diff --git a/docs/LangRef.rst b/docs/LangRef.rst
index 86d8c62af2b..0c1039f60c0 100644
--- a/docs/LangRef.rst
+++ b/docs/LangRef.rst
@@ -1066,6 +1066,30 @@ Currently, only the following parameter attributes are defined:
     site. If the alignment is not specified, then the code generator
     makes a target-specific assumption.
 
+.. _attr_byref:
+
+``byref(<ty>)``
+
+    The ``byref`` argument attribute allows specifying the pointee
+    memory type of an argument. This is similar to ``byval``, but does
+    not imply a copy is made anywhere, or that the argument is passed
+    on the stack. This implies the pointer is dereferenceable up to
+    the storage size of the type.
+
+    It is not generally permissible to introduce a write to an
+    ``byref`` pointer. The pointer may have any address space and may
+    be read only.
+
+    This is not a valid attribute for return values.
+
+    The alignment for an ``byref`` parameter can be explicitly
+    specified by combining it with the ``align`` attribute, similar to
+    ``byval``. If the alignment is not specified, then the code generator
+    makes a target-specific assumption.
+
+     This is intended for representing ABI constraints, and is not
+    intended to be inferred for optimization use.
+
 .. _attr_preallocated:
 
 ``preallocated(<ty>)``
diff --git a/docs/ReleaseNotes.rst b/docs/ReleaseNotes.rst
index 6293c82e353..42867a89da6 100644
--- a/docs/ReleaseNotes.rst
+++ b/docs/ReleaseNotes.rst
@@ -59,6 +59,9 @@ Changes to the LLVM IR
 
 * ...
 
+* Added the ``byref`` attribute to better represent argument passing
+  for the `amdgpu_kernel` calling convention.
+
 Changes to building LLVM
 ------------------------
 
@@ -88,6 +91,9 @@ Changes to the AMDGPU Target
 
 During this release ...
 
+* The new ``byref`` attribute is now the preferred method for
+  representing aggregate kernel arguments.
+
 Changes to the AVR Target
 -----------------------------
 
diff --git a/include/llvm/Bitcode/LLVMBitCodes.h b/include/llvm/Bitcode/LLVMBitCodes.h
index de4fe663032..452918cde64 100644
--- a/include/llvm/Bitcode/LLVMBitCodes.h
+++ b/include/llvm/Bitcode/LLVMBitCodes.h
@@ -644,6 +644,7 @@ enum AttributeKindCodes {
   ATTR_KIND_NO_MERGE = 66,
   ATTR_KIND_NULL_POINTER_IS_VALID = 67,
   ATTR_KIND_NOUNDEF = 68,
+  ATTR_KIND_BYREF = 69,
 };
 
 enum ComdatSelectionKindCodes {
diff --git a/include/llvm/IR/Argument.h b/include/llvm/IR/Argument.h
index 2ca18c61034..2dd7c6cbc8b 100644
--- a/include/llvm/IR/Argument.h
+++ b/include/llvm/IR/Argument.h
@@ -65,6 +65,9 @@ public:
   /// Return true if this argument has the byval attribute.
   bool hasByValAttr() const;
 
+  /// Return true if this argument has the byref attribute.
+  bool hasByRefAttr() const;
+
   /// Return true if this argument has the swiftself attribute.
   bool hasSwiftSelfAttr() const;
 
@@ -80,6 +83,15 @@ public:
   /// in-memory ABI size copied to the stack for the call. Otherwise, return 0.
   uint64_t getPassPointeeByValueCopySize(const DataLayout &DL) const;
 
+  /// Return true if this argument has the byval, inalloca, preallocated, or
+  /// byref attribute. These attributes represent arguments being passed by
+  /// value (which may or may not involve a stack copy)
+  bool hasPointeeInMemoryValueAttr() const;
+
+  /// If hasPointeeInMemoryValueAttr returns true, the in-memory ABI type is
+  /// returned. Otherwise, nullptr.
+  Type *getPointeeInMemoryValueType() const;
+
   /// If this is a byval or inalloca argument, return its alignment.
   /// FIXME: Remove this function once transition to Align is over.
   /// Use getParamAlign() instead.
@@ -91,6 +103,9 @@ public:
   /// If this is a byval argument, return its type.
   Type *getParamByValType() const;
 
+  /// If this is a byref argument, return its type.
+  Type *getParamByRefType() const;
+
   /// Return true if this argument has the nest attribute.
   bool hasNestAttr() const;
 
diff --git a/include/llvm/IR/Attributes.h b/include/llvm/IR/Attributes.h
index 58365aa2b76..03f2fc123cb 100644
--- a/include/llvm/IR/Attributes.h
+++ b/include/llvm/IR/Attributes.h
@@ -108,6 +108,7 @@ public:
                                         unsigned ElemSizeArg,
                                         const Optional<unsigned> &NumElemsArg);
   static Attribute getWithByValType(LLVMContext &Context, Type *Ty);
+  static Attribute getWithByRefType(LLVMContext &Context, Type *Ty);
   static Attribute getWithPreallocatedType(LLVMContext &Context, Type *Ty);
 
   static Attribute::AttrKind getAttrKindFromName(StringRef AttrName);
@@ -303,6 +304,7 @@ public:
   uint64_t getDereferenceableBytes() const;
   uint64_t getDereferenceableOrNullBytes() const;
   Type *getByValType() const;
+  Type *getByRefType() const;
   Type *getPreallocatedType() const;
   std::pair<unsigned, Optional<unsigned>> getAllocSizeArgs() const;
   std::string getAsString(bool InAttrGrp = false) const;
@@ -626,6 +628,9 @@ public:
   /// Return the byval type for the specified function parameter.
   Type *getParamByValType(unsigned ArgNo) const;
 
