[SLP]Fix gathering of the scalars by not ignoring UndefValues.

[ABataev]

Summary

The compiler should not ignore UndefValue when gathering the scalars,
otherwise the resulting code may be less defined than the original one.
Also, grouped scalars to insert them at first to reduce the analysis in
further passes.

[alexfh]

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

4876

"values"?

[ABataev]

Fixed a comment

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

4876

Fixed, thanks!

[alexfh]

The patch fixes the segfaults we've seen after https://reviews.llvm.org/D103458.

[alexfh]

I have no idea what this code is doing, but just based on the fact that it fixes the problem, it looks good to me ;)

You probably want a review from someone who knows this code though.

[Carrot]

Thanks for the fix!
The changes to CreateInsertElement looks good to me. But I'm not confident to review other parts of the patch.

[vdmitrie]

LGTM. Thank you, Alexey.

[rupprecht]

Thanks Alexey!

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

for (int I = 0, E = VL.size(); I < E; ++I) {
     if (auto *Inst = dyn_cast<Instruction>(VL[I]))
       if ((CheckPredecessor(Inst->getParent(), Builder.GetInsertBlock()) ||
            getTreeEntry(Inst) || (L && (L->contains(Inst)))) &&
           PostponedIndices.insert(I).second)
         PostponedInsts.emplace_back(Inst, I);
   }
 
   auto &&CreateInsertElement = [this](Value *Vec, Value *V, unsigned Pos) {
-    // No need to insert undefs elements - exit.
-    if (isa<UndefValue>(V))
-      return Vec;
     Vec = Builder.CreateInsertElement(Vec, V, Builder.getInt32(Pos));
     auto *InsElt = dyn_cast<InsertElementInst>(Vec);
     if (!InsElt)
       return Vec;
     GatherSeq.insert(InsElt);
     CSEBlocks.insert(InsElt->getParent());
     // Add to our 'need-to-extract' list.
     if (TreeEntry *Entry = getTreeEntry(V)) {
       // Find which lane we need to extract.
       unsigned FoundLane =
           std::distance(Entry->Scalars.begin(), find(Entry->Scalars, V));
       assert(FoundLane < Entry->Scalars.size() && "Couldn't find extract lane");
       if (!Entry->ReuseShuffleIndices.empty()) {
         FoundLane = std::distance(Entry->ReuseShuffleIndices.begin(),
                                   find(Entry->ReuseShuffleIndices, FoundLane));
       }
       ExternalUses.emplace_back(V, InsElt, FoundLane);
     }
     return Vec;
   };
   Value *Val0 =
       isa<StoreInst>(VL[0]) ? cast<StoreInst>(VL[0])->getValueOperand() : VL[0];
   FixedVectorType *VecTy = FixedVectorType::get(Val0->getType(), VL.size());
   Value *Vec = PoisonValue::get(VecTy);
+  SmallVector<int> NonConsts;
+  // Insert constant values at first.
   for (int I = 0, E = VL.size(); I < E; ++I) {
     if (PostponedIndices.contains(I))
       continue;
+    if (!isConstant(VL[I])) {
+      NonConsts.push_back(I);
+      continue;
+    }
     Vec = CreateInsertElement(Vec, VL[I], I);
   }
+  // Insert non-constant values.
+  for (int I : NonConsts)
+    Vec = CreateInsertElement(Vec, VL[I], I);
   // Append instructions, which are/may be part of the loop, in the end to make
   // it possible to hoist non-loop-based instructions.
   for (const std::pair<Value *, unsigned> &Pair : PostponedInsts)
     Vec = CreateInsertElement(Vec, Pair.first, Pair.second);
 
   return Vec;
 }
 
if (HasUndefs && UniqueVals == 1 && UniqueValues.size() == 1) {
       else
         ReuseShuffleIndicies.assign(VF, 0);
     } else if (UniqueValues.size() >= VF - 1 || UniqueValues.size() <= 1) {
       ReuseShuffleIndicies.clear();
       UniqueValues.clear();
       UniqueValues.append(VL.begin(), std::next(VL.begin(), NumValues));
     }
     UniqueValues.append(VF - UniqueValues.size(),
-                        UndefValue::get(VL[0]->getType()));
+                        PoisonValue::get(VL[0]->getType()));
     VL = UniqueValues;
   }
 
