OpaquePtr: add Type parameter to Loads analysis API.

This makes the functions in Loads.h require a type to be specified
independently of the pointer Value so that when pointers have no structure
other than address-space, it can still do its job.

Most callers had an obvious memory operation handy to provide this type, but a
SROA and ArgumentPromotion were doing more complicated analysis. They get
updated to merge the properties of the various instructions they were
considering.

llvm-svn: 365468

7 files changed, 63 insertions, 21 deletions

diff --git a/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp b/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
index 8b77adc78f3..95a9f31cced 100644
--- a/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
+++ b/llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
@@ -479,9 +479,9 @@ doPromotion(Function *F, SmallPtrSetImpl<Argument *> &ArgsToPromote,
   return NF;
 }
 
-/// AllCallersPassInValidPointerForArgument - Return true if we can prove that
-/// all callees pass in a valid pointer for the specified function argument.
-static bool allCallersPassInValidPointerForArgument(Argument *Arg) {
+/// Return true if we can prove that all callees pass in a valid pointer for the
+/// specified function argument.
+static bool allCallersPassValidPointerForArgument(Argument *Arg, Type *Ty) {
   Function *Callee = Arg->getParent();
   const DataLayout &DL = Callee->getParent()->getDataLayout();
 
@@ -493,7 +493,7 @@ static bool allCallersPassInValidPointerForArgument(Argument *Arg) {
     CallSite CS(U);
     assert(CS && "Should only have direct calls!");
 
-    if (!isDereferenceablePointer(CS.getArgument(ArgNo), DL))
+    if (!isDereferenceablePointer(CS.getArgument(ArgNo), Ty, DL))
       return false;
   }
   return true;
@@ -566,7 +566,7 @@ static void markIndicesSafe(const IndicesVector &ToMark,
 /// This method limits promotion of aggregates to only promote up to three
 /// elements of the aggregate in order to avoid exploding the number of
 /// arguments passed in.
-static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
+static bool isSafeToPromoteArgument(Argument *Arg, Type *ByValTy, AAResults &AAR,
                                     unsigned MaxElements) {
   using GEPIndicesSet = std::set<IndicesVector>;
 
@@ -596,9 +596,28 @@ static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
   GEPIndicesSet ToPromote;
 
   // If the pointer is always valid, any load with first index 0 is valid.
-  if (isByVal || allCallersPassInValidPointerForArgument(Arg))
+
+  if (ByValTy)
     SafeToUnconditionallyLoad.insert(IndicesVector(1, 0));
 
+  // Whenever a new underlying type for the operand is found, make sure it's
+  // consistent with the GEPs and loads we've already seen and, if necessary,
+  // use it to see if all incoming pointers are valid (which implies the 0-index
+  // is safe).
+  Type *BaseTy = ByValTy;
+  auto UpdateBaseTy = [&](Type *NewBaseTy) {
+    if (BaseTy)
+      return BaseTy == NewBaseTy;
+
+    BaseTy = NewBaseTy;
+    if (allCallersPassValidPointerForArgument(Arg, BaseTy)) {
+      assert(SafeToUnconditionallyLoad.empty());
+      SafeToUnconditionallyLoad.insert(IndicesVector(1, 0));
+    }
+
+    return true;
+  };
+
   // First, iterate the entry block and mark loads of (geps of) arguments as
   // safe.
   BasicBlock &EntryBlock = Arg->getParent()->front();
@@ -621,6 +640,9 @@ static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
               // right away, can't promote this argument at all.
               return false;
 
+          if (!UpdateBaseTy(GEP->getSourceElementType()))
+            return false;
+
           // Indices checked out, mark them as safe
           markIndicesSafe(Indices, SafeToUnconditionallyLoad);
           Indices.clear();
@@ -628,6 +650,11 @@ static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
       } else if (V == Arg) {
         // Direct loads are equivalent to a GEP with a single 0 index.
         markIndicesSafe(IndicesVector(1, 0), SafeToUnconditionallyLoad);
+
+        if (BaseTy && LI->getType() != BaseTy)
+          return false;
+
+        BaseTy = LI->getType();
       }
     }
 
