[InstCombine] Switch foldOpIntoPhi() to use InstSimplify

foldOpIntoPhi() currently only folds operations into the phi if all
but one operands constant-fold. The two exceptions to this are freeze
and select, where we allow more general simplification.

This patch makes foldOpIntoPhi() generally simplification based and
removes all the instruction-specific logic. We just try to simplify
the instruction for each operand, and for the (potentially) one
non-simplified operand, we move it into the new block with adjusted
operands.

This fixes llvm/llvm-project#57448, which
was my original motivation for the change.

Author: nikic

llvm/lib/Transforms/InstCombine/InstructionCombining.cpp

@@ -1155,22 +1155,6 @@ Instruction *InstCombinerImpl::FoldOpIntoSelect(Instruction &Op, SelectInst *SI,
   return SelectInst::Create(SI->getCondition(), NewTV, NewFV, "", nullptr, SI);
 }
 
-static Value *foldOperationIntoPhiValue(BinaryOperator *I, Value *InV,
-                                        InstCombiner::BuilderTy &Builder) {
-  bool ConstIsRHS = isa<Constant>(I->getOperand(1));
-  Constant *C = cast<Constant>(I->getOperand(ConstIsRHS));
-
-  Value *Op0 = InV, *Op1 = C;
-  if (!ConstIsRHS)
-    std::swap(Op0, Op1);
-
-  Value *RI = Builder.CreateBinOp(I->getOpcode(), Op0, Op1, "phi.bo");
-  auto *FPInst = dyn_cast<Instruction>(RI);
-  if (FPInst && isa<FPMathOperator>(FPInst))
-    FPInst->copyFastMathFlags(I);
-  return RI;
-}
-
 Instruction *InstCombinerImpl::foldOpIntoPhi(Instruction &I, PHINode *PN) {
   unsigned NumPHIValues = PN->getNumIncomingValues();
   if (NumPHIValues == 0)
@@ -1189,48 +1173,66 @@ Instruction *InstCombinerImpl::foldOpIntoPhi(Instruction &I, PHINode *PN) {
     // Otherwise, we can replace *all* users with the new PHI we form.
   }
 
-  // Check to see if all of the operands of the PHI are simple constants
-  // (constantint/constantfp/undef).  If there is one non-constant value,
-  // remember the BB it is in.  If there is more than one or if *it* is a PHI,
-  // bail out.  We don't do arbitrary constant expressions here because moving
-  // their computation can be expensive without a cost model.
-  BasicBlock *NonConstBB = nullptr;
+  // Check to see whether the instruction can be folded into each phi operand.
+  // If there is one operand that does not fold, remember the BB it is in.
+  // If there is more than one or if *it* is a PHI, bail out.
+  SmallVector<Value *> NewPhiValues;
+  BasicBlock *NonSimplifiedBB = nullptr;
+  Value *NonSimplifiedInVal = nullptr;
   for (unsigned i = 0; i != NumPHIValues; ++i) {
     Value *InVal = PN->getIncomingValue(i);
-    // For non-freeze, require constant operand
-    // For freeze, require non-undef, non-poison operand
-    if (!isa<FreezeInst>(I) && match(InVal, m_ImmConstant()))
-      continue;
-    if (isa<FreezeInst>(I) && isGuaranteedNotToBeUndefOrPoison(InVal))
+    BasicBlock *InBB = PN->getIncomingBlock(i);
+
+    // NB: It is a precondition of this transform that the operands be
+    // phi translatable! This is usually trivially satisfied by limiting it
+    // to constant ops, and for selects we do a more sophisticated check.
+    SmallVector<Value *> Ops;
+    for (Value *Op : I.operands()) {
+      if (Op == PN)
+        Ops.push_back(InVal);
+      else
+        Ops.push_back(Op->DoPHITranslation(PN->getParent(), InBB));
+    }
+
+    // Don't consider the simplification successful if we get back a constant
+    // expression. That's just an instruction in hiding.
+    Value *NewVal = simplifyInstructionWithOperands(&I, Ops, SQ);
+    if (NewVal && !match(NewVal, m_ConstantExpr())) {
+      NewPhiValues.push_back(NewVal);
       continue;
+    }
 
     if (isa<PHINode>(InVal)) return nullptr;  // Itself a phi.
-    if (NonConstBB) return nullptr;  // More than one non-const value.
+    if (NonSimplifiedBB) return nullptr;  // More than one non-simplified value.
 