+  /// Return the byref type for the specified function parameter.
+  Type *getParamByRefType(unsigned ArgNo) const;
+
   /// Return the preallocated type for the specified function parameter.
   Type *getParamPreallocatedType(unsigned ArgNo) const;
 
@@ -729,6 +734,7 @@ class AttrBuilder {
   uint64_t DerefOrNullBytes = 0;
   uint64_t AllocSizeArgs = 0;
   Type *ByValType = nullptr;
+  Type *ByRefType = nullptr;
   Type *PreallocatedType = nullptr;
 
 public:
@@ -808,6 +814,9 @@ public:
   /// Retrieve the byval type.
   Type *getByValType() const { return ByValType; }
 
+  /// Retrieve the byref type.
+  Type *getByRefType() const { return ByRefType; }
+
   /// Retrieve the preallocated type.
   Type *getPreallocatedType() const { return PreallocatedType; }
 
@@ -854,6 +863,9 @@ public:
   /// This turns a byval type into the form used internally in Attribute.
   AttrBuilder &addByValAttr(Type *Ty);
 
+  /// This turns a byref type into the form used internally in Attribute.
+  AttrBuilder &addByRefAttr(Type *Ty);
+
   /// This turns a preallocated type into the form used internally in Attribute.
   AttrBuilder &addPreallocatedAttr(Type *Ty);
 
diff --git a/include/llvm/IR/Attributes.td b/include/llvm/IR/Attributes.td
index 395f9dbfb17..214eb84b6a4 100644
--- a/include/llvm/IR/Attributes.td
+++ b/include/llvm/IR/Attributes.td
@@ -39,6 +39,9 @@ def Builtin : EnumAttr<"builtin">;
 /// Pass structure by value.
 def ByVal : TypeAttr<"byval">;
 
+/// Mark in-memory ABI type.
+def ByRef : TypeAttr<"byref">;
+
 /// Parameter or return value may not contain uninitialized or poison bits.
 def NoUndef : EnumAttr<"noundef">;
 
diff --git a/include/llvm/IR/Function.h b/include/llvm/IR/Function.h
index bb4ec13c761..9bbd0cb6b20 100644
--- a/include/llvm/IR/Function.h
+++ b/include/llvm/IR/Function.h
@@ -467,6 +467,11 @@ public:
     return Ty ? Ty : (arg_begin() + ArgNo)->getType()->getPointerElementType();
   }
 
+  /// Extract the byref type for a parameter.
+  Type *getParamByRefType(unsigned ArgNo) const {
+    return AttributeSets.getParamByRefType(ArgNo);
+  }
+
   /// Extract the number of dereferenceable bytes for a call or
   /// parameter (0=unknown).
   /// @param i AttributeList index, referring to a return value or argument.
diff --git a/lib/Analysis/MemoryBuiltins.cpp b/lib/Analysis/MemoryBuiltins.cpp
index 204f855d28b..402a2bcadf5 100644
--- a/lib/Analysis/MemoryBuiltins.cpp
+++ b/lib/Analysis/MemoryBuiltins.cpp
@@ -676,13 +676,14 @@ SizeOffsetType ObjectSizeOffsetVisitor::visitAllocaInst(AllocaInst &I) {
 }
 
 SizeOffsetType ObjectSizeOffsetVisitor::visitArgument(Argument &A) {
+  Type *MemoryTy = A.getPointeeInMemoryValueType();
   // No interprocedural analysis is done at the moment.
-  if (!A.hasPassPointeeByValueCopyAttr()) {
+  if (!MemoryTy) {
     ++ObjectVisitorArgument;
     return unknown();
   }
-  PointerType *PT = cast<PointerType>(A.getType());
-  APInt Size(IntTyBits, DL.getTypeAllocSize(PT->getElementType()));
+
+  APInt Size(IntTyBits, DL.getTypeAllocSize(MemoryTy));
   return std::make_pair(align(Size, A.getParamAlignment()), Zero);
 }
 
diff --git a/lib/AsmParser/LLLexer.cpp b/lib/AsmParser/LLLexer.cpp
index 777ce3abddd..591c6c3be2f 100644
--- a/lib/AsmParser/LLLexer.cpp
+++ b/lib/AsmParser/LLLexer.cpp
@@ -697,6 +697,7 @@ lltok::Kind LLLexer::LexIdentifier() {
   KEYWORD(writeonly);
   KEYWORD(zeroext);
   KEYWORD(immarg);
+  KEYWORD(byref);
 