@@ -645,6 +672,9 @@ static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
       Loads.push_back(LI);
       // Direct loads are equivalent to a GEP with a zero index and then a load.
       Operands.push_back(0);
+
+      if (!UpdateBaseTy(LI->getType()))
+        return false;
     } else if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(UR)) {
       if (GEP->use_empty()) {
         // Dead GEP's cause trouble later.  Just remove them if we run into
@@ -653,9 +683,12 @@ static bool isSafeToPromoteArgument(Argument *Arg, bool isByVal, AAResults &AAR,
         // TODO: This runs the above loop over and over again for dead GEPs
         // Couldn't we just do increment the UI iterator earlier and erase the
         // use?
-        return isSafeToPromoteArgument(Arg, isByVal, AAR, MaxElements);
+        return isSafeToPromoteArgument(Arg, ByValTy, AAR, MaxElements);
       }
 
+      if (!UpdateBaseTy(GEP->getSourceElementType()))
+        return false;
+
       // Ensure that all of the indices are constants.
       for (User::op_iterator i = GEP->idx_begin(), e = GEP->idx_end(); i != e;
            ++i)
@@ -966,8 +999,9 @@ promoteArguments(Function *F, function_ref<AAResults &(Function &F)> AARGetter,
     }
 
     // Otherwise, see if we can promote the pointer to its value.
-    if (isSafeToPromoteArgument(PtrArg, PtrArg->hasByValAttr(), AAR,
-                                MaxElements))
+    Type *ByValTy =
+        PtrArg->hasByValAttr() ? PtrArg->getParamByValType() : nullptr;
+    if (isSafeToPromoteArgument(PtrArg, ByValTy, AAR, MaxElements))
       ArgsToPromote.insert(PtrArg);
   }
 
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 63f313e1f7f..4b3333affa7 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1060,7 +1060,7 @@ Value *InstCombiner::simplifyMaskedLoad(IntrinsicInst &II) {
 
   // If we can unconditionally load from this address, replace with a
   // load/select idiom. TODO: use DT for context sensitive query
-  if (isDereferenceableAndAlignedPointer(LoadPtr, Alignment,
+  if (isDereferenceableAndAlignedPointer(LoadPtr, II.getType(), Alignment,
                                          II.getModule()->getDataLayout(),
                                          &II, nullptr)) {
     Value *LI = Builder.CreateAlignedLoad(II.getType(), LoadPtr, Alignment,
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
index 0df80e07e84..054fb7da09a 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -1064,8 +1064,10 @@ Instruction *InstCombiner::visitLoadInst(LoadInst &LI) {
     if (SelectInst *SI = dyn_cast<SelectInst>(Op)) {
       // load (select (Cond, &V1, &V2))  --> select(Cond, load &V1, load &V2).
       unsigned Align = LI.getAlignment();
-      if (isSafeToLoadUnconditionally(SI->getOperand(1), Align, DL, SI) &&
-          isSafeToLoadUnconditionally(SI->getOperand(2), Align, DL, SI)) {
+      if (isSafeToLoadUnconditionally(SI->getOperand(1), LI.getType(), Align,
+                                      DL, SI) &&
+          isSafeToLoadUnconditionally(SI->getOperand(2), LI.getType(), Align,
+                                      DL, SI)) {
         LoadInst *V1 =
             Builder.CreateLoad(LI.getType(), SI->getOperand(1),
                                SI->getOperand(1)->getName() + ".val");
diff --git a/llvm/lib/Transforms/Scalar/LICM.cpp b/llvm/lib/Transforms/Scalar/LICM.cpp
index 2d27a660102..3c5e773f793 100644
--- a/llvm/lib/Transforms/Scalar/LICM.cpp
+++ b/llvm/lib/Transforms/Scalar/LICM.cpp
@@ -2016,8 +2016,8 @@ bool llvm::promoteLoopAccessesToScalars(
         // deref info through it.
         if (!DereferenceableInPH) {
           DereferenceableInPH = isDereferenceableAndAlignedPointer(
-              Store->getPointerOperand(), Store->getAlignment(), MDL,
-              Preheader->getTerminator(), DT);
+              Store->getPointerOperand(), Store->getValueOperand()->getType(),
+              Store->getAlignment(), MDL, Preheader->getTerminator(), DT);
         }
       } else
         return false; // Not a load or store.
diff --git a/llvm/lib/Transforms/Scalar/MergeICmps.cpp b/llvm/lib/Transforms/Scalar/MergeICmps.cpp
index 630f029850c..3d047a19326 100644
--- a/llvm/lib/Transforms/Scalar/MergeICmps.cpp
+++ b/llvm/lib/Transforms/Scalar/MergeICmps.cpp
@@ -162,7 +162,7 @@ BCEAtom visitICmpLoadOperand(Value *const Val, BaseIdentifier &BaseId) {
     return {};
   }
   const auto &DL = GEP->getModule()->getDataLayout();
-  if (!isDereferenceablePointer(GEP, DL)) {
+  if (!isDereferenceablePointer(GEP, LoadI->getType(), DL)) {
     LLVM_DEBUG(dbgs() << "not dereferenceable\n");
     // We need to make sure that we can do comparison in any order, so we
     // require memory to be unconditionnally dereferencable.
diff --git a/llvm/lib/Transforms/Scalar/SROA.cpp b/llvm/lib/Transforms/Scalar/SROA.cpp
index cc79afdb05a..33f90d0b01e 100644
--- a/llvm/lib/Transforms/Scalar/SROA.cpp
+++ b/llvm/lib/Transforms/Scalar/SROA.cpp
@@ -1190,12 +1190,16 @@ static Type *findCommonType(AllocaSlices::const_iterator B,
 /// FIXME: This should be hoisted into a generic utility, likely in
 /// Transforms/Util/Local.h
 static bool isSafePHIToSpeculate(PHINode &PN) {
+  const DataLayout &DL = PN.getModule()->getDataLayout();
+
   // For now, we can only do this promotion if the load is in the same block
   // as the PHI, and if there are no stores between the phi and load.
   // TODO: Allow recursive phi users.
   // TODO: Allow stores.
   BasicBlock *BB = PN.getParent();
   unsigned MaxAlign = 0;
+  uint64_t APWidth = DL.getIndexTypeSizeInBits(PN.getType());
+  APInt MaxSize(APWidth, 0);
   bool HaveLoad = false;
   for (User *U : PN.users()) {
     LoadInst *LI = dyn_cast<LoadInst>(U);
@@ -1214,15 +1218,15 @@ static bool isSafePHIToSpeculate(PHINode &PN) {
       if (BBI->mayWriteToMemory())
         return false;
 