   ShuffleInstructionBuilder ShuffleBuilder(Builder, VF);
   Value *Vec = gather(VL);
   if (!ReuseShuffleIndicies.empty()) {
     ShuffleBuilder.addMask(ReuseShuffleIndicies);
     Vec = ShuffleBuilder.finalize(Vec);

llvm/test/Transforms/SLPVectorizer/AArch64/insertelement-inseltpoison.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -slp-vectorizer -S | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"
 
 define <2 x float> @insertelement-fixed-vector() {
 ; CHECK-LABEL: @insertelement-fixed-vector(
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x float> @llvm.fabs.v2f32(<2 x float> poison)
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
 ; CHECK-NEXT:    ret <2 x float> [[TMP1]]
 ;
   %f0 = tail call fast float @llvm.fabs.f32(float undef)
   %f1 = tail call fast float @llvm.fabs.f32(float undef)
   %i0 = insertelement <2 x float> poison, float %f0, i32 0
   %i1 = insertelement <2 x float> %i0, float %f1, i32 1
   ret <2 x float> %i1
 }

llvm/test/Transforms/SLPVectorizer/AArch64/insertelement.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -slp-vectorizer -S | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64-unknown-linux-gnu"
 
 define <2 x float> @insertelement-fixed-vector() {
 ; CHECK-LABEL: @insertelement-fixed-vector(
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x float> @llvm.fabs.v2f32(<2 x float> poison)
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
 ; CHECK-NEXT:    ret <2 x float> [[TMP1]]
 ;
   %f0 = tail call fast float @llvm.fabs.f32(float undef)
   %f1 = tail call fast float @llvm.fabs.f32(float undef)
   %i0 = insertelement <2 x float> undef, float %f0, i32 0
   %i1 = insertelement <2 x float> %i0, float %f1, i32 1
   ret <2 x float> %i1
 }

llvm/test/Transforms/SLPVectorizer/AArch64/trunc-insertion.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -slp-vectorizer -S | FileCheck %s
 target triple = "aarch64-unknown-linux-gnu"
 @d = internal unnamed_addr global i32 5, align 4
 
 define dso_local void @l() local_unnamed_addr {
 ; CHECK-LABEL: @l(
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    br label [[BB1:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ poison, [[BB:%.*]] ], [ [[TMP11:%.*]], [[BB25:%.*]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[BB:%.*]] ], [ [[TMP11:%.*]], [[BB25:%.*]] ]
 ; CHECK-NEXT:    br i1 undef, label [[BB3:%.*]], label [[BB11:%.*]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    [[I4:%.*]] = zext i1 undef to i32
-; CHECK-NEXT:    [[TMP1:%.*]] = xor <2 x i16> [[TMP0]], poison
+; CHECK-NEXT:    [[TMP1:%.*]] = xor <2 x i16> [[TMP0]], undef
 ; CHECK-NEXT:    [[TMP2:%.*]] = icmp ugt <2 x i16> [[TMP1]], <i16 8, i16 8>
 ; CHECK-NEXT:    [[TMP3:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32>
 ; CHECK-NEXT:    br label [[BB25]]
 ; CHECK:       bb11:
 ; CHECK-NEXT:    [[I12:%.*]] = zext i1 undef to i32
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i16> [[TMP0]], poison
+; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i16> [[TMP0]], undef
 ; CHECK-NEXT:    [[TMP5:%.*]] = sext <2 x i16> [[TMP4]] to <2 x i64>
-; CHECK-NEXT:    [[TMP6:%.*]] = icmp ule <2 x i64> poison, [[TMP5]]
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp ule <2 x i64> undef, [[TMP5]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = zext <2 x i1> [[TMP6]] to <2 x i32>
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp ult <2 x i32> poison, [[TMP7]]
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp ult <2 x i32> undef, [[TMP7]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = zext <2 x i1> [[TMP8]] to <2 x i32>
 ; CHECK-NEXT:    br label [[BB25]]
 ; CHECK:       bb25:
 ; CHECK-NEXT:    [[I28:%.*]] = phi i32 [ [[I12]], [[BB11]] ], [ [[I4]], [[BB3]] ]
 ; CHECK-NEXT:    [[TMP10:%.*]] = phi <2 x i32> [ [[TMP9]], [[BB11]] ], [ [[TMP3]], [[BB3]] ]
 ; CHECK-NEXT:    [[TMP11]] = phi <2 x i16> [ [[TMP4]], [[BB11]] ], [ [[TMP1]], [[BB3]] ]
 ; CHECK-NEXT:    [[TMP12:%.*]] = trunc <2 x i32> [[TMP10]] to <2 x i8>
 ; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x i8> [[TMP12]], i32 0