   KEYWORD(type);
   KEYWORD(opaque);
diff --git a/lib/AsmParser/LLParser.cpp b/lib/AsmParser/LLParser.cpp
index c9f21ee8382..1a1c1d8eec9 100644
--- a/lib/AsmParser/LLParser.cpp
+++ b/lib/AsmParser/LLParser.cpp
@@ -1382,6 +1382,7 @@ bool LLParser::ParseFnAttributeValuePairs(AttrBuilder &B,
     case lltok::kw_swifterror:
     case lltok::kw_swiftself:
     case lltok::kw_immarg:
+    case lltok::kw_byref:
       HaveError |=
         Error(Lex.getLoc(),
               "invalid use of parameter-only attribute on a function");
@@ -1675,6 +1676,13 @@ bool LLParser::ParseOptionalParamAttrs(AttrBuilder &B) {
       B.addDereferenceableOrNullAttr(Bytes);
       continue;
     }
+    case lltok::kw_byref: {
+      Type *Ty;
+      if (ParseByRef(Ty))
+        return true;
+      B.addByRefAttr(Ty);
+      continue;
+    }
     case lltok::kw_inalloca:        B.addAttribute(Attribute::InAlloca); break;
     case lltok::kw_inreg:           B.addAttribute(Attribute::InReg); break;
     case lltok::kw_nest:            B.addAttribute(Attribute::Nest); break;
@@ -1795,6 +1803,7 @@ bool LLParser::ParseOptionalReturnAttrs(AttrBuilder &B) {
     case lltok::kw_swifterror:
     case lltok::kw_swiftself:
     case lltok::kw_immarg:
+    case lltok::kw_byref:
       HaveError |= Error(Lex.getLoc(), "invalid use of parameter-only attribute");
       break;
 
@@ -2568,11 +2577,11 @@ bool LLParser::ParseByValWithOptionalType(Type *&Result) {
   return false;
 }
 
-/// ParsePreallocated
-///   ::= preallocated(<ty>)
-bool LLParser::ParsePreallocated(Type *&Result) {
+/// ParseRequiredTypeAttr
+///   ::= attrname(<ty>)
+bool LLParser::ParseRequiredTypeAttr(Type *&Result, lltok::Kind AttrName) {
   Result = nullptr;
-  if (!EatIfPresent(lltok::kw_preallocated))
+  if (!EatIfPresent(AttrName))
     return true;
   if (!EatIfPresent(lltok::lparen))
     return Error(Lex.getLoc(), "expected '('");
@@ -2583,6 +2592,18 @@ bool LLParser::ParsePreallocated(Type *&Result) {
   return false;
 }
 
+/// ParsePreallocated
+///   ::= preallocated(<ty>)
+bool LLParser::ParsePreallocated(Type *&Result) {
+  return ParseRequiredTypeAttr(Result, lltok::kw_preallocated);
+}
+
+/// ParseByRef
+///   ::= byref(<type>)
+bool LLParser::ParseByRef(Type *&Result) {
+  return ParseRequiredTypeAttr(Result, lltok::kw_byref);
+}
+
 /// ParseOptionalOperandBundles
 ///    ::= /*empty*/
 ///    ::= '[' OperandBundle [, OperandBundle ]* ']'
diff --git a/lib/AsmParser/LLParser.h b/lib/AsmParser/LLParser.h
index ebd8655dc35..333b8a35cfc 100644
--- a/lib/AsmParser/LLParser.h
+++ b/lib/AsmParser/LLParser.h
@@ -333,7 +333,10 @@ namespace llvm {
                                     std::vector<unsigned> &FwdRefAttrGrps,
                                     bool inAttrGrp, LocTy &BuiltinLoc);
     bool ParseByValWithOptionalType(Type *&Result);
+
+    bool ParseRequiredTypeAttr(Type *&Result, lltok::Kind AttrName);
     bool ParsePreallocated(Type *&Result);
+    bool ParseByRef(Type *&Result);
 
     // Module Summary Index Parsing.
     bool SkipModuleSummaryEntry();
diff --git a/lib/AsmParser/LLToken.h b/lib/AsmParser/LLToken.h
index 0fb3bae77dd..8bdeb57999c 100644
--- a/lib/AsmParser/LLToken.h
+++ b/lib/AsmParser/LLToken.h
@@ -240,6 +240,7 @@ enum Kind {
   kw_writeonly,
   kw_zeroext,
   kw_immarg,
+  kw_byref,
 
   kw_type,
   kw_opaque,
diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp
index 659e26c2bd2..86b8f5ca5b8 100644
--- a/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -1532,6 +1532,8 @@ static Attribute::AttrKind getAttrFromCode(uint64_t Code) {
     return Attribute::Preallocated;
   case bitc::ATTR_KIND_NOUNDEF:
     return Attribute::NoUndef;
+  case bitc::ATTR_KIND_BYREF:
+    return Attribute::ByRef;
   }
 }
 
@@ -1649,6 +1651,8 @@ Error BitcodeReader::parseAttributeGroupBlock() {
             return Err;
           if (Kind == Attribute::ByVal) {
             B.addByValAttr(HasType ? getTypeByID(Record[++i]) : nullptr);
+          } else if (Kind == Attribute::ByRef) {
+            B.addByRefAttr(getTypeByID(Record[++i]));
           } else if (Kind == Attribute::Preallocated) {
             B.addPreallocatedAttr(getTypeByID(Record[++i]));
           }
diff --git a/lib/Bitcode/Writer/BitcodeWriter.cpp b/lib/Bitcode/Writer/BitcodeWriter.cpp
index 9c15a5f9f19..4cab4e06bc6 100644
--- a/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -733,6 +733,8 @@ static uint64_t getAttrKindEncoding(Attribute::AttrKind Kind) {
     return bitc::ATTR_KIND_PREALLOCATED;
   case Attribute::NoUndef:
     return bitc::ATTR_KIND_NOUNDEF;
+  case Attribute::ByRef:
+    return bitc::ATTR_KIND_BYREF;
   case Attribute::EndAttrKinds:
     llvm_unreachable("Can not encode end-attribute kinds marker.");
   case Attribute::None:
diff --git a/lib/IR/AsmWriter.cpp b/lib/IR/AsmWriter.cpp
index fd08310316b..83ad4e2b273 100644
--- a/lib/IR/AsmWriter.cpp
+++ b/lib/IR/AsmWriter.cpp
@@ -4269,11 +4269,14 @@ void AssemblyWriter::writeAttribute(const Attribute &Attr, bool InAttrGroup) {
   }
 
