Index: include/llvm/Transforms/Utils/SimplifyLibCalls.h
===================================================================
--- include/llvm/Transforms/Utils/SimplifyLibCalls.h
+++ include/llvm/Transforms/Utils/SimplifyLibCalls.h
@@ -167,9 +167,9 @@
   Value *optimizeMemCmp(CallInst *CI, IRBuilder<> &B);
   Value *optimizeBCmp(CallInst *CI, IRBuilder<> &B);
   Value *optimizeMemCmpBCmpCommon(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemCpy(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemMove(CallInst *CI, IRBuilder<> &B);
-  Value *optimizeMemSet(CallInst *CI, IRBuilder<> &B);
+  Value *optimizeMemCpy(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
+  Value *optimizeMemMove(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
+  Value *optimizeMemSet(CallInst *CI, IRBuilder<> &B, bool isIntrinsic = false);
   Value *optimizeRealloc(CallInst *CI, IRBuilder<> &B);
   Value *optimizeWcslen(CallInst *CI, IRBuilder<> &B);
   // Wrapper for all String/Memory Library Call Optimizations
Index: lib/Transforms/Utils/SimplifyLibCalls.cpp
===================================================================
--- lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -186,6 +186,19 @@
   return true;
 }
 
+static void annotateDereferenceableBytes(CallInst *CI,
+                                         ArrayRef<unsigned> ArgNos,
+                                         uint64_t DerefBytes) {
+  for (unsigned ArgNo : ArgNos) {
+    if (CI->getDereferenceableBytes(ArgNo + 1) < DerefBytes) {
+      CI->removeParamAttr(ArgNo, Attribute::Dereferenceable);
+      CI->removeParamAttr(ArgNo, Attribute::DereferenceableOrNull);
+      CI->addParamAttr(ArgNo, Attribute::getWithDereferenceableBytes(
+                                  CI->getContext(), DerefBytes));
+    }
+  }
+}
+
 //===----------------------------------------------------------------------===//
 // String and Memory Library Call Optimizations
 //===----------------------------------------------------------------------===//
@@ -765,9 +778,11 @@
   ConstantInt *LenC = dyn_cast<ConstantInt>(CI->getArgOperand(2));
 
   // memchr(x, y, 0) -> null
-  if (LenC && LenC->isZero())
-    return Constant::getNullValue(CI->getType());
-
+  if (LenC) {
+    annotateDereferenceableBytes(CI, {0}, LenC->getZExtValue());
+    if (LenC->isZero())
+      return Constant::getNullValue(CI->getType());
+  }
   // From now on we need at least constant length and string.
   StringRef Str;
   if (!LenC || !getConstantStringInfo(SrcStr, Str, 0, /*TrimAtNul=*/false))
@@ -926,10 +941,12 @@
     return Constant::getNullValue(CI->getType());
 
   // Handle constant lengths.
-  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size)) {
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
     if (Value *Res = optimizeMemCmpConstantSize(CI, LHS, RHS,
                                                 LenC->getZExtValue(), B, DL))
       return Res;
+  }
 
   return nullptr;
 }
@@ -955,18 +972,33 @@
   return optimizeMemCmpBCmpCommon(CI, B);
 }
 
-Value *LibCallSimplifier::optimizeMemCpy(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemCpy(CallInst *CI, IRBuilder<> &B,
+                                         bool isIntrinsic) {
+  Value *Op0 = CI->getArgOperand(0), *Op1 = CI->getArgOperand(1);
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   // memcpy(x, y, n) -> llvm.memcpy(align 1 x, align 1 y, n)
-  B.CreateMemCpy(CI->getArgOperand(0), 1, CI->getArgOperand(1), 1,
-                 CI->getArgOperand(2));
-  return CI->getArgOperand(0);
+  B.CreateMemCpy(Op0, 1, Op1, 1, Size);
+  return Op0;
 }
 
-Value *LibCallSimplifier::optimizeMemMove(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemMove(CallInst *CI, IRBuilder<> &B, bool isIntrinsic) {
+  Value *Op0 = CI->getArgOperand(0), *Op1 = CI->getArgOperand(1);
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0, 1}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   // memmove(x, y, n) -> llvm.memmove(align 1 x, align 1 y, n)
-  B.CreateMemMove(CI->getArgOperand(0), 1, CI->getArgOperand(1), 1,
-                  CI->getArgOperand(2));
-  return CI->getArgOperand(0);
+  B.CreateMemMove(Op0, 1, Op1, 1, Size);
+  return Op0;
 }
 
 /// Fold memset[_chk](malloc(n), 0, n) --> calloc(1, n).
@@ -1015,14 +1047,23 @@
   return Calloc;
 }
 
-Value *LibCallSimplifier::optimizeMemSet(CallInst *CI, IRBuilder<> &B) {
+Value *LibCallSimplifier::optimizeMemSet(CallInst *CI, IRBuilder<> &B,
+                                         bool isIntrinsic) {
+  Value *Op0 = CI->getArgOperand(0), *Op1 = CI->getArgOperand(1);
+  Value *Size = CI->getArgOperand(2);
+  if (ConstantInt *LenC = dyn_cast<ConstantInt>(Size))
+    annotateDereferenceableBytes(CI, {0}, LenC->getZExtValue());
+
+  if (isIntrinsic)
+    return nullptr;
+
   if (auto *Calloc = foldMallocMemset(CI, B))
     return Calloc;
 
