Index: llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
@@ -861,6 +861,16 @@
   return nullptr;
 }
 
+// If we get the pattern "(A & ~B) + B", we transfer this pattern to "(A &
+// ~B) | B", And InstCombine will finally fold "(A & ~B) | B" to "A or B"
+Instruction *InstCombinerImpl::foldAddWithOr(BinaryOperator &Add) {
+  Value *Op0 = Add.getOperand(0), *Op1 = Add.getOperand(1);
+  if (match(Op0, m_c_And(m_Not(m_Specific(Op1)), m_Value())) ||
+      match(Op1, m_c_And(m_Not(m_Specific(Op0)), m_Value())))
+    return BinaryOperator::CreateOr(Op0, Op1);
+  return nullptr;
+}
+
 Instruction *InstCombinerImpl::foldAddWithConstant(BinaryOperator &Add) {
   Value *Op0 = Add.getOperand(0), *Op1 = Add.getOperand(1);
   Constant *Op1C;
@@ -1309,6 +1319,9 @@
   if (Instruction *X = foldNoWrapAdd(I, Builder))
     return X;
 
+  if (Instruction *X = foldAddWithOr(I))
+    return X;
+
   Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
   Type *Ty = I.getType();
   if (Ty->isIntOrIntVectorTy(1))
Index: llvm/lib/Transforms/InstCombine/InstCombineInternal.h
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -620,6 +620,7 @@
   Instruction *foldBinOpIntoSelectOrPhi(BinaryOperator &I);
 
   Instruction *foldAddWithConstant(BinaryOperator &Add);
+  Instruction *foldAddWithOr(BinaryOperator &Add);
 
   /// Try to rotate an operation below a PHI node, using PHI nodes for
   /// its operands.
Index: llvm/test/Transforms/InstCombine/and-to-xor.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/InstCombine/and-to-xor.ll
@@ -0,0 +1,28 @@
+; Try to fold (A & ~B) + B to A | B
+; RUN: opt < %s -instcombine -S | FileCheck %s
+
+; CHECK: define i32 @and_to_xor1(i32 %0, i32 %1) local_unnamed_addr
+; CHECK-NOT: %{{[0-9]+}} = xor i32 %{{[0-9]+}}, -1
+; CHECK-NOT:  %{{[0-9]+}} = and i32 %{{[0-9]+}}, %{{[0-9]+}}
+; CHECK: %{{[0-9]+}} = or i32 %{{[0-9]+}}, %{{[0-9]+}}
+define i32 @and_to_xor1(i32 %0, i32 %1) local_unnamed_addr #0 {
+  %3 = shl nsw i32 %0, 1
+  %4 = mul nsw i32 %1, %0
+  %5 = xor i32 %4, -1
+  %6 = and i32 %3, %5
+  %7 = add nsw i32 %6, %4
+  ret i32 %7
+}
+
+; CHECK: define i32 @and_to_xor2(i32 %0, i32 %1)
+; CHECK-NOT: %{{[0-9]+}} = xor i32 %{{[0-9]+}}, -1
+; CHECK-NOT:  %{{[0-9]+}} = and i32 %{{[0-9]+}}, %{{[0-9]+}}
+; CHECK: %{{[0-9]+}} = or i32 %{{[0-9]+}}, %{{[0-9]+}}
+define i32 @and_to_xor2(i32 %0, i32 %1) local_unnamed_addr #0 {
+  %3 = shl nsw i32 %0, 1
+  %4 = mul nsw i32 %1, %0
+  %5 = xor i32 %4, -1
+  %6 = and i32 %3, %5
+  %7 = add nsw i32 %4, %6
+  ret i32 %7
+}