InstCombine: Canonicalize (gep i8* X, -(ptrtoint Y)) to (sub (ptrtoint X), (ptrtoint Y))

The GEP pattern is what SCEV expander emits for "ugly geps". The latter is what
you get for pointer subtraction in C code. The rest of instcombine already
knows how to deal with that so just canonicalize on that.

llvm-svn: 191090

1 files changed, 14 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index 803c7279bbc..fcb26ab82af 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -1182,6 +1182,20 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) {
         GetElementPtrInst::Create(Src->getOperand(0), Indices, GEP.getName());
   }
 
+  // Canonicalize (gep i8* X, -(ptrtoint Y)) to (sub (ptrtoint X), (ptrtoint Y))
+  // The GEP pattern is emitted by the SCEV expander for certain kinds of
+  // pointer arithmetic.
+  if (TD && GEP.getNumIndices() == 1 &&
+      match(GEP.getOperand(1), m_Neg(m_PtrToInt(m_Value()))) &&
+      GEP.getType() == Builder->getInt8PtrTy() &&
+      GEP.getOperand(1)->getType()->getScalarSizeInBits() ==
+          TD->getPointerSizeInBits(GEP.getPointerAddressSpace())) {
+    Operator *Index = cast<Operator>(GEP.getOperand(1));
+    Value *PtrToInt = Builder->CreatePtrToInt(PtrOp, Index->getType());
+    Value *NewSub = Builder->CreateSub(PtrToInt, Index->getOperand(1));
+    return CastInst::Create(Instruction::IntToPtr, NewSub, GEP.getType());
+  }
+
   // Handle gep(bitcast x) and gep(gep x, 0, 0, 0).
   Value *StrippedPtr = PtrOp->stripPointerCasts();
   PointerType *StrippedPtrTy = dyn_cast<PointerType>(StrippedPtr->getType());