   // memset(p, v, n) -> llvm.memset(align 1 p, v, n)
-  Value *Val = B.CreateIntCast(CI->getArgOperand(1), B.getInt8Ty(), false);
-  B.CreateMemSet(CI->getArgOperand(0), Val, CI->getArgOperand(2), 1);
-  return CI->getArgOperand(0);
+  Value *Val = B.CreateIntCast(Op1, B.getInt8Ty(), false);
+  B.CreateMemSet(Op0, Val, Size, 1);
+  return Op0;
 }
 
 Value *LibCallSimplifier::optimizeRealloc(CallInst *CI, IRBuilder<> &B) {
@@ -2710,6 +2751,12 @@
     case Intrinsic::sqrt:
       return optimizeSqrt(CI, Builder);
     // TODO: Use foldMallocMemset() with memset intrinsic.
+    case Intrinsic::memset:
+      return optimizeMemSet(CI, Builder, true);
+    case Intrinsic::memcpy:
+      return optimizeMemCpy(CI, Builder, true);
+    case Intrinsic::memmove:
+      return optimizeMemMove(CI, Builder, true);
     default:
       return nullptr;
     }
Index: test/Transforms/InstCombine/mem-deref-bytes.ll
===================================================================
--- test/Transforms/InstCombine/mem-deref-bytes.ll
+++ test/Transforms/InstCombine/mem-deref-bytes.ll
@@ -0,0 +1,127 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -instcombine  -S < %s | FileCheck %s
+
+declare i32 @memcmp(i8* nocapture, i8* nocapture, i64)
+declare i8* @memcpy(i8* nocapture, i8* nocapture, i64)
+declare i8* @memmove(i8* nocapture, i8* nocapture, i64)
+declare i8* @memset(i8* nocapture, i8, i64)
+declare i8* @memchr(i8* nocapture, i32, i64)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
+
+define i32 @memcmp_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_set_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_update_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_update_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable(4) %d, i8* dereferenceable(8) %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_update_deref2(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_update_deref2(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* dereferenceable_or_null(8) %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_no_update_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_no_update_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(40) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable(40) %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_const_size_no_update_deref2(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcmp_const_size_no_update_deref2(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* dereferenceable(16) [[D:%.*]], i8* dereferenceable(16) [[S:%.*]], i64 16)
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* dereferenceable_or_null(40) %d, i8* %s, i64 16)
+  ret i32 %call
+}
+
+define i32 @memcmp_nonconst_size(i8* nocapture readonly %d, i8* nocapture readonly %s, i64 %n) {
+; CHECK-LABEL: @memcmp_nonconst_size(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[D:%.*]], i8* [[S:%.*]], i64 [[N:%.*]])
+; CHECK-NEXT:    ret i32 [[CALL]]
+;
+  %call = tail call i32 @memcmp(i8* %d, i8* %s, i64 %n)
+  ret i32 %call
+}
+
+define i8* @memcpy_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memcpy_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(64) [[D:%.*]], i8* align 1 dereferenceable(64) [[S:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  %call = tail call i8* @memcpy(i8* %d, i8* %s, i64 64)
+  ret i8* %call
+}
+
+define i8* @memmove_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @memmove_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 dereferenceable(64) [[D:%.*]], i8* align 1 dereferenceable(64) [[S:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  %call = tail call i8* @memmove(i8* %d, i8* %s, i64 64)
+  ret i8* %call
+}
+
+define i8* @memset_const_size_set_deref(i8* nocapture readonly %s, i8 %c) {
+; CHECK-LABEL: @memset_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 dereferenceable(64) [[S:%.*]], i8 [[C:%.*]], i64 64, i1 false)
+; CHECK-NEXT:    ret i8* [[S]]
+;
+  %call = tail call i8* @memset(i8* %s, i8 %c, i64 64)
+  ret i8* %call
+}
+
+define i8* @memchr_const_size_set_deref(i8* nocapture readonly %s, i32 %c) {
+; CHECK-LABEL: @memchr_const_size_set_deref(
+; CHECK-NEXT:    [[CALL:%.*]] = tail call i8* @memchr(i8* dereferenceable(64) [[S:%.*]], i32 [[C:%.*]], i64 64)
+; CHECK-NEXT:    ret i8* [[CALL]]
+;
+  %call = tail call i8* @memchr(i8* %s, i32 %c, i64 64)
+  ret i8* %call
+}
+
+define i8* @llvm_memcpy_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @llvm_memcpy_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 dereferenceable(16) [[D:%.*]], i8* align 1 dereferenceable(16) [[S:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %d, i8* align 1 %s, i64 16, i1 false)
+  ret i8* %d
+}
+
+define i8* @llvm_memmove_const_size_set_deref(i8* nocapture readonly %d, i8* nocapture readonly %s) {
+; CHECK-LABEL: @llvm_memmove_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 dereferenceable(16) [[D:%.*]], i8* align 1 dereferenceable(16) [[S:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[D]]
+;
+  call void @llvm.memmove.p0i8.p0i8.i64(i8* align 1 %d, i8* align 1 %s, i64 16, i1 false)
+  ret i8* %d
+}
+define i8* @llvm_memset_const_size_set_deref(i8* nocapture readonly %s, i8 %c) {
+; CHECK-LABEL: @llvm_memset_const_size_set_deref(
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 1 dereferenceable(16) [[S:%.*]], i8 [[C:%.*]], i64 16, i1 false)
+; CHECK-NEXT:    ret i8* [[S]]
+;
+  call void @llvm.memset.p0i8.i64(i8* align 1 %s, i8 %c, i64 16, i1 false)
+  ret i8* %s
+}