   assert((Attr.hasAttribute(Attribute::ByVal) ||
+          Attr.hasAttribute(Attribute::ByRef) ||
           Attr.hasAttribute(Attribute::Preallocated)) &&
          "unexpected type attr");
 
   if (Attr.hasAttribute(Attribute::ByVal)) {
     Out << "byval";
+  } else if (Attr.hasAttribute(Attribute::ByRef)) {
+    Out << "byref";
   } else {
     Out << "preallocated";
   }
diff --git a/lib/IR/AttributeImpl.h b/lib/IR/AttributeImpl.h
index 5c334348cde..b013474d927 100644
--- a/lib/IR/AttributeImpl.h
+++ b/lib/IR/AttributeImpl.h
@@ -251,6 +251,7 @@ public:
   std::pair<unsigned, Optional<unsigned>> getAllocSizeArgs() const;
   std::string getAsString(bool InAttrGrp) const;
   Type *getByValType() const;
+  Type *getByRefType() const;
   Type *getPreallocatedType() const;
 
   using iterator = const Attribute *;
diff --git a/lib/IR/Attributes.cpp b/lib/IR/Attributes.cpp
index 8bf4e82357c..43074e8193b 100644
--- a/lib/IR/Attributes.cpp
+++ b/lib/IR/Attributes.cpp
@@ -172,6 +172,10 @@ Attribute Attribute::getWithByValType(LLVMContext &Context, Type *Ty) {
   return get(Context, ByVal, Ty);
 }
 
+Attribute Attribute::getWithByRefType(LLVMContext &Context, Type *Ty) {
+  return get(Context, ByRef, Ty);
+}
+
 Attribute Attribute::getWithPreallocatedType(LLVMContext &Context, Type *Ty) {
   return get(Context, Preallocated, Ty);
 }
@@ -459,9 +463,9 @@ std::string Attribute::getAsString(bool InAttrGrp) const {
     return Result;
   }
 
-  if (hasAttribute(Attribute::Preallocated)) {
-    std::string Result;
-    Result += "preallocated";
+  const bool IsByRef = hasAttribute(Attribute::ByRef);
+  if (IsByRef || hasAttribute(Attribute::Preallocated)) {
+    std::string Result = IsByRef ? "byref" : "preallocated";
     raw_string_ostream OS(Result);
     Result += '(';
     getValueAsType()->print(OS, false, true);
@@ -742,6 +746,10 @@ uint64_t AttributeSet::getDereferenceableOrNullBytes() const {
   return SetNode ? SetNode->getDereferenceableOrNullBytes() : 0;
 }
 
+Type *AttributeSet::getByRefType() const {
+  return SetNode ? SetNode->getByRefType() : nullptr;
+}
+
 Type *AttributeSet::getByValType() const {
   return SetNode ? SetNode->getByValType() : nullptr;
 }
@@ -842,6 +850,9 @@ AttributeSetNode *AttributeSetNode::get(LLVMContext &C, const AttrBuilder &B) {
     case Attribute::ByVal:
       Attr = Attribute::getWithByValType(C, B.getByValType());
       break;
+    case Attribute::ByRef:
+      Attr = Attribute::getWithByRefType(C, B.getByRefType());
+      break;
     case Attribute::Preallocated:
       Attr = Attribute::getWithPreallocatedType(C, B.getPreallocatedType());
       break;
@@ -928,6 +939,12 @@ Type *AttributeSetNode::getByValType() const {
   return nullptr;
 }
 
+Type *AttributeSetNode::getByRefType() const {
+  if (auto A = findEnumAttribute(Attribute::ByRef))
+    return A->getValueAsType();
+  return nullptr;
+}
+
 Type *AttributeSetNode::getPreallocatedType() const {
   if (auto A = findEnumAttribute(Attribute::Preallocated))
     return A->getValueAsType();
@@ -1449,6 +1466,10 @@ Type *AttributeList::getParamByValType(unsigned Index) const {
   return getAttributes(Index+FirstArgIndex).getByValType();
 }
 
+Type *AttributeList::getParamByRefType(unsigned Index) const {
+  return getAttributes(Index + FirstArgIndex).getByRefType();
+}
+
 Type *AttributeList::getParamPreallocatedType(unsigned Index) const {
   return getAttributes(Index + FirstArgIndex).getPreallocatedType();
 }
@@ -1534,6 +1555,7 @@ void AttrBuilder::clear() {
   DerefBytes = DerefOrNullBytes = 0;
   AllocSizeArgs = 0;
   ByValType = nullptr;
+  ByRefType = nullptr;
   PreallocatedType = nullptr;
 }
 
