Replace three "strip & accumulate" implementations with a single one

This patch replaces the three almost identical "strip & accumulate"
implementations for constant pointer offsets with a single one,
combining the respective functionalities. The old interfaces are kept
for now.

Differential Revision: https://reviews.llvm.org/D64468

llvm-svn: 365723
diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index ce0b8a0..0a2be05 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -659,32 +659,7 @@
   Type *IntPtrTy = DL.getIntPtrType(V->getType())->getScalarType();
   APInt Offset = APInt::getNullValue(IntPtrTy->getIntegerBitWidth());
 
-  // Even though we don't look through PHI nodes, we could be called on an
-  // instruction in an unreachable block, which may be on a cycle.
-  SmallPtrSet<Value *, 4> Visited;
-  Visited.insert(V);
-  do {
-    if (GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
-      if ((!AllowNonInbounds && !GEP->isInBounds()) ||
-          !GEP->accumulateConstantOffset(DL, Offset))
-        break;
-      V = GEP->getPointerOperand();
-    } else if (Operator::getOpcode(V) == Instruction::BitCast) {
-      V = cast<Operator>(V)->getOperand(0);
-    } else if (GlobalAlias *GA = dyn_cast<GlobalAlias>(V)) {
-      if (GA->isInterposable())
-        break;
-      V = GA->getAliasee();
-    } else {
-      if (auto *Call = dyn_cast<CallBase>(V))
-        if (Value *RV = Call->getReturnedArgOperand()) {
-          V = RV;
-          continue;
-        }
-      break;
-    }
-    assert(V->getType()->isPtrOrPtrVectorTy() && "Unexpected operand type!");
-  } while (Visited.insert(V).second);
+  V = V->stripAndAccumulateConstantOffsets(DL, Offset, AllowNonInbounds);
 
   Constant *OffsetIntPtr = ConstantInt::get(IntPtrTy, Offset);
   if (V->getType()->isVectorTy())
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 0b337ae..27d8e32 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -38,7 +38,6 @@
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/ConstantRange.h"
 #include "llvm/IR/Constants.h"
-#include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Dominators.h"
@@ -3423,57 +3422,6 @@
   return nullptr;
 }
 
-/// Analyze the specified pointer to see if it can be expressed as a base
-/// pointer plus a constant offset. Return the base and offset to the caller.
-Value *llvm::GetPointerBaseWithConstantOffset(Value *Ptr, int64_t &Offset,
-                                              const DataLayout &DL) {
-  unsigned BitWidth = DL.getIndexTypeSizeInBits(Ptr->getType());
-  APInt ByteOffset(BitWidth, 0);
-
-  // We walk up the defs but use a visited set to handle unreachable code. In
-  // that case, we stop after accumulating the cycle once (not that it
-  // matters).
-  SmallPtrSet<Value *, 16> Visited;
-  while (Visited.insert(Ptr).second) {
-    if (Ptr->getType()->isVectorTy())
-      break;
-
-    if (GEPOperator *GEP = dyn_cast<GEPOperator>(Ptr)) {
-      // If one of the values we have visited is an addrspacecast, then
-      // the pointer type of this GEP may be different from the type
-      // of the Ptr parameter which was passed to this function.  This
-      // means when we construct GEPOffset, we need to use the size
-      // of GEP's pointer type rather than the size of the original
-      // pointer type.
-      APInt GEPOffset(DL.getIndexTypeSizeInBits(Ptr->getType()), 0);
-      if (!GEP->accumulateConstantOffset(DL, GEPOffset))
-        break;
-
-      APInt OrigByteOffset(ByteOffset);
-      ByteOffset += GEPOffset.sextOrTrunc(ByteOffset.getBitWidth());
-      if (ByteOffset.getMinSignedBits() > 64) {
-        // Stop traversal if the pointer offset wouldn't fit into int64_t
-        // (this should be removed if Offset is updated to an APInt)
-        ByteOffset = OrigByteOffset;
-        break;
-      }
-
-      Ptr = GEP->getPointerOperand();
-    } else if (Operator::getOpcode(Ptr) == Instruction::BitCast ||
-               Operator::getOpcode(Ptr) == Instruction::AddrSpaceCast) {
-      Ptr = cast<Operator>(Ptr)->getOperand(0);
-    } else if (GlobalAlias *GA = dyn_cast<GlobalAlias>(Ptr)) {
-      if (GA->isInterposable())
-        break;
-      Ptr = GA->getAliasee();
-    } else {
-      break;
-    }
-  }
-  Offset = ByteOffset.getSExtValue();
-  return Ptr;
-}
-
 bool llvm::isGEPBasedOnPointerToString(const GEPOperator *GEP,
                                        unsigned CharSize) {
   // Make sure the GEP has exactly three arguments.
@@ -4401,7 +4349,7 @@
       // Note: It's really tempting to think that a conditional branch or
       // switch should be listed here, but that's incorrect.  It's not
       // branching off of poison which is UB, it is executing a side effecting
-      // instruction which follows the branch.  
+      // instruction which follows the branch.
       return nullptr;
   }
 }
diff --git a/llvm/lib/IR/Value.cpp b/llvm/lib/IR/Value.cpp
index 9e0a43c..b7f77dc 100644
--- a/llvm/lib/IR/Value.cpp
+++ b/llvm/lib/IR/Value.cpp
@@ -555,13 +555,13 @@
 }
 