-    NonConstBB = PN->getIncomingBlock(i);
+    NonSimplifiedBB = InBB;
+    NonSimplifiedInVal = InVal;
+    NewPhiValues.push_back(nullptr);
 
     // If the InVal is an invoke at the end of the pred block, then we can't
     // insert a computation after it without breaking the edge.
     if (isa<InvokeInst>(InVal))
-      if (cast<Instruction>(InVal)->getParent() == NonConstBB)
+      if (cast<Instruction>(InVal)->getParent() == NonSimplifiedBB)
         return nullptr;
 
     // If the incoming non-constant value is reachable from the phis block,
     // we'll push the operation across a loop backedge. This could result in
     // an infinite combine loop, and is generally non-profitable (especially
     // if the operation was originally outside the loop).
-    if (isPotentiallyReachable(PN->getParent(), NonConstBB, nullptr, &DT, LI))
+    if (isPotentiallyReachable(PN->getParent(), NonSimplifiedBB, nullptr, &DT,
+                               LI))
       return nullptr;
   }
 
-  // If there is exactly one non-constant value, we can insert a copy of the
+  // If there is exactly one non-simplified value, we can insert a copy of the
   // operation in that block.  However, if this is a critical edge, we would be
   // inserting the computation on some other paths (e.g. inside a loop).  Only
   // do this if the pred block is unconditionally branching into the phi block.
   // Also, make sure that the pred block is not dead code.
-  if (NonConstBB != nullptr) {
-    BranchInst *BI = dyn_cast<BranchInst>(NonConstBB->getTerminator());
-    if (!BI || !BI->isUnconditional() || !DT.isReachableFromEntry(NonConstBB))
+  if (NonSimplifiedBB != nullptr) {
+    BranchInst *BI = dyn_cast<BranchInst>(NonSimplifiedBB->getTerminator());
+    if (!BI || !BI->isUnconditional() ||
+        !DT.isReachableFromEntry(NonSimplifiedBB))
       return nullptr;
   }
 
@@ -1241,88 +1243,23 @@ Instruction *InstCombinerImpl::foldOpIntoPhi(Instruction &I, PHINode *PN) {
 