@@ -1560,6 +1582,8 @@ AttrBuilder &AttrBuilder::addAttribute(Attribute Attr) {
     StackAlignment = Attr.getStackAlignment();
   else if (Kind == Attribute::ByVal)
     ByValType = Attr.getValueAsType();
+  else if (Kind == Attribute::ByRef)
+    ByRefType = Attr.getValueAsType();
   else if (Kind == Attribute::Preallocated)
     PreallocatedType = Attr.getValueAsType();
   else if (Kind == Attribute::Dereferenceable)
@@ -1586,6 +1610,8 @@ AttrBuilder &AttrBuilder::removeAttribute(Attribute::AttrKind Val) {
     StackAlignment.reset();
   else if (Val == Attribute::ByVal)
     ByValType = nullptr;
+  else if (Val == Attribute::ByRef)
+    ByRefType = nullptr;
   else if (Val == Attribute::Preallocated)
     PreallocatedType = nullptr;
   else if (Val == Attribute::Dereferenceable)
@@ -1676,6 +1702,12 @@ AttrBuilder &AttrBuilder::addByValAttr(Type *Ty) {
   return *this;
 }
 
+AttrBuilder &AttrBuilder::addByRefAttr(Type *Ty) {
+  Attrs[Attribute::ByRef] = true;
+  ByRefType = Ty;
+  return *this;
+}
+
 AttrBuilder &AttrBuilder::addPreallocatedAttr(Type *Ty) {
   Attrs[Attribute::Preallocated] = true;
   PreallocatedType = Ty;
@@ -1702,6 +1734,9 @@ AttrBuilder &AttrBuilder::merge(const AttrBuilder &B) {
   if (!ByValType)
     ByValType = B.ByValType;
 
+  if (!ByRefType)
+    ByRefType = B.ByRefType;
+
   if (!PreallocatedType)
     PreallocatedType = B.PreallocatedType;
 
@@ -1733,6 +1768,9 @@ AttrBuilder &AttrBuilder::remove(const AttrBuilder &B) {
   if (B.ByValType)
     ByValType = nullptr;
 
+  if (B.ByRefType)
+    ByRefType = nullptr;
+
   if (B.PreallocatedType)
     PreallocatedType = nullptr;
 
@@ -1796,7 +1834,7 @@ bool AttrBuilder::operator==(const AttrBuilder &B) {
 
   return Alignment == B.Alignment && StackAlignment == B.StackAlignment &&
          DerefBytes == B.DerefBytes && ByValType == B.ByValType &&
-         PreallocatedType == B.PreallocatedType;
+         ByRefType == B.ByRefType && PreallocatedType == B.PreallocatedType;
 }
 
 //===----------------------------------------------------------------------===//
@@ -1825,7 +1863,8 @@ AttrBuilder AttributeFuncs::typeIncompatible(Type *Ty) {
         .addAttribute(Attribute::StructRet)
         .addAttribute(Attribute::InAlloca)
         .addPreallocatedAttr(Ty)
-        .addByValAttr(Ty);
+        .addByValAttr(Ty)
+        .addByRefAttr(Ty);
 
   return Incompatible;
 }
diff --git a/lib/IR/Function.cpp b/lib/IR/Function.cpp
index 8db2389ef54..35472f7473b 100644
--- a/lib/IR/Function.cpp
+++ b/lib/IR/Function.cpp
@@ -102,6 +102,12 @@ bool Argument::hasByValAttr() const {
   return hasAttribute(Attribute::ByVal);
 }
 
+bool Argument::hasByRefAttr() const {
+  if (!getType()->isPointerTy())
+    return false;
+  return hasAttribute(Attribute::ByRef);
+}
+
 bool Argument::hasSwiftSelfAttr() const {
   return getParent()->hasParamAttribute(getArgNo(), Attribute::SwiftSelf);
 }
@@ -129,27 +135,52 @@ bool Argument::hasPassPointeeByValueCopyAttr() const {
          Attrs.hasParamAttribute(getArgNo(), Attribute::Preallocated);
 }
 
-uint64_t Argument::getPassPointeeByValueCopySize(const DataLayout &DL) const {
-  AttributeSet ParamAttrs
-    = getParent()->getAttributes().getParamAttributes(getArgNo());
+bool Argument::hasPointeeInMemoryValueAttr() const {
+  if (!getType()->isPointerTy())
+    return false;
+  AttributeList Attrs = getParent()->getAttributes();
+  return Attrs.hasParamAttribute(getArgNo(), Attribute::ByVal) ||
+         Attrs.hasParamAttribute(getArgNo(), Attribute::InAlloca) ||
+         Attrs.hasParamAttribute(getArgNo(), Attribute::Preallocated) ||
+         Attrs.hasParamAttribute(getArgNo(), Attribute::ByRef);
+}
 
+/// For a byval, inalloca, or preallocated parameter, get the in-memory
+/// parameter type.
+static Type *getMemoryParamAllocType(AttributeSet ParamAttrs, Type *ArgTy) {
   // FIXME: All the type carrying attributes are mutually exclusive, so there
   // should be a single query to get the stored type that handles any of them.
   if (Type *ByValTy = ParamAttrs.getByValType())
-    return DL.getTypeAllocSize(ByValTy);
+    return ByValTy;
+  if (Type *ByRefTy = ParamAttrs.getByRefType())
+    return ByRefTy;
   if (Type *PreAllocTy = ParamAttrs.getPreallocatedType())
-    return DL.getTypeAllocSize(PreAllocTy);
+    return PreAllocTy;
 
   // FIXME: inalloca always depends on pointee element type. It's also possible
   // for byval to miss it.
   if (ParamAttrs.hasAttribute(Attribute::InAlloca) ||
       ParamAttrs.hasAttribute(Attribute::ByVal) ||
       ParamAttrs.hasAttribute(Attribute::Preallocated))
-    return DL.getTypeAllocSize(cast<PointerType>(getType())->getElementType());
+    return cast<PointerType>(ArgTy)->getElementType();
 
