECK-LABEL: @int_fabs_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @int_fabs_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; NOACCELERATE-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @llvm.fabs.f32(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @llvm.fabs.f32(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @llvm.fabs.f32(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @llvm.fabs.f32(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @floorf(float) #1
+define <4 x float> @floor_4x(<4 x float>* %a) {
+; CHECK-LABEL: @floor_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vfloorf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @floor_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @floorf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @floorf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @floorf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @floorf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @floorf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @floorf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @floorf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @floorf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @sqrtf(float) #1
+define <4 x float> @sqrt_4x(<4 x float>* %a) {
+; CHECK-LABEL: @sqrt_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsqrtf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @sqrt_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @sqrtf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @sqrtf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @sqrtf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @sqrtf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @sqrtf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @sqrtf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @sqrtf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @sqrtf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @expf(float) #1
+define <4 x float> @exp_4x(<4 x float>* %a) {
+; CHECK-LABEL: @exp_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vexpf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @exp_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @expf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @expf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @expf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @expf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @expf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @expf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @expf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @expm1f(float) #1
+define <4 x float> @expm1_4x(<4 x float>* %a) {
+; CHECK-LABEL: @expm1_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vexpm1f(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @expm1_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @expm1f(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @expm1f(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @expm1f(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @expm1f(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @expm1f(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @expm1f(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @expm1f(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @expm1f(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @logf(float) #1
+define <4 x float> @log_4x(<4 x float>* %a) {
+; CHECK-LABEL: @log_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlogf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @log_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @logf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @logf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @logf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @logf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @logf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @logf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @logf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @log1pf(float) #1
+define <4 x float> @log1p_4x(<4 x float>* %a) {
+; CHECK-LABEL: @log1p_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlog1pf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @log1p_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @log1pf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @log1pf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @log1pf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @log1pf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @log1pf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @log1pf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @log1pf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @log1pf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @log10pf(float) #1
+define <4 x float> @log10p_4x(<4 x float>* %a) {
+; CHECK-LABEL: @log10p_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast float @log10pf(float [[VECEXT]])
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast float @log10pf(float [[VECEXT_1]])
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; CHECK-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; CHECK-NEXT:    [[TMP3:%.*]] = tail call fast float @log10pf(float [[VECEXT_2]])
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; CHECK-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; CHECK-NEXT:    [[TMP4:%.*]] = tail call fast float @log10pf(float [[VECEXT_3]])
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @log10p_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @log10pf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @log10pf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @log10pf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @log10pf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @log10pf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @log10pf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @log10pf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @log10pf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @logbf(float) #1
+define <4 x float> @logb_4x(<4 x float>* %a) {
+; CHECK-LABEL: @logb_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlogbf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @logb_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @logbf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @logbf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @logbf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @logbf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @logbf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @logbf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @logbf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @logbf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @sinf(float) #1
 define <4 x float> @sin_4x(<4 x float>* %a) {
 ; CHECK-LABEL: @sin_4x(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @sin_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @sinf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @sinf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @sinf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @sinf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @sinf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @sinf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @sinf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @cosf(float) #1
+define <4 x float> @cos_4x(<4 x float>* %a) {
+; CHECK-LABEL: @cos_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcosf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @cos_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @cosf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @cosf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @cosf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @cosf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @cosf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @cosf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @cosf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @tanf(float) #1
+define <4 x float> @tan_4x(<4 x float>* %a) {
+; CHECK-LABEL: @tan_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vtanf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @tan_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @tanf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @tanf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @tanf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @tanf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @tanf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @tanf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @tanf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @tanf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @asinf(float) #1
+define <4 x float> @asin_4x(<4 x float>* %a) {
+; CHECK-LABEL: @asin_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vasinf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @asin_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @asinf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @asinf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @asinf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @asinf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @asinf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @asinf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @asinf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @asinf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @acosf(float) #1
+define <4 x float> @acos_4x(<4 x float>* %a) {