   // If we are going to have to insert a new computation, do so right before the
   // predecessor's terminator.
-  if (NonConstBB)
-    Builder.SetInsertPoint(NonConstBB->getTerminator());
-
-  // Next, add all of the operands to the PHI.
-  if (SelectInst *SI = dyn_cast<SelectInst>(&I)) {
-    // We only currently try to fold the condition of a select when it is a phi,
-    // not the true/false values.
-    Value *TrueV = SI->getTrueValue();
-    Value *FalseV = SI->getFalseValue();
-    BasicBlock *PhiTransBB = PN->getParent();
-    for (unsigned i = 0; i != NumPHIValues; ++i) {
-      BasicBlock *ThisBB = PN->getIncomingBlock(i);
-      Value *TrueVInPred = TrueV->DoPHITranslation(PhiTransBB, ThisBB);
-      Value *FalseVInPred = FalseV->DoPHITranslation(PhiTransBB, ThisBB);
-      Value *InV = nullptr;
-      // Beware of ConstantExpr:  it may eventually evaluate to getNullValue,
-      // even if currently isNullValue gives false.
-      Constant *InC = dyn_cast<Constant>(PN->getIncomingValue(i));
-      // For vector constants, we cannot use isNullValue to fold into
-      // FalseVInPred versus TrueVInPred. When we have individual nonzero
-      // elements in the vector, we will incorrectly fold InC to
-      // `TrueVInPred`.
-      if (InC && isa<ConstantInt>(InC))
-        InV = InC->isNullValue() ? FalseVInPred : TrueVInPred;
-      else {
-        // Generate the select in the same block as PN's current incoming block.
-        // Note: ThisBB need not be the NonConstBB because vector constants
-        // which are constants by definition are handled here.
-        // FIXME: This can lead to an increase in IR generation because we might
-        // generate selects for vector constant phi operand, that could not be
-        // folded to TrueVInPred or FalseVInPred as done for ConstantInt. For
-        // non-vector phis, this transformation was always profitable because
-        // the select would be generated exactly once in the NonConstBB.
-        Builder.SetInsertPoint(ThisBB->getTerminator());
-        InV = Builder.CreateSelect(PN->getIncomingValue(i), TrueVInPred,
-                                   FalseVInPred, "phi.sel");
-      }
-      NewPN->addIncoming(InV, ThisBB);
-    }
-  } else if (CmpInst *CI = dyn_cast<CmpInst>(&I)) {
-    Constant *C = cast<Constant>(I.getOperand(1));
-    for (unsigned i = 0; i != NumPHIValues; ++i) {
-      Value *InV = nullptr;
-      if (auto *InC = dyn_cast<Constant>(PN->getIncomingValue(i)))
-        InV = ConstantExpr::getCompare(CI->getPredicate(), InC, C);
-      else
-        InV = Builder.CreateCmp(CI->getPredicate(), PN->getIncomingValue(i),
-                                C, "phi.cmp");
-      NewPN->addIncoming(InV, PN->getIncomingBlock(i));
-    }
-  } else if (auto *BO = dyn_cast<BinaryOperator>(&I)) {
-    for (unsigned i = 0; i != NumPHIValues; ++i) {
-      Value *InV = foldOperationIntoPhiValue(BO, PN->getIncomingValue(i),
-                                             Builder);
-      NewPN->addIncoming(InV, PN->getIncomingBlock(i));
-    }
-  } else if (isa<FreezeInst>(&I)) {
-    for (unsigned i = 0; i != NumPHIValues; ++i) {
-      Value *InV;
-      if (NonConstBB == PN->getIncomingBlock(i))
-        InV = Builder.CreateFreeze(PN->getIncomingValue(i), "phi.fr");
+  Instruction *Clone = nullptr;
+  if (NonSimplifiedBB) {
+    Clone = I.clone();
+    for (Use &U : Clone->operands()) {
+      if (U == PN)
+        U = NonSimplifiedInVal;
       else
-        InV = PN->getIncomingValue(i);
-      NewPN->addIncoming(InV, PN->getIncomingBlock(i));
-    }
-  } else if (auto *EV = dyn_cast<ExtractValueInst>(&I)) {
-    for (unsigned i = 0; i != NumPHIValues; ++i)
-      NewPN->addIncoming(Builder.CreateExtractValue(PN->getIncomingValue(i),
-                                                    EV->getIndices(), "phi.ev"),
-                         PN->getIncomingBlock(i));
-  } else {
-    CastInst *CI = cast<CastInst>(&I);
-    Type *RetTy = CI->getType();
-    for (unsigned i = 0; i != NumPHIValues; ++i) {
-      Value *InV;
-      if (Constant *InC = dyn_cast<Constant>(PN->getIncomingValue(i)))
-        InV = ConstantExpr::getCast(CI->getOpcode(), InC, RetTy);
-      else
-        InV = Builder.CreateCast(CI->getOpcode(), PN->getIncomingValue(i),
-                                 I.getType(), "phi.cast");
-      NewPN->addIncoming(InV, PN->getIncomingBlock(i));
+        U = U->DoPHITranslation(PN->getParent(), NonSimplifiedBB);
     }
+    InsertNewInstBefore(Clone, *NonSimplifiedBB->getTerminator());
+  }
+
+  for (unsigned i = 0; i != NumPHIValues; ++i) {
+    if (NewPhiValues[i])
+      NewPN->addIncoming(NewPhiValues[i], PN->getIncomingBlock(i));
+    else
+      NewPN->addIncoming(Clone, PN->getIncomingBlock(i));
   }
 