+  return nullptr;
+}
+
+uint64_t Argument::getPassPointeeByValueCopySize(const DataLayout &DL) const {
+  AttributeSet ParamAttrs =
+      getParent()->getAttributes().getParamAttributes(getArgNo());
+  if (Type *MemTy = getMemoryParamAllocType(ParamAttrs, getType()))
+    return DL.getTypeAllocSize(MemTy);
   return 0;
 }
 
+Type *Argument::getPointeeInMemoryValueType() const {
+  AttributeSet ParamAttrs =
+      getParent()->getAttributes().getParamAttributes(getArgNo());
+  return getMemoryParamAllocType(ParamAttrs, getType());
+}
+
 unsigned Argument::getParamAlignment() const {
   assert(getType()->isPointerTy() && "Only pointers have alignments");
   return getParent()->getParamAlignment(getArgNo());
@@ -165,6 +196,11 @@ Type *Argument::getParamByValType() const {
   return getParent()->getParamByValType(getArgNo());
 }
 
+Type *Argument::getParamByRefType() const {
+  assert(getType()->isPointerTy() && "Only pointers have byval types");
+  return getParent()->getParamByRefType(getArgNo());
+}
+
 uint64_t Argument::getDereferenceableBytes() const {
   assert(getType()->isPointerTy() &&
          "Only pointers have dereferenceable bytes");
diff --git a/lib/IR/Verifier.cpp b/lib/IR/Verifier.cpp
index c518ae87ea9..ea562f64da2 100644
--- a/lib/IR/Verifier.cpp
+++ b/lib/IR/Verifier.cpp
@@ -1652,9 +1652,10 @@ void Verifier::verifyParameterAttrs(AttributeSet Attrs, Type *Ty,
   AttrCount += Attrs.hasAttribute(Attribute::StructRet) ||
                Attrs.hasAttribute(Attribute::InReg);
   AttrCount += Attrs.hasAttribute(Attribute::Nest);
+  AttrCount += Attrs.hasAttribute(Attribute::ByRef);
   Assert(AttrCount <= 1,
          "Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', "
-         "and 'sret' are incompatible!",
+         "'byref', and 'sret' are incompatible!",
          V);
 
   Assert(!(Attrs.hasAttribute(Attribute::InAlloca) &&
@@ -1720,9 +1721,10 @@ void Verifier::verifyParameterAttrs(AttributeSet Attrs, Type *Ty,
     SmallPtrSet<Type*, 4> Visited;
     if (!PTy->getElementType()->isSized(&Visited)) {
       Assert(!Attrs.hasAttribute(Attribute::ByVal) &&
-                 !Attrs.hasAttribute(Attribute::InAlloca) &&
-                 !Attrs.hasAttribute(Attribute::Preallocated),
-             "Attributes 'byval', 'inalloca', and 'preallocated' do not "
+             !Attrs.hasAttribute(Attribute::ByRef) &&
+             !Attrs.hasAttribute(Attribute::InAlloca) &&
+             !Attrs.hasAttribute(Attribute::Preallocated),
+             "Attributes 'byval', 'byref', 'inalloca', and 'preallocated' do not "
              "support unsized types!",
              V);
     }
@@ -1731,10 +1733,18 @@ void Verifier::verifyParameterAttrs(AttributeSet Attrs, Type *Ty,
              "Attribute 'swifterror' only applies to parameters "
              "with pointer to pointer type!",
              V);
+
+    if (Attrs.hasAttribute(Attribute::ByRef)) {
+      Assert(Attrs.getByRefType() == PTy->getElementType(),
+             "Attribute 'byref' type does not match parameter!", V);
+    }
   } else {
     Assert(!Attrs.hasAttribute(Attribute::ByVal),
            "Attribute 'byval' only applies to parameters with pointer type!",
            V);
+    Assert(!Attrs.hasAttribute(Attribute::ByRef),
+           "Attribute 'byref' only applies to parameters with pointer type!",
+           V);
     Assert(!Attrs.hasAttribute(Attribute::SwiftError),
            "Attribute 'swifterror' only applies to parameters "
            "with pointer type!",
@@ -1765,10 +1775,11 @@ void Verifier::verifyFunctionAttrs(FunctionType *FT, AttributeList Attrs,
           !RetAttrs.hasAttribute(Attribute::Returned) &&
           !RetAttrs.hasAttribute(Attribute::InAlloca) &&
           !RetAttrs.hasAttribute(Attribute::Preallocated) &&
+          !RetAttrs.hasAttribute(Attribute::ByRef) &&
           !RetAttrs.hasAttribute(Attribute::SwiftSelf) &&
           !RetAttrs.hasAttribute(Attribute::SwiftError)),
-         "Attributes 'byval', 'inalloca', 'preallocated', 'nest', 'sret', "
-         "'nocapture', 'nofree', "
+         "Attributes 'byval', 'inalloca', 'preallocated', 'byref', "
+         "'nest', 'sret', 'nocapture', 'nofree', "
          "'returned', 'swiftself', and 'swifterror' do not apply to return "
          "values!",
          V);
@@ -3174,17 +3185,19 @@ static bool isTypeCongruent(Type *L, Type *R) {
 
