diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -13,6 +13,7 @@
 #include "InstCombineInternal.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/Analysis/ConstantFolding.h"
+#include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/DataLayout.h"
@@ -337,6 +338,42 @@
     }
   }
 
+  // Replace Int2Ptr/Ptr2Int RoundTrip Cast with bitcast if the pointer
+  // is dereferenceable.
+  Value *Ptr = isIntToPtrRoundTripCast(&CI);
+  if (Ptr) {
+    if (isDereferenceableAndAlignedPointer(Ptr, Align(1), APInt(64, 1), DL)) {
+      return new BitCastInst(Ptr, CI.getDestTy());
+    }
+    // Vector to find out all target users of roundtrip (int2ptr/ptr2int) cast
+    // which are dominated by load/store instruction of same address as of
+    // roundtripcast.
+    SmallVector<User *> TargetUsers;
+    Instruction *I;
+    for (auto *CU : CI.users()) {
+      if (!(I = dyn_cast<Instruction>(CU)))
+        continue;
+      int NumIterations = 0;
+      for (auto *U : Ptr->users()) {
+        if (NumIterations == 10)
+          goto DoneWithUsers;
+        NumIterations++;
+        if ((isa<LoadInst>(U) || isa<StoreInst>(U)) &&
+            DT.dominates(cast<Instruction>(U), I)) {
+          TargetUsers.push_back(CU);
+          break;
+        }
+      }
+    }
+  DoneWithUsers:
+    if (!TargetUsers.empty()) {
+      Value *BitCast = Builder.CreateBitCast(Ptr, CI.getDestTy());
+      for (auto *U : TargetUsers) {
+        U->replaceUsesOfWith(&CI, BitCast);
+      }
+      return &CI;
+    }
+  }
   return nullptr;
 }
 
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
--- a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -343,6 +343,7 @@
   Instruction::CastOps isEliminableCastPair(const CastInst *CI1,
                                             const CastInst *CI2);
   Value *simplifyIntToPtrRoundTripCast(Value *Val);
+  Value *isIntToPtrRoundTripCast(Value *Val);
 