llvm/test/Transforms/SLPVectorizer/X86/crash_exceed_scheduling.ll

 ; CHECK-NEXT:    [[IXX22:%.*]] = fsub double undef, undef
 ; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[TMP6]], i32 0
 ; CHECK-NEXT:    [[IX2:%.*]] = fmul double [[TMP8]], [[TMP8]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP1]], i32 1
 ; CHECK-NEXT:    [[TMP10:%.*]] = fadd fast <2 x double> [[TMP6]], [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = fadd fast <2 x double> [[TMP3]], [[TMP5]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = fmul fast <2 x double> [[TMP10]], [[TMP11]]
 ; CHECK-NEXT:    [[IXX101:%.*]] = fsub double undef, undef
-; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <2 x double> poison, double [[TMP7]], i32 0
-; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <2 x double> poison, double [[TMP1]], i32 1
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <2 x double> <double poison, double undef>, double [[TMP7]], i32 0
+; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <2 x double> <double undef, double poison>, double [[TMP1]], i32 1
 ; CHECK-NEXT:    [[TMP15:%.*]] = fmul fast <2 x double> [[TMP13]], [[TMP14]]
 ; CHECK-NEXT:    switch i32 undef, label [[BB1:%.*]] [
 ; CHECK-NEXT:    i32 0, label [[BB2:%.*]]
 ; CHECK-NEXT:    ]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    br label [[LABEL:%.*]]
 ; CHECK:       bb2:
 ; CHECK-NEXT:    br label [[LABEL]]

llvm/test/Transforms/SLPVectorizer/X86/crash_lencod.ll

 
 define fastcc void @dct36(double* %inbuf) {
 ; CHECK-LABEL: @dct36(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds double, double* [[INBUF:%.*]], i64 1
 ; CHECK-NEXT:    [[TMP0:%.*]] = bitcast double* [[INBUF]] to <2 x double>*
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> poison, double [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> <double poison, double undef>, double [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[ARRAYIDX44]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %arrayidx41 = getelementptr inbounds double, double* %inbuf, i64 2
   %arrayidx44 = getelementptr inbounds double, double* %inbuf, i64 1
   %0 = load double, double* %arrayidx44, align 8
   %add46 = fadd double %0, undef
   store double %add46, double* %arrayidx41, align 8
   %1 = load double, double* %inbuf, align 8
   %add49 = fadd double %1, %0
   store double %add49, double* %arrayidx44, align 8
   ret void
 }

llvm/test/Transforms/SLPVectorizer/X86/crash_mandeltext.ll

 
 define void @zot(%struct.hoge* %arg) {
 ; CHECK-LABEL: @zot(
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    [[TMP:%.*]] = load double, double* undef, align 8
 ; CHECK-NEXT:    [[TMP2:%.*]] = load double, double* undef, align 8
 ; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> poison, double [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[TMP]], i32 1
-; CHECK-NEXT:    [[TMP2:%.*]] = fsub <2 x double> [[TMP1]], poison
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub <2 x double> [[TMP1]], undef
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_HOGE:%.*]], %struct.hoge* [[ARG:%.*]], i64 0, i32 1
-; CHECK-NEXT:    [[TMP3:%.*]] = fmul <2 x double> [[TMP2]], poison
-; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], poison
+; CHECK-NEXT:    [[TMP3:%.*]] = fmul <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], undef
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TMP7]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8
 ; CHECK-NEXT:    br i1 undef, label [[BB11:%.*]], label [[BB12:%.*]]
 ; CHECK:       bb11:
 ; CHECK-NEXT:    br label [[BB14:%.*]]
 ; CHECK:       bb12:
 ; CHECK-NEXT:    br label [[BB14]]
 ; CHECK:       bb14:

llvm/test/Transforms/SLPVectorizer/X86/crash_smallpt.ll

 ; CHECK:       for.cond36.preheader:
 ; CHECK-NEXT:    br i1 undef, label [[FOR_BODY42_LR_PH_US:%.*]], label [[_Z5CLAMPD_EXIT_1:%.*]]
 ; CHECK:       cond.false51.us:
 ; CHECK-NEXT:    unreachable
 ; CHECK:       cond.true48.us:
 ; CHECK-NEXT:    br i1 undef, label [[COND_TRUE63_US:%.*]], label [[COND_FALSE66_US:%.*]]
 ; CHECK:       cond.false66.us:
 ; CHECK-NEXT:    [[ADD_I276_US:%.*]] = fadd double 0.000000e+00, undef
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> poison, double [[ADD_I276_US]], i32 0
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> <double poison, double undef>, double [[ADD_I276_US]], i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = fadd <2 x double> [[TMP0]], <double 0.000000e+00, double 0xBFA5CC2D1960285F>
 ; CHECK-NEXT:    [[TMP2:%.*]] = fmul <2 x double> [[TMP1]], <double 1.400000e+02, double 1.400000e+02>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fadd <2 x double> [[TMP2]], <double 5.000000e+01, double 5.200000e+01>
-; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> poison, [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> undef, [[TMP1]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[AGG_TMP99208_SROA_0_0_IDX]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP3]], <2 x double>* [[TMP5]], align 8
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast double* [[AGG_TMP101211_SROA_0_0_IDX]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP6]], align 8
 ; CHECK-NEXT:    unreachable
 ; CHECK:       cond.true63.us:
 ; CHECK-NEXT:    unreachable
 ; CHECK:       for.body42.lr.ph.us:

 %struct.Ray.5.11.53.95.137.191.197.203.239.257.263.269.275.281.287.293.383.437.443.455.461.599.601 = type { %struct.Vec.0.6.48.90.132.186.192.198.234.252.258.264.270.276.282.288.378.432.438.450.456.594.600, %struct.Vec.0.6.48.90.132.186.192.198.234.252.258.264.270.276.282.288.378.432.438.450.456.594.600 }
 %struct.Vec.0.6.48.90.132.186.192.198.234.252.258.264.270.276.282.288.378.432.438.450.456.594.600 = type { double, double, double }
 
 define void @_Z8radianceRK3RayiPt() #0 {
 ; CHECK-LABEL: @_Z8radianceRK3RayiPt(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 undef, label [[IF_THEN78:%.*]], label [[IF_THEN38:%.*]]
 ; CHECK:       if.then38:
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> poison, double poison, i32 1
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul <2 x double> poison, [[TMP0]]
-; CHECK-NEXT:    [[TMP2:%.*]] = fsub <2 x double> poison, [[TMP1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = fmul <2 x double> poison, [[TMP2]]
-; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> poison, [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> poison, [[TMP4]]
-; CHECK-NEXT:    [[TMP6:%.*]] = fadd <2 x double> poison, [[TMP5]]
-; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x double> poison, [[TMP6]]
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> <double undef, double poison>, double undef, i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul <2 x double> undef, [[TMP0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub <2 x double> undef, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fmul <2 x double> undef, [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> undef, [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> undef, [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = fadd <2 x double> undef, [[TMP5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x double> undef, [[TMP6]]
 ; CHECK-NEXT:    [[AGG_TMP74663_SROA_0_0_IDX:%.*]] = getelementptr inbounds [[STRUCT_RAY_5_11_53_95_137_191_197_203_239_257_263_269_275_281_287_293_383_437_443_455_461_599_601:%.*]], %struct.Ray.5.11.53.95.137.191.197.203.239.257.263.269.275.281.287.293.383.437.443.455.461.599.601* undef, i64 0, i32 1, i32 0
 ; CHECK-NEXT:    [[TMP8:%.*]] = bitcast double* [[AGG_TMP74663_SROA_0_0_IDX]] to <2 x double>*
 ; CHECK-NEXT:    store <2 x double> [[TMP7]], <2 x double>* [[TMP8]], align 8
 ; CHECK-NEXT:    br label [[RETURN:%.*]]
 ; CHECK:       if.then78:
 ; CHECK-NEXT:    br label [[RETURN]]
 ; CHECK:       return:
 ; CHECK-NEXT:    ret void

llvm/test/Transforms/SLPVectorizer/X86/geps-non-pow-2.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=haswell < %s | FileCheck %s
 @e = dso_local local_unnamed_addr global i32 0, align 4
 @f = dso_local local_unnamed_addr global i32 0, align 4
 