   for (User *U : make_early_inc_range(PN->users())) {

llvm/test/Transforms/InstCombine/intptr1.ll

@@ -57,19 +57,18 @@ define void @test1_neg(ptr %a, ptr readnone %a_end, ptr %b.i64) {
 ; CHECK-NEXT:    br i1 [[CMP1]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
 ; CHECK:       for.body.preheader:
 ; CHECK-NEXT:    [[B:%.*]] = load i64, ptr [[B_I64:%.*]], align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[B]] to ptr
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[A_ADDR_03:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[BB:%.*]] ], [ [[A]], [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[B_ADDR_02:%.*]] = phi i64 [ [[ADD_INT:%.*]], [[BB]] ], [ [[B]], [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[TMP:%.*]] = inttoptr i64 [[B_ADDR_02]] to ptr
-; CHECK-NEXT:    [[PTRCMP:%.*]] = icmp ult ptr [[TMP]], [[A_END]]
+; CHECK-NEXT:    [[B_ADDR_02:%.*]] = phi ptr [ [[ADD:%.*]], [[BB]] ], [ [[TMP0]], [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[PTRCMP:%.*]] = icmp ult ptr [[B_ADDR_02]], [[A_END]]
 ; CHECK-NEXT:    br i1 [[PTRCMP]], label [[FOR_END]], label [[BB]]
 ; CHECK:       bb:
 ; CHECK-NEXT:    [[I1:%.*]] = load float, ptr [[A]], align 4
 ; CHECK-NEXT:    [[MUL_I:%.*]] = fmul float [[I1]], 4.200000e+01
 ; CHECK-NEXT:    store float [[MUL_I]], ptr [[A_ADDR_03]], align 4
-; CHECK-NEXT:    [[ADD:%.*]] = getelementptr inbounds float, ptr [[A]], i64 1
-; CHECK-NEXT:    [[ADD_INT]] = ptrtoint ptr [[ADD]] to i64
+; CHECK-NEXT:    [[ADD]] = getelementptr inbounds float, ptr [[A]], i64 1
 ; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds float, ptr [[A_ADDR_03]], i64 1
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult ptr [[INCDEC_PTR]], [[A_END]]
 ; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END]]

llvm/test/Transforms/InstCombine/intptr4.ll

@@ -8,18 +8,17 @@ define  void @test(ptr %a, ptr readnone %a_end, i64 %b, ptr %bf) unnamed_addr  {
 ; CHECK-NEXT:    [[B_FLOAT:%.*]] = inttoptr i64 [[B:%.*]] to ptr
 ; CHECK-NEXT:    br i1 [[CMP1]], label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[B]] to ptr
 ; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER:%.*]]
 ; CHECK:       bb2:
-; CHECK-NEXT:    [[BFI:%.*]] = ptrtoint ptr [[BF:%.*]] to i64
 ; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER]]
 ; CHECK:       for.body.preheader:
-; CHECK-NEXT:    [[B_PHI:%.*]] = phi i64 [ [[B]], [[BB1]] ], [ [[BFI]], [[BB2]] ]
-; CHECK-NEXT:    [[B_PHI_PTR:%.*]] = inttoptr i64 [[B_PHI]] to ptr
+; CHECK-NEXT:    [[B_PHI:%.*]] = phi ptr [ [[TMP0]], [[BB1]] ], [ [[BF:%.*]], [[BB2]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[A_ADDR_03:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[A]], [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[B_ADDR_FLOAT:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC:%.*]], [[FOR_BODY]] ], [ [[B_FLOAT]], [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[B_ADDR_I64_PTR:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC]], [[FOR_BODY]] ], [ [[B_PHI_PTR]], [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[B_ADDR_I64_PTR:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC]], [[FOR_BODY]] ], [ [[B_PHI]], [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[L:%.*]] = load float, ptr [[B_ADDR_FLOAT]], align 4
 ; CHECK-NEXT:    [[MUL_I:%.*]] = fmul float [[L]], 4.200000e+01
 ; CHECK-NEXT:    store float [[MUL_I]], ptr [[A_ADDR_03]], align 4