+; CHECK-LABEL: @acos_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vacosf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @acos_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @acosf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @acosf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @acosf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @acosf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @acosf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @acosf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @acosf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @acosf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @atanf(float) #1
+define <4 x float> @atan_4x(<4 x float>* %a) {
+; CHECK-LABEL: @atan_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vatanf(<4 x float> [[TMP0]])
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
 ; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
@@ -24,36 +859,330 @@
 ; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
 ; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
 ;
-; NOACCELERATE-LABEL: @sin_4x(
+; NOACCELERATE-LABEL: @atan_4x(
 ; NOACCELERATE-NEXT:  entry:
 ; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
 ; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
-; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @atanf(float [[VECEXT]])
 ; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
 ; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
-; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @atanf(float [[VECEXT_1]])
 ; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
 ; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
-; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @atanf(float [[VECEXT_2]])
 ; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
 ; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
-; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @atanf(float [[VECEXT_3]])
 ; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
 ; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
 ;
 entry:
   %0 = load <4 x float>, <4 x float>* %a, align 16
   %vecext = extractelement <4 x float> %0, i32 0
-  %1 = tail call fast float @llvm.sin.f32(float %vecext)
+  %1 = tail call fast float @atanf(float %vecext)
   %vecins = insertelement <4 x float> undef, float %1, i32 0
   %vecext.1 = extractelement <4 x float> %0, i32 1
-  %2 = tail call fast float @llvm.sin.f32(float %vecext.1)
+  %2 = tail call fast float @atanf(float %vecext.1)
   %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
   %vecext.2 = extractelement <4 x float> %0, i32 2
-  %3 = tail call fast float @llvm.sin.f32(float %vecext.2)
+  %3 = tail call fast float @atanf(float %vecext.2)
   %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
   %vecext.3 = extractelement <4 x float> %0, i32 3
-  %4 = tail call fast float @llvm.sin.f32(float %vecext.3)
+  %4 = tail call fast float @atanf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @sinhf(float) #1
+define <4 x float> @sinh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @sinh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinhf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @sinh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @sinhf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @sinhf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @sinhf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @sinhf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @sinhf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @sinhf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @sinhf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @sinhf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @coshf(float) #1
+define <4 x float> @cosh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @cosh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcoshf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @cosh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @coshf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @coshf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @coshf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @coshf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @coshf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @coshf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @coshf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @coshf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @tanhf(float) #1
+define <4 x float> @tanh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @tanh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vtanhf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @tanh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @tanhf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @tanhf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @tanhf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @tanhf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @tanhf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @tanhf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @tanhf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @tanhf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @asinhf(float) #1
+define <4 x float> @asinh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @asinh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vasinhf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @asinh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @asinhf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @asinhf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @asinhf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @asinhf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @asinhf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @asinhf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @asinhf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @asinhf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @acoshf(float) #1
+define <4 x float> @acosh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @acosh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vacoshf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @acosh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @acoshf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @acoshf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @acoshf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @acoshf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @acoshf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @acoshf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @acoshf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @acoshf(float %vecext.3)
+  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
+  ret <4 x float> %vecins.3
+}
+declare float @atanhf(float) #1
+define <4 x float> @atanh_4x(<4 x float>* %a) {
+; CHECK-LABEL: @atanh_4x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vatanhf(<4 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP4]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
+; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+; NOACCELERATE-LABEL: @atanh_4x(
+; NOACCELERATE-NEXT:  entry:
+; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
+; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
+; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @atanhf(float [[VECEXT]])
+; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
+; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
+; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @atanhf(float [[VECEXT_1]])
+; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
+; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
+; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @atanhf(float [[VECEXT_2]])
+; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
+; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
+; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @atanhf(float [[VECEXT_3]])
+; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
+; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
+;
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  %1 = tail call fast float @atanhf(float %vecext)
+  %vecins = insertelement <4 x float> undef, float %1, i32 0
+  %vecext.1 = extractelement <4 x float> %0, i32 1
+  %2 = tail call fast float @atanhf(float %vecext.1)
+  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
+  %vecext.2 = extractelement <4 x float> %0, i32 2
+  %3 = tail call fast float @atanhf(float %vecext.2)
+  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
+  %vecext.3 = extractelement <4 x float> %0, i32 3
+  %4 = tail call fast float @atanhf(float %vecext.3)
   %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
   ret <4 x float> %vecins.3
 }
@@ -97,8 +1226,8 @@
 declare float @llvm.cos.f32(float) #1
 
 ; Accelerate provides cos() for <4 x float>
-define <4 x float> @cos_4x(<4 x float>* %a) {
-; CHECK-LABEL: @cos_4x(
+define <4 x float> @int_cos_4x(<4 x float>* %a) {
+; CHECK-LABEL: @int_cos_4x(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
 ; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcosf(<4 x float> [[TMP0]])
@@ -112,7 +1241,7 @@
 ; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP5]], i32 3
 ; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
 ;
-; NOACCELERATE-LABEL: @cos_4x(
+; NOACCELERATE-LABEL: @int_cos_4x(
 ; NOACCELERATE-NEXT:  entry:
 ; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, <4 x float>* [[A:%.*]], align 16
 ; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0