 ; Function Attrs: nofree norecurse nounwind uwtable
 define dso_local i32 @g() local_unnamed_addr {
 ; CHECK-LABEL: @g(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* @e, align 4
 ; CHECK-NEXT:    [[TOBOOL_NOT19:%.*]] = icmp eq i32 [[TMP0]], 0
 ; CHECK-NEXT:    br i1 [[TOBOOL_NOT19]], label [[WHILE_END:%.*]], label [[WHILE_BODY:%.*]]
 ; CHECK:       while.body:
 ; CHECK-NEXT:    [[C_022:%.*]] = phi i32* [ [[C_022_BE:%.*]], [[WHILE_BODY_BACKEDGE:%.*]] ], [ undef, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x i32*> [ [[TMP14:%.*]], [[WHILE_BODY_BACKEDGE]] ], [ poison, [[ENTRY]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x i32*> [ [[TMP14:%.*]], [[WHILE_BODY_BACKEDGE]] ], [ undef, [[ENTRY]] ]
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[C_022]], i64 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = ptrtoint i32* [[C_022]] to i64
 ; CHECK-NEXT:    [[TMP3:%.*]] = trunc i64 [[TMP2]] to i32
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i32, <2 x i32*> [[TMP1]], <2 x i64> <i64 1, i64 1>
 ; CHECK-NEXT:    switch i32 [[TMP3]], label [[WHILE_BODY_BACKEDGE]] [
 ; CHECK-NEXT:    i32 2, label [[SW_BB:%.*]]
 ; CHECK-NEXT:    i32 4, label [[SW_BB6:%.*]]
 ; CHECK-NEXT:    ]

llvm/test/Transforms/SLPVectorizer/X86/phi3.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -basic-aa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
 
 %struct.GPar.0.16.26 = type { [0 x double], double }
 
 @d = external global double, align 8
 
 declare %struct.GPar.0.16.26* @Rf_gpptr(...)
 
 define void @Rf_GReset() {
 ; CHECK-LABEL: @Rf_GReset(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load double, double* @d, align 8
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> poison, double [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> <double undef, double poison>, double [[TMP0]], i32 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, [[TMP1]]
 ; CHECK-NEXT:    br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label [[IF_THEN:%.*]], label [[IF_END7:%.*]]
 ; CHECK:       if.then:
-; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
-; CHECK-NEXT:    [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], poison
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], undef
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
 ; CHECK-NEXT:    [[CMP:%.*]] = fcmp ogt double [[TMP5]], [[TMP6]]
 ; CHECK-NEXT:    br i1 [[CMP]], label [[IF_THEN6:%.*]], label [[IF_END7]]
 ; CHECK:       if.then6:
 ; CHECK-NEXT:    br label [[IF_END7]]
 ; CHECK:       if.end7:
 ; CHECK-NEXT:    ret void
if.end7:                                          ; preds = %if.then6, %if.then, %entry
   %g.0 = phi double [ 0.000000e+00, %if.then6 ], [ %sub, %if.then ], [ %sub, %entry ]
   ret void
 }
 
 define void @Rf_GReset_unary_fneg() {
 ; CHECK-LABEL: @Rf_GReset_unary_fneg(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load double, double* @d, align 8
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> poison, double [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> <double undef, double poison>, double [[TMP0]], i32 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = fneg <2 x double> [[TMP1]]
 ; CHECK-NEXT:    br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label [[IF_THEN:%.*]], label [[IF_END7:%.*]]
 ; CHECK:       if.then:
-; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
-; CHECK-NEXT:    [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], poison
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], undef
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
 ; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
 ; CHECK-NEXT:    [[CMP:%.*]] = fcmp ogt double [[TMP5]], [[TMP6]]
 ; CHECK-NEXT:    br i1 [[CMP]], label [[IF_THEN6:%.*]], label [[IF_END7]]
 ; CHECK:       if.then6:
 ; CHECK-NEXT:    br label [[IF_END7]]
 ; CHECK:       if.end7:
 ; CHECK-NEXT:    ret void

llvm/test/Transforms/SLPVectorizer/X86/phi_landingpad.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -slp-vectorizer -mtriple=x86_64-apple-macosx10.9.0 -S -o - | FileCheck %s
 
 target datalayout = "f64:64:64-v64:64:64"
 