llvm/test/Transforms/InstCombine/intptr5.ll

@@ -8,20 +8,19 @@ define  void @test(ptr %a, ptr readnone %a_end, i64 %b, ptr %bf) unnamed_addr  {
 ; CHECK-NEXT:    [[B_FLOAT:%.*]] = inttoptr i64 [[B:%.*]] to ptr
 ; CHECK-NEXT:    br i1 [[CMP1]], label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[B]] to ptr
 ; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER:%.*]]
 ; CHECK:       bb2:
-; CHECK-NEXT:    [[BFI:%.*]] = ptrtoint ptr [[BF:%.*]] to i64
 ; CHECK-NEXT:    br label [[FOR_BODY_PREHEADER]]
 ; CHECK:       for.body.preheader:
-; CHECK-NEXT:    [[B_PHI:%.*]] = phi i64 [ [[B]], [[BB1]] ], [ [[BFI]], [[BB2]] ]
-; CHECK-NEXT:    [[B_PHI_PTR:%.*]] = inttoptr i64 [[B_PHI]] to ptr
+; CHECK-NEXT:    [[B_PHI:%.*]] = phi ptr [ [[TMP0]], [[BB1]] ], [ [[BF:%.*]], [[BB2]] ]
 ; CHECK-NEXT:    switch i64 [[B]], label [[FOR_BODY:%.*]] [
 ; CHECK-NEXT:    i64 1, label [[FOR_BODY]]
 ; CHECK-NEXT:    ]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[A_ADDR_03:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[A]], [[FOR_BODY_PREHEADER]] ], [ [[A]], [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[B_ADDR_FLOAT:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC:%.*]], [[FOR_BODY]] ], [ [[B_FLOAT]], [[FOR_BODY_PREHEADER]] ], [ [[B_FLOAT]], [[FOR_BODY_PREHEADER]] ]
-; CHECK-NEXT:    [[B_ADDR_I64_PTR:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC]], [[FOR_BODY]] ], [ [[B_PHI_PTR]], [[FOR_BODY_PREHEADER]] ], [ [[B_PHI_PTR]], [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[B_ADDR_I64_PTR:%.*]] = phi ptr [ [[B_ADDR_FLOAT_INC]], [[FOR_BODY]] ], [ [[B_PHI]], [[FOR_BODY_PREHEADER]] ], [ [[B_PHI]], [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    [[L:%.*]] = load float, ptr [[B_ADDR_FLOAT]], align 4
 ; CHECK-NEXT:    [[MUL_I:%.*]] = fmul float [[L]], 4.200000e+01
 ; CHECK-NEXT:    store float [[MUL_I]], ptr [[A_ADDR_03]], align 4