+    uint64_t Size = DL.getTypeStoreSizeInBits(LI->getType());
     MaxAlign = std::max(MaxAlign, LI->getAlignment());
+    MaxSize = MaxSize.ult(Size) ? APInt(APWidth, Size) : MaxSize;
     HaveLoad = true;
   }
 
   if (!HaveLoad)
     return false;
 
-  const DataLayout &DL = PN.getModule()->getDataLayout();
-
   // We can only transform this if it is safe to push the loads into the
   // predecessor blocks. The only thing to watch out for is that we can't put
   // a possibly trapping load in the predecessor if it is a critical edge.
@@ -1244,7 +1248,7 @@ static bool isSafePHIToSpeculate(PHINode &PN) {
     // If this pointer is always safe to load, or if we can prove that there
     // is already a load in the block, then we can move the load to the pred
     // block.
-    if (isSafeToLoadUnconditionally(InVal, MaxAlign, DL, TI))
+    if (isSafeToLoadUnconditionally(InVal, MaxAlign, MaxSize, DL, TI))
       continue;
 
     return false;
@@ -1334,9 +1338,11 @@ static bool isSafeSelectToSpeculate(SelectInst &SI) {
     // Both operands to the select need to be dereferenceable, either
     // absolutely (e.g. allocas) or at this point because we can see other
     // accesses to it.
-    if (!isSafeToLoadUnconditionally(TValue, LI->getAlignment(), DL, LI))
+    if (!isSafeToLoadUnconditionally(TValue, LI->getType(), LI->getAlignment(),
+                                     DL, LI))
       return false;
-    if (!isSafeToLoadUnconditionally(FValue, LI->getAlignment(), DL, LI))
+    if (!isSafeToLoadUnconditionally(FValue, LI->getType(), LI->getAlignment(),
+                                     DL, LI))
       return false;
   }
 
diff --git a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
index c3ccfde8acc..f0b79079d81 100644
--- a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
@@ -340,7 +340,7 @@ static bool canMoveAboveCall(Instruction *I, CallInst *CI, AliasAnalysis *AA) {
       // being loaded from.
       const DataLayout &DL = L->getModule()->getDataLayout();
       if (isModSet(AA->getModRefInfo(CI, MemoryLocation::get(L))) ||
-          !isSafeToLoadUnconditionally(L->getPointerOperand(),
+          !isSafeToLoadUnconditionally(L->getPointerOperand(), L->getType(),
                                        L->getAlignment(), DL, L))
         return false;
     }