 define void @test_phi_in_landingpad() personality i8*
 ; CHECK-LABEL: @test_phi_in_landingpad(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    invoke void @foo()
 ; CHECK-NEXT:    to label [[INNER:%.*]] unwind label [[LPAD:%.*]]
 ; CHECK:       inner:
 ; CHECK-NEXT:    invoke void @foo()
 ; CHECK-NEXT:    to label [[DONE:%.*]] unwind label [[LPAD]]
 ; CHECK:       lpad:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x double> [ poison, [[ENTRY:%.*]] ], [ poison, [[INNER]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x double> [ undef, [[ENTRY:%.*]] ], [ undef, [[INNER]] ]
 ; CHECK-NEXT:    [[TMP1:%.*]] = landingpad { i8*, i32 }
 ; CHECK-NEXT:    catch i8* null
 ; CHECK-NEXT:    br label [[DONE]]
 ; CHECK:       done:
-; CHECK-NEXT:    [[TMP2:%.*]] = phi <2 x double> [ poison, [[INNER]] ], [ [[TMP0]], [[LPAD]] ]
+; CHECK-NEXT:    [[TMP2:%.*]] = phi <2 x double> [ undef, [[INNER]] ], [ [[TMP0]], [[LPAD]] ]
 ; CHECK-NEXT:    ret void
 ;
   bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
 entry:
   invoke void @foo()
   to label %inner unwind label %lpad
 
 inner:

llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll

 ; SSE-NEXT:    ret void
 ;
 ; AVX-LABEL: @pr35497(
 ; AVX-NEXT:  entry:
 ; AVX-NEXT:    [[TMP0:%.*]] = load i64, i64* undef, align 1
 ; AVX-NEXT:    [[ADD:%.*]] = add i64 undef, undef
 ; AVX-NEXT:    store i64 [[ADD]], i64* undef, align 1
 ; AVX-NEXT:    [[ARRAYIDX2_1:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 5
-; AVX-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> poison, i64 [[TMP0]], i32 1
+; AVX-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> <i64 undef, i64 poison>, i64 [[TMP0]], i32 1
 ; AVX-NEXT:    [[TMP2:%.*]] = shl <2 x i64> [[TMP1]], <i64 2, i64 2>
 ; AVX-NEXT:    [[TMP3:%.*]] = and <2 x i64> [[TMP2]], <i64 20, i64 20>
 ; AVX-NEXT:    [[ARRAYIDX2_2:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 4
-; AVX-NEXT:    [[TMP4:%.*]] = add nuw nsw <2 x i64> [[TMP3]], poison
+; AVX-NEXT:    [[TMP4:%.*]] = add nuw nsw <2 x i64> [[TMP3]], zeroinitializer
 ; AVX-NEXT:    [[ARRAYIDX2_5:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 1
 ; AVX-NEXT:    [[TMP5:%.*]] = extractelement <2 x i64> [[TMP4]], i32 1
 ; AVX-NEXT:    [[TMP6:%.*]] = insertelement <2 x i64> poison, i64 [[TMP5]], i32 0
 ; AVX-NEXT:    [[TMP7:%.*]] = insertelement <2 x i64> [[TMP6]], i64 [[ADD]], i32 1
 ; AVX-NEXT:    [[TMP8:%.*]] = shl <2 x i64> [[TMP7]], <i64 2, i64 2>
 ; AVX-NEXT:    [[TMP9:%.*]] = and <2 x i64> [[TMP8]], <i64 20, i64 20>
 ; AVX-NEXT:    [[ARRAYIDX2_6:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 0
 ; AVX-NEXT:    [[TMP10:%.*]] = bitcast i64* [[ARRAYIDX2_6]] to <2 x i64>*