llvm/test/Transforms/InstCombine/intptr7.ll

@@ -51,17 +51,16 @@ define void @no_matching_phi(i64 %a, ptr %b, i1 %cond) {
 ; CHECK-NEXT:    [[ADDB:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 2
 ; CHECK-NEXT:    br i1 [[COND:%.*]], label [[B:%.*]], label [[A:%.*]]
 ; CHECK:       A:
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[ADD_INT]] to ptr
 ; CHECK-NEXT:    br label [[C:%.*]]
 ; CHECK:       B:
-; CHECK-NEXT:    [[ADDB_INT:%.*]] = ptrtoint ptr [[ADDB]] to i64
 ; CHECK-NEXT:    [[ADD:%.*]] = inttoptr i64 [[ADD_INT]] to ptr
 ; CHECK-NEXT:    store float 1.000000e+01, ptr [[ADD]], align 4
 ; CHECK-NEXT:    br label [[C]]
 ; CHECK:       C:
 ; CHECK-NEXT:    [[A_ADDR_03:%.*]] = phi ptr [ [[ADDB]], [[A]] ], [ [[ADD]], [[B]] ]
-; CHECK-NEXT:    [[B_ADDR_02:%.*]] = phi i64 [ [[ADD_INT]], [[A]] ], [ [[ADDB_INT]], [[B]] ]
-; CHECK-NEXT:    [[I0:%.*]] = inttoptr i64 [[B_ADDR_02]] to ptr
-; CHECK-NEXT:    [[I1:%.*]] = load float, ptr [[I0]], align 4
+; CHECK-NEXT:    [[B_ADDR_02:%.*]] = phi ptr [ [[TMP0]], [[A]] ], [ [[ADDB]], [[B]] ]
+; CHECK-NEXT:    [[I1:%.*]] = load float, ptr [[B_ADDR_02]], align 4
 ; CHECK-NEXT:    [[MUL_I:%.*]] = fmul float [[I1]], 4.200000e+01
 ; CHECK-NEXT:    store float [[MUL_I]], ptr [[A_ADDR_03]], align 4
 ; CHECK-NEXT:    ret void

llvm/test/Transforms/InstCombine/phi-select-constant.ll

@@ -77,17 +77,15 @@ final:
 define <2 x i8> @vec3(i1 %cond1, i1 %cond2, <2 x i1> %x, <2 x i8> %y, <2 x i8> %z) {
 ; CHECK-LABEL: @vec3(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[PHI_SEL1:%.*]] = shufflevector <2 x i8> [[Z:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
 ; CHECK-NEXT:    br i1 [[COND1:%.*]], label [[IF1:%.*]], label [[ELSE:%.*]]
 ; CHECK:       if1:
-; CHECK-NEXT:    [[PHI_SEL2:%.*]] = shufflevector <2 x i8> [[Y]], <2 x i8> [[Z]], <2 x i32> <i32 0, i32 3>
 ; CHECK-NEXT:    br i1 [[COND2:%.*]], label [[IF2:%.*]], label [[ELSE]]
 ; CHECK:       if2:
-; CHECK-NEXT:    [[PHI_SEL:%.*]] = select <2 x i1> [[X:%.*]], <2 x i8> [[Y]], <2 x i8> [[Z]]
 ; CHECK-NEXT:    br label [[ELSE]]
 ; CHECK:       else:
-; CHECK-NEXT:    [[PHI:%.*]] = phi <2 x i8> [ [[PHI_SEL]], [[IF2]] ], [ [[PHI_SEL1]], [[ENTRY:%.*]] ], [ [[PHI_SEL2]], [[IF1]] ]
-; CHECK-NEXT:    ret <2 x i8> [[PHI]]
+; CHECK-NEXT:    [[PHI:%.*]] = phi <2 x i1> [ [[X:%.*]], [[IF2]] ], [ <i1 false, i1 true>, [[ENTRY:%.*]] ], [ <i1 true, i1 false>, [[IF1]] ]
+; CHECK-NEXT:    [[SEL:%.*]] = select <2 x i1> [[PHI]], <2 x i8> [[Y:%.*]], <2 x i8> [[Z:%.*]]
+; CHECK-NEXT:    ret <2 x i8> [[SEL]]
 ;
 entry:
   br i1 %cond1, label %if1, label %else