 static AttrBuilder getParameterABIAttributes(int I, AttributeList Attrs) {
   static const Attribute::AttrKind ABIAttrs[] = {
-      Attribute::StructRet,   Attribute::ByVal,     Attribute::InAlloca,
-      Attribute::InReg,       Attribute::SwiftSelf, Attribute::SwiftError,
-      Attribute::Preallocated};
+      Attribute::StructRet,    Attribute::ByVal,     Attribute::InAlloca,
+      Attribute::InReg,        Attribute::SwiftSelf, Attribute::SwiftError,
+      Attribute::Preallocated, Attribute::ByRef};
   AttrBuilder Copy;
   for (auto AK : ABIAttrs) {
     if (Attrs.hasParamAttribute(I, AK))
       Copy.addAttribute(AK);
   }
-  // `align` is ABI-affecting only in combination with `byval`.
+
+  // `align` is ABI-affecting only in combination with `byval` or `byref`.
   if (Attrs.hasParamAttribute(I, Attribute::Alignment) &&
-      Attrs.hasParamAttribute(I, Attribute::ByVal))
+      (Attrs.hasParamAttribute(I, Attribute::ByVal) ||
+       Attrs.hasParamAttribute(I, Attribute::ByRef)))
     Copy.addAlignmentAttr(Attrs.getParamAlignment(I));
   return Copy;
 }
diff --git a/lib/Transforms/Utils/CodeExtractor.cpp b/lib/Transforms/Utils/CodeExtractor.cpp
index 8cdbb9d3565..91036c510e4 100644
--- a/lib/Transforms/Utils/CodeExtractor.cpp
+++ b/lib/Transforms/Utils/CodeExtractor.cpp
@@ -895,6 +895,7 @@ Function *CodeExtractor::constructFunction(const ValueSet &inputs,
       case Attribute::WriteOnly:
       case Attribute::ZExt:
       case Attribute::ImmArg:
+      case Attribute::ByRef:
       case Attribute::EndAttrKinds:
       case Attribute::EmptyKey:
       case Attribute::TombstoneKey:
diff --git a/test/Assembler/byref-parse-error-0.ll b/test/Assembler/byref-parse-error-0.ll
new file mode 100644
index 00000000000..287cd8453a6
--- /dev/null
+++ b/test/Assembler/byref-parse-error-0.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:34: error: expected '('{{$}}
+define void @test_byref(i8* byref) {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-1.ll b/test/Assembler/byref-parse-error-1.ll
new file mode 100644
index 00000000000..3f189d340c9
--- /dev/null
+++ b/test/Assembler/byref-parse-error-1.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:35: error: expected type{{$}}
+define void @test_byref(i8* byref() {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-10.ll b/test/Assembler/byref-parse-error-10.ll
new file mode 100644
index 00000000000..55997e5ffe5
--- /dev/null
+++ b/test/Assembler/byref-parse-error-10.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:27: error: invalid use of parameter-only attribute on a function{{$}}
+define void @test_byref() byref(4) {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-2.ll b/test/Assembler/byref-parse-error-2.ll
new file mode 100644
index 00000000000..6037c3ac3c7
--- /dev/null
+++ b/test/Assembler/byref-parse-error-2.ll
@@ -0,0 +1,7 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:35: error: expected type{{$}}
+define void @test_byref(i8* byref()) {
+  ret void
+}
+
diff --git a/test/Assembler/byref-parse-error-3.ll b/test/Assembler/byref-parse-error-3.ll
new file mode 100644
index 00000000000..b86eab4e69c
--- /dev/null
+++ b/test/Assembler/byref-parse-error-3.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:35: error: expected type{{$}}
+define void @test_byref(i8* byref(-1)) {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-4.ll b/test/Assembler/byref-parse-error-4.ll
new file mode 100644
index 00000000000..6b6a6c25715
--- /dev/null
+++ b/test/Assembler/byref-parse-error-4.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:35: error: expected type{{$}}
+define void @test_byref(i8* byref(0)) {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-5.ll b/test/Assembler/byref-parse-error-5.ll
new file mode 100644
index 00000000000..c1a154805f4
--- /dev/null
+++ b/test/Assembler/byref-parse-error-5.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:8: error: invalid use of parameter-only attribute{{$}}
+define byref i8* @test_byref() {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-6.ll b/test/Assembler/byref-parse-error-6.ll
new file mode 100644
index 00000000000..c5ecf83596e
--- /dev/null
+++ b/test/Assembler/byref-parse-error-6.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:8: error: invalid use of parameter-only attribute{{$}}
+define byref 8 i8* @test_byref() {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-7.ll b/test/Assembler/byref-parse-error-7.ll
new file mode 100644
index 00000000000..9ac60af5348
--- /dev/null
+++ b/test/Assembler/byref-parse-error-7.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:8: error: invalid use of parameter-only attribute{{$}}
+define byref(8) i8* @test_byref() {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-8.ll b/test/Assembler/byref-parse-error-8.ll
new file mode 100644
index 00000000000..8f86b9f8afc
--- /dev/null
+++ b/test/Assembler/byref-parse-error-8.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:27: error: invalid use of parameter-only attribute on a function{{$}}
+define void @test_byref() byref {
+  ret void
+}
diff --git a/test/Assembler/byref-parse-error-9.ll b/test/Assembler/byref-parse-error-9.ll
new file mode 100644
index 00000000000..bc707062a2e
--- /dev/null
+++ b/test/Assembler/byref-parse-error-9.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as < %s 2>&1 | FileCheck %s
+
+; CHECK: <stdin>:[[@LINE+1]]:27: error: invalid use of parameter-only attribute on a function{{$}}
+define void @test_byref() byref=4 {
+  ret void
+}
diff --git a/test/Bitcode/attributes.ll b/test/Bitcode/attributes.ll
index fbbe4a80f31..409528230a7 100644
--- a/test/Bitcode/attributes.ll
+++ b/test/Bitcode/attributes.ll
@@ -392,6 +392,12 @@ define noundef i32 @f66(i32 noundef %a)
   ret i32 %a
 }
 