   Value *foldAndOfICmps(ICmpInst *LHS, ICmpInst *RHS, BinaryOperator &And);
   Value *foldOrOfICmps(ICmpInst *LHS, ICmpInst *RHS, BinaryOperator &Or);
diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -349,6 +349,14 @@
 // Simplifies IntToPtr/PtrToInt RoundTrip Cast To BitCast.
 // inttoptr ( ptrtoint (x) ) --> x
 Value *InstCombinerImpl::simplifyIntToPtrRoundTripCast(Value *Val) {
+  if (Value *Ptr = isIntToPtrRoundTripCast(Val)) {
+    return CastInst::CreateBitOrPointerCast(Ptr, Val->getType(), "",
+                                            cast<Instruction>(Val));
+  }
+  return nullptr;
+}
+
+Value *InstCombinerImpl::isIntToPtrRoundTripCast(Value *Val) {
   auto *IntToPtr = dyn_cast<IntToPtrInst>(Val);
   if (IntToPtr && DL.getPointerTypeSizeInBits(IntToPtr->getDestTy()) ==
                       DL.getTypeSizeInBits(IntToPtr->getSrcTy())) {
@@ -359,8 +367,7 @@
             PtrToInt->getSrcTy()->getPointerAddressSpace() &&
         DL.getPointerTypeSizeInBits(PtrToInt->getSrcTy()) ==
             DL.getTypeSizeInBits(PtrToInt->getDestTy())) {
-      return CastInst::CreateBitOrPointerCast(PtrToInt->getOperand(0), CastTy,
-                                              "", PtrToInt);
+      return PtrToInt->getOperand(0);
     }
   }
   return nullptr;
diff --git a/llvm/test/Transforms/InstCombine/load-int2ptr-fold.ll b/llvm/test/Transforms/InstCombine/load-int2ptr-fold.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/load-int2ptr-fold.ll
@@ -0,0 +1,147 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -instcombine -S -disable-i2p-p2i-opt < %s | FileCheck %s
+
+target datalayout = "e-p:64:64-p1:16:16-p2:32:32:32-p3:64:64:64"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @test(i8* %X, i8* %Y, i8* %Z) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:    [[XVAL:%.*]] = load i8, i8* [[X:%.*]], align 1
+; CHECK-NEXT:    [[YVAL:%.*]] = load i8, i8* [[Y:%.*]], align 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 [[XVAL]], [[YVAL]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; CHECK:       if.then:
+; CHECK-NEXT:    br label [[CALL:%.*]]
+; CHECK:       if.else:
+; CHECK-NEXT:    [[Z_I:%.*]] = ptrtoint i8* [[Z:%.*]] to i64
+; CHECK-NEXT:    [[Z_P:%.*]] = inttoptr i64 [[Z_I]] to i8*
+; CHECK-NEXT:    br label [[CALL]]
+; CHECK:       call:
+; CHECK-NEXT:    [[PHI_1:%.*]] = phi i8* [ [[Z_P]], [[IF_ELSE]] ], [ [[Y]], [[IF_THEN]] ]
+; CHECK-NEXT:    [[PHI_2:%.*]] = phi i8* [ [[Z_P]], [[IF_ELSE]] ], [ [[X]], [[IF_THEN]] ]
+; CHECK-NEXT:    tail call void @foo(i8* [[PHI_1]], i8* [[PHI_2]])
+; CHECK-NEXT:    ret void
+;
+  %Xval = load i8, i8* %X
+  %Yval = load i8, i8* %Y
+  %cmp  = icmp slt i8 %Xval, %Yval
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:
+  %Y.i = ptrtoint i8* %Y to i64
+  %Y.p = inttoptr i64 %Y.i to i8*
+  %X.i = ptrtoint i8* %X to i64
+  %X.p = inttoptr i64 %X.i to i8*
+  br label %call
+
+if.else:
+  %Z.i = ptrtoint i8* %Z to i64
+  %Z.p = inttoptr i64 %Z.i to i8*
+  br label %call
+
+call:
+  %phi.1 = phi i8* [ %Z.p, %if.else ], [ %Y.p, %if.then ]
+  %phi.2 = phi i8* [ %Z.p, %if.else ], [ %X.p, %if.then ]
+  tail call void @foo(i8* %phi.1, i8* %phi.2)
+  ret void
+}
+
+declare void @foo (i8* %a, i8* %b)
+
+define i8* @test1(i8* %X, i8* %Y, i8* %Z, i1 %cmp) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[XVAL:%.*]] = load i8, i8* [[X:%.*]], align 1
+; CHECK-NEXT:    br i1 [[CMP:%.*]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
+; CHECK:       for.body.preheader:
+; CHECK-NEXT:    [[YVAL:%.*]] = load i8, i8* [[Y:%.*]], align 1
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[PHI:%.*]] = phi i8* [ [[X]], [[FOR_BODY]] ], [ [[Y]], [[FOR_BODY_PREHEADER]] ]
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp slt i8 [[XVAL]], [[YVAL]]
+; CHECK-NEXT:    br i1 [[CMP1]], label [[FOR_BODY]], label [[FOR_END]]
+; CHECK:       for.end:
+; CHECK-NEXT:    [[PHI1:%.*]] = phi i8* [ [[PHI]], [[FOR_BODY]] ], [ [[Z:%.*]], [[ENTRY:%.*]] ]
+; CHECK-NEXT:    ret i8* [[PHI1]]
+;
+entry:
+  %Xval = load i8, i8* %X
+  br i1 %cmp, label %for.body.preheader, label %for.end
+
+for.body.preheader:                               ; preds = %entry
+  %Yval = load i8, i8* %Y
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %for.body.preheader
+  %phi = phi i8* [ %X.p, %for.body ], [ %Y, %for.body.preheader ]
+  %X.i = ptrtoint i8* %X to i64
+  %X.p = inttoptr i64 %X.i to i8*
+  %cmp1  = icmp slt i8 %Xval, %Yval
+  br i1 %cmp1, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %entry
+  %phi1 = phi i8* [%phi, %for.body], [%Z, %entry]
+  ret i8* %phi1
+}
+
+define void @test_dereferenceable(i8* %X, i8* dereferenceable(1) %Z, i1 %cmp) {
+; CHECK-LABEL: @test_dereferenceable(
+; CHECK-NEXT:    br i1 [[CMP:%.*]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; CHECK:       if.then:
+; CHECK-NEXT:    [[X_I:%.*]] = ptrtoint i8* [[X:%.*]] to i64
+; CHECK-NEXT:    [[X_P:%.*]] = inttoptr i64 [[X_I]] to i8*
+; CHECK-NEXT:    br label [[CALL:%.*]]
+; CHECK:       if.else:
+; CHECK-NEXT:    br label [[CALL]]
+; CHECK:       call:
+; CHECK-NEXT:    [[PHI_1:%.*]] = phi i8* [ [[Z:%.*]], [[IF_ELSE]] ], [ [[X_P]], [[IF_THEN]] ]
+; CHECK-NEXT:    tail call void @foo(i8* [[PHI_1]], i8* [[PHI_1]])
+; CHECK-NEXT:    ret void
+;
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:
+  %X.i = ptrtoint i8* %X to i64
+  %X.p = inttoptr i64 %X.i to i8*
+  br label %call
+
+if.else:
+  %Z.i = ptrtoint i8* %Z to i64
+  %Z.p = inttoptr i64 %Z.i to i8*
+  br label %call
+
+call:
+  %phi.1 = phi i8* [ %Z.p, %if.else ], [ %X.p, %if.then ]
+  tail call void @foo(i8* %phi.1, i8* %phi.1)
+  ret void
+}
+
+define void @test_dereferenceable_2(i8* dereferenceable(16) %X, i8* dereferenceable(16) %Z, i1 %cmp) {
+; CHECK-LABEL: @test_dereferenceable_2(
+; CHECK-NEXT:    br i1 [[CMP:%.*]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; CHECK:       if.then:
+; CHECK-NEXT:    br label [[CALL:%.*]]
+; CHECK:       if.else:
+; CHECK-NEXT:    br label [[CALL]]
+; CHECK:       call:
+; CHECK-NEXT:    [[PHI_1:%.*]] = phi i8* [ [[Z:%.*]], [[IF_ELSE]] ], [ [[X:%.*]], [[IF_THEN]] ]
+; CHECK-NEXT:    tail call void @foo(i8* nonnull [[PHI_1]], i8* nonnull [[PHI_1]])
+; CHECK-NEXT:    ret void
+;
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:
+  %X.i = ptrtoint i8* %X to i64
+  %X.p = inttoptr i64 %X.i to i8*
+  br label %call
+
+if.else:
+  %Z.i = ptrtoint i8* %Z to i64
+  %Z.p = inttoptr i64 %Z.i to i8*
+  br label %call
+
+call:
+  %phi.1 = phi i8* [ %Z.p, %if.else ], [ %X.p, %if.then ]
+  tail call void @foo(i8* %phi.1, i8* %phi.1)
+  ret void
+}