llvm/test/Transforms/SLPVectorizer/X86/reorder_repeated_ops.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 define void @hoge() {
 ; CHECK-LABEL: @hoge(
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    br i1 undef, label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    ret void
 ; CHECK:       bb2:
 ; CHECK-NEXT:    [[T:%.*]] = select i1 undef, i16 undef, i16 15
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i16> poison, i16 [[T]], i32 0
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i16> <i16 poison, i16 undef>, i16 [[T]], i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = sext <2 x i16> [[TMP0]] to <2 x i32>
-; CHECK-NEXT:    [[TMP2:%.*]] = sub nsw <2 x i32> <i32 poison, i32 63>, [[TMP1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = sub <2 x i32> [[TMP2]], poison
+; CHECK-NEXT:    [[TMP2:%.*]] = sub nsw <2 x i32> <i32 undef, i32 63>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sub <2 x i32> [[TMP2]], undef
 ; CHECK-NEXT:    [[SHUFFLE10:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
 ; CHECK-NEXT:    [[TMP4:%.*]] = add <4 x i32> [[SHUFFLE10]], <i32 15, i32 31, i32 47, i32 poison>
 ; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP4]])
 ; CHECK-NEXT:    [[T19:%.*]] = select i1 undef, i32 [[TMP5]], i32 undef
 ; CHECK-NEXT:    [[T20:%.*]] = icmp sgt i32 [[T19]], 63
-; CHECK-NEXT:    [[TMP6:%.*]] = sub nsw <2 x i32> poison, [[TMP1]]
-; CHECK-NEXT:    [[TMP7:%.*]] = sub <2 x i32> [[TMP6]], poison
+; CHECK-NEXT:    [[TMP6:%.*]] = sub nsw <2 x i32> undef, [[TMP1]]
+; CHECK-NEXT:    [[TMP7:%.*]] = sub <2 x i32> [[TMP6]], undef
 ; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP7]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
 ; CHECK-NEXT:    [[TMP8:%.*]] = add nsw <4 x i32> [[SHUFFLE]], <i32 -49, i32 -33, i32 -33, i32 -17>
 ; CHECK-NEXT:    [[TMP9:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP8]])
 ; CHECK-NEXT:    [[OP_EXTRA:%.*]] = icmp slt i32 [[TMP9]], undef
 ; CHECK-NEXT:    [[OP_EXTRA1:%.*]] = select i1 [[OP_EXTRA]], i32 [[TMP9]], i32 undef
 ; CHECK-NEXT:    [[OP_EXTRA2:%.*]] = icmp slt i32 [[OP_EXTRA1]], undef
 ; CHECK-NEXT:    [[OP_EXTRA3:%.*]] = select i1 [[OP_EXTRA2]], i32 [[OP_EXTRA1]], i32 undef
 ; CHECK-NEXT:    [[OP_EXTRA4:%.*]] = icmp slt i32 [[OP_EXTRA3]], undef

llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder.ll

bb:
   ret void
 }
 
 define internal i32 @ipvideo_decode_block_opcode_0xD_16() {
 ; CHECK-LABEL: @ipvideo_decode_block_opcode_0xD_16(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ poison, [[ENTRY:%.*]] ], [ [[SHRINK_SHUFFLE:%.*]], [[IF_END:%.*]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[ENTRY:%.*]] ], [ [[SHRINK_SHUFFLE:%.*]], [[IF_END:%.*]] ]
 ; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[TMP0]], <2 x i16> poison, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    br label [[IF_END]]
 ; CHECK:       if.end:
 ; CHECK-NEXT:    [[ARRAYIDX11_1:%.*]] = getelementptr inbounds i16, i16* undef, i32 1
 ; CHECK-NEXT:    [[ARRAYIDX11_2:%.*]] = getelementptr inbounds i16, i16* undef, i32 2
 ; CHECK-NEXT:    [[ARRAYIDX11_3:%.*]] = getelementptr inbounds i16, i16* undef, i32 3
 ; CHECK-NEXT:    [[ARRAYIDX11_4:%.*]] = getelementptr inbounds i16, i16* undef, i32 4
 ; CHECK-NEXT:    [[ARRAYIDX11_5:%.*]] = getelementptr inbounds i16, i16* undef, i32 5

llvm/test/Transforms/SLPVectorizer/X86/value-bug-inseltpoison.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer < %s -S -mtriple="x86_64-grtev3-linux-gnu" -mcpu=corei7-avx | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 ; We used to crash on this example because we were building a constant
 ; expression during vectorization and the vectorizer expects instructions
 ; as elements of the vectorized tree.
 ; PR19621
 