 const Value *
-Value::stripAndAccumulateInBoundsConstantOffsets(const DataLayout &DL,
-                                                 APInt &Offset) const {
-  if (!getType()->isPointerTy())
+Value::stripAndAccumulateConstantOffsets(const DataLayout &DL, APInt &Offset,
+                                         bool AllowNonInbounds) const {
+  if (!getType()->isPtrOrPtrVectorTy())
     return this;
 
-  assert(Offset.getBitWidth() == DL.getIndexSizeInBits(cast<PointerType>(
-                                     getType())->getAddressSpace()) &&
+  unsigned BitWidth = Offset.getBitWidth();
+  assert(BitWidth == DL.getIndexTypeSizeInBits(getType()) &&
          "The offset bit width does not match the DL specification.");
 
   // Even though we don't look through PHI nodes, we could be called on an
@@ -571,27 +571,39 @@
   const Value *V = this;
   do {
     if (auto *GEP = dyn_cast<GEPOperator>(V)) {
-      if (!GEP->isInBounds())
+      // If in-bounds was requested, we do not strip non-in-bounds GEPs.
+      if (!AllowNonInbounds && !GEP->isInBounds())
         return V;
-      APInt GEPOffset(Offset);
+
+      // If one of the values we have visited is an addrspacecast, then
+      // the pointer type of this GEP may be different from the type
+      // of the Ptr parameter which was passed to this function.  This
+      // means when we construct GEPOffset, we need to use the size
+      // of GEP's pointer type rather than the size of the original
+      // pointer type.
+      APInt GEPOffset(DL.getIndexTypeSizeInBits(V->getType()), 0);
       if (!GEP->accumulateConstantOffset(DL, GEPOffset))
         return V;
-      Offset = GEPOffset;
+
+      // Stop traversal if the pointer offset wouldn't fit in the bit-width
+      // provided by the Offset argument. This can happen due to AddrSpaceCast
+      // stripping.
+      if (GEPOffset.getMinSignedBits() > BitWidth)
+        return V;
+
+      Offset += GEPOffset.sextOrTrunc(BitWidth);
       V = GEP->getPointerOperand();
-    } else if (Operator::getOpcode(V) == Instruction::BitCast) {
+    } else if (Operator::getOpcode(V) == Instruction::BitCast ||
+               Operator::getOpcode(V) == Instruction::AddrSpaceCast) {
       V = cast<Operator>(V)->getOperand(0);
     } else if (auto *GA = dyn_cast<GlobalAlias>(V)) {
-      V = GA->getAliasee();
-    } else {
-      if (const auto *Call = dyn_cast<CallBase>(V))
-        if (const Value *RV = Call->getReturnedArgOperand()) {
+      if (!GA->isInterposable())
+        V = GA->getAliasee();
+    } else if (const auto *Call = dyn_cast<CallBase>(V)) {
+        if (const Value *RV = Call->getReturnedArgOperand())
           V = RV;
-          continue;
-        }
-
-      return V;
     }
-    assert(V->getType()->isPointerTy() && "Unexpected operand type!");
+    assert(V->getType()->isPtrOrPtrVectorTy() && "Unexpected operand type!");
   } while (Visited.insert(V).second);
 
   return V;