llvm/test/Transforms/InstCombine/phi.ll

@@ -697,10 +697,10 @@ ret:
 define i32 @test23(i32 %A, i1 %pb, ptr %P) {
 ; CHECK-LABEL: @test23(
 ; CHECK-NEXT:  BB0:
-; CHECK-NEXT:    [[PHI_BO:%.*]] = add i32 [[A:%.*]], 19
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[A:%.*]], 19
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       Loop:
-; CHECK-NEXT:    [[B:%.*]] = phi i32 [ [[PHI_BO]], [[BB0:%.*]] ], [ 61, [[LOOP]] ]
+; CHECK-NEXT:    [[B:%.*]] = phi i32 [ [[TMP0]], [[BB0:%.*]] ], [ 61, [[LOOP]] ]
 ; CHECK-NEXT:    store i32 [[B]], ptr [[P:%.*]], align 4
 ; CHECK-NEXT:    br i1 [[PB:%.*]], label [[LOOP]], label [[EXIT:%.*]]
 ; CHECK:       Exit:
@@ -1280,14 +1280,12 @@ define i1 @pr57488_icmp_of_phi(ptr %ptr.base, i64 %len) {
 ; CHECK-NEXT:    [[LEN_ZERO:%.*]] = icmp eq i64 [[LEN]], 0
 ; CHECK-NEXT:    br i1 [[LEN_ZERO]], label [[EXIT:%.*]], label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[ACCUM:%.*]] = phi i8 [ [[ACCUM_NEXT:%.*]], [[LOOP]] ], [ 1, [[START:%.*]] ]
+; CHECK-NEXT:    [[ACCUM:%.*]] = phi i1 [ [[AND:%.*]], [[LOOP]] ], [ true, [[START:%.*]] ]
 ; CHECK-NEXT:    [[PTR:%.*]] = phi ptr [ [[PTR_NEXT:%.*]], [[LOOP]] ], [ [[PTR_BASE]], [[START]] ]
 ; CHECK-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i64, ptr [[PTR]], i64 1
-; CHECK-NEXT:    [[ACCUM_BOOL:%.*]] = icmp ne i8 [[ACCUM]], 0
 ; CHECK-NEXT:    [[VAL:%.*]] = load i64, ptr [[PTR]], align 8
 ; CHECK-NEXT:    [[VAL_ZERO:%.*]] = icmp eq i64 [[VAL]], 0
-; CHECK-NEXT:    [[AND:%.*]] = and i1 [[ACCUM_BOOL]], [[VAL_ZERO]]
-; CHECK-NEXT:    [[ACCUM_NEXT]] = zext i1 [[AND]] to i8
+; CHECK-NEXT:    [[AND]] = and i1 [[ACCUM]], [[VAL_ZERO]]
 ; CHECK-NEXT:    [[EXIT_COND:%.*]] = icmp eq ptr [[PTR_NEXT]], [[END]]
 ; CHECK-NEXT:    br i1 [[EXIT_COND]], label [[EXIT]], label [[LOOP]]
 ; CHECK:       exit:

llvm/test/Transforms/InstCombine/recurrence.ll

@@ -4,9 +4,9 @@
 define i64 @test_or(i64 %a) {
 ; CHECK-LABEL: @test_or(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = or i64 [[A:%.*]], 15
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[TMP0:%.*]] = or i64 [[A:%.*]], 15
 ; CHECK-NEXT:    tail call void @use(i64 [[TMP0]])
 ; CHECK-NEXT:    br label [[LOOP]]
 ;
@@ -84,9 +84,9 @@ loop:                                             ; preds = %loop, %entry
 define i64 @test_and(i64 %a) {
 ; CHECK-LABEL: @test_and(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = and i64 [[A:%.*]], 15
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[TMP0:%.*]] = and i64 [[A:%.*]], 15
 ; CHECK-NEXT:    tail call void @use(i64 [[TMP0]])
 ; CHECK-NEXT:    br label [[LOOP]]
 ;