 define void @test() {
 ; CHECK-LABEL: @test(
 ; CHECK-NEXT:  bb279:
 ; CHECK-NEXT:    br label [[BB283:%.*]]
 ; CHECK:       bb283:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x float> [ poison, [[BB279:%.*]] ], [ [[TMP11:%.*]], [[EXIT:%.*]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x float> [ poison, [[BB279]] ], [ poison, [[EXIT]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x float> [ undef, [[BB279:%.*]] ], [ [[TMP11:%.*]], [[EXIT:%.*]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x float> [ undef, [[BB279]] ], [ undef, [[EXIT]] ]
 ; CHECK-NEXT:    br label [[BB284:%.*]]
 ; CHECK:       bb284:
 ; CHECK-NEXT:    [[TMP2:%.*]] = fpext <2 x float> [[TMP0]] to <2 x double>
-; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
-; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], poison
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], undef
 ; CHECK-NEXT:    br label [[BB21_I:%.*]]
 ; CHECK:       bb21.i:
 ; CHECK-NEXT:    br i1 undef, label [[BB22_I:%.*]], label [[EXIT]]
 ; CHECK:       bb22.i:
-; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> poison, [[TMP4]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> undef, [[TMP4]]
 ; CHECK-NEXT:    br label [[BB32_I:%.*]]
 ; CHECK:       bb32.i:
 ; CHECK-NEXT:    [[TMP6:%.*]] = phi <2 x double> [ [[TMP5]], [[BB22_I]] ], [ zeroinitializer, [[BB32_I]] ]
 ; CHECK-NEXT:    br i1 undef, label [[BB32_I]], label [[BB21_I]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[TMP7:%.*]] = fpext <2 x float> [[TMP1]] to <2 x double>
-; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP7]], <double poison, double 0.000000e+00>
-; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x double> poison, [[TMP8]]
-; CHECK-NEXT:    [[TMP10:%.*]] = fadd <2 x double> [[TMP9]], poison
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP7]], <double undef, double 0.000000e+00>
+; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x double> undef, [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = fadd <2 x double> [[TMP9]], undef
 ; CHECK-NEXT:    [[TMP11]] = fptrunc <2 x double> [[TMP10]] to <2 x float>
 ; CHECK-NEXT:    br label [[BB283]]
 ;
 bb279:
   br label %bb283
 
 bb283:
   %Av.sroa.8.0 = phi float [ undef, %bb279 ], [ %tmp315, %exit ]

llvm/test/Transforms/SLPVectorizer/X86/value-bug.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer < %s -S -mtriple="x86_64-grtev3-linux-gnu" -mcpu=corei7-avx | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 ; We used to crash on this example because we were building a constant
 ; expression during vectorization and the vectorizer expects instructions
 ; as elements of the vectorized tree.
 ; PR19621
 
 define void @test() {
 ; CHECK-LABEL: @test(
 ; CHECK-NEXT:  bb279:
 ; CHECK-NEXT:    br label [[BB283:%.*]]
 ; CHECK:       bb283:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x float> [ poison, [[BB279:%.*]] ], [ [[TMP11:%.*]], [[EXIT:%.*]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x float> [ poison, [[BB279]] ], [ poison, [[EXIT]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x float> [ undef, [[BB279:%.*]] ], [ [[TMP11:%.*]], [[EXIT:%.*]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x float> [ undef, [[BB279]] ], [ undef, [[EXIT]] ]
 ; CHECK-NEXT:    br label [[BB284:%.*]]
 ; CHECK:       bb284:
 ; CHECK-NEXT:    [[TMP2:%.*]] = fpext <2 x float> [[TMP0]] to <2 x double>
-; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
-; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], poison
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], undef
 ; CHECK-NEXT:    br label [[BB21_I:%.*]]
 ; CHECK:       bb21.i:
 ; CHECK-NEXT:    br i1 undef, label [[BB22_I:%.*]], label [[EXIT]]
 ; CHECK:       bb22.i:
-; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> poison, [[TMP4]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> undef, [[TMP4]]
 ; CHECK-NEXT:    br label [[BB32_I:%.*]]
 ; CHECK:       bb32.i:
 ; CHECK-NEXT:    [[TMP6:%.*]] = phi <2 x double> [ [[TMP5]], [[BB22_I]] ], [ zeroinitializer, [[BB32_I]] ]
 ; CHECK-NEXT:    br i1 undef, label [[BB32_I]], label [[BB21_I]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[TMP7:%.*]] = fpext <2 x float> [[TMP1]] to <2 x double>
-; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP7]], <double poison, double 0.000000e+00>
-; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x double> poison, [[TMP8]]
-; CHECK-NEXT:    [[TMP10:%.*]] = fadd <2 x double> [[TMP9]], poison
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP7]], <double undef, double 0.000000e+00>
+; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x double> undef, [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = fadd <2 x double> [[TMP9]], undef
 ; CHECK-NEXT:    [[TMP11]] = fptrunc <2 x double> [[TMP10]] to <2 x float>
 ; CHECK-NEXT:    br label [[BB283]]
 ;
 bb279:
   br label %bb283
 
 bb283:
   %Av.sroa.8.0 = phi float [ undef, %bb279 ], [ %tmp315, %exit ]