+; CHECK: define void @f67(i32* byref(i32) %a)
+define void @f67(i32* byref(i32) %a)
+{
+  ret void
+}
+
 ; CHECK: attributes #0 = { noreturn }
 ; CHECK: attributes #1 = { nounwind }
 ; CHECK: attributes #2 = { readnone }
diff --git a/test/CodeGen/X86/byref.ll b/test/CodeGen/X86/byref.ll
new file mode 100644
index 00000000000..90d5e9901b6
--- /dev/null
+++ b/test/CodeGen/X86/byref.ll
@@ -0,0 +1,20 @@
+; RUN: llc < %s -mtriple=i686-pc-win32 | FileCheck %s
+
+%Foo = type { i32, i32 }
+
+declare x86_stdcallcc void @foo_byref_stdcall_p(%Foo* byref(%Foo))
+declare x86_stdcallcc void @i(i32)
+
+; byref does not imply a stack copy, so this should append 4 bytes,
+; not 8.
+define void @stdcall(%Foo* %value) {
+; CHECK-LABEL: _stdcall:
+; CHECK: pushl 4(%esp)
+; CHECK: calll _foo_byref_stdcall_p@4
+  call x86_stdcallcc void @foo_byref_stdcall_p(%Foo* byref(%Foo) %value)
+; CHECK-NOT: %esp
+; CHECK: pushl
+; CHECK: calll _i@4
+  call x86_stdcallcc void @i(i32 0)
+  ret void
+}
diff --git a/test/Instrumentation/AddressSanitizer/byref-args.ll b/test/Instrumentation/AddressSanitizer/byref-args.ll
new file mode 100644
index 00000000000..df2eeb4c184
--- /dev/null
+++ b/test/Instrumentation/AddressSanitizer/byref-args.ll
@@ -0,0 +1,20 @@
+; RUN: opt < %s -asan -S | FileCheck %s
+
+; Test that for call instructions, the byref arguments are not
+; instrumented, as no copy is implied.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.bar = type { %struct.foo }
+%struct.foo = type { i8*, i8*, i8* }
+
+; CHECK-LABEL: @func2
+; CHECK-NEXT: tail call void @func1(
+; CHECK-NEXT: ret void
+define dso_local void @func2(%struct.foo* %foo) sanitize_address {
+  tail call void @func1(%struct.foo* byref(%struct.foo) align 8 %foo) #2
+  ret void
+}
+
+declare dso_local void @func1(%struct.foo* byref(%struct.foo) align 8)
diff --git a/test/Transforms/DeadArgElim/byref.ll b/test/Transforms/DeadArgElim/byref.ll
new file mode 100644
index 00000000000..95e839c04aa
--- /dev/null
+++ b/test/Transforms/DeadArgElim/byref.ll
@@ -0,0 +1,22 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -deadargelim -S | FileCheck %s
+
+declare void @sideeffect()
+
+define void @unused_byref_arg(i32* byref(i32) %dead_arg) {
+; CHECK-LABEL: @unused_byref_arg(
+; CHECK-NEXT:    tail call void @sideeffect()
+; CHECK-NEXT:    ret void
+;
+  tail call void @sideeffect()
+  ret void
+}
+
+define void @dont_replace_by_undef(i32* %ptr) {
+; CHECK-LABEL: @dont_replace_by_undef(
+; CHECK-NEXT:    call void @unused_byref_arg(i32* undef)
+; CHECK-NEXT:    ret void
+;
+  call void @unused_byref_arg(i32* %ptr)
+  ret void
+}
diff --git a/test/Transforms/Inline/byref-align.ll b/test/Transforms/Inline/byref-align.ll
new file mode 100644
index 00000000000..fb70db2af44
--- /dev/null
+++ b/test/Transforms/Inline/byref-align.ll
@@ -0,0 +1,52 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
+; RUN: opt -inline -preserve-alignment-assumptions-during-inlining -S < %s | FileCheck %s
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Test behavior of inserted alignment assumptions with byref. There is
+; no implied copy to a higher alignment, so an alignment assume call
+; should be inserted.
+define void @byref_callee(float* align(128) byref(float) nocapture %a, float* %b) #0 {
+; CHECK-LABEL: define {{[^@]+}}@byref_callee
+; CHECK-SAME: (float* nocapture byref(float) align 128 [[A:%.*]], float* [[B:%.*]]) #0
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[LOAD:%.*]] = load float, float* [[A]], align 4
+; CHECK-NEXT:    [[B_IDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 8
+; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[LOAD]], 2.000000e+00
+; CHECK-NEXT:    store float [[ADD]], float* [[B_IDX]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %load = load float, float* %a, align 4
+  %b.idx = getelementptr inbounds float, float* %b, i64 8
+  %add = fadd float %load, 2.0
+  store float %add, float* %b.idx, align 4
+  ret void
+}
+
+define void @byref_caller(float* nocapture align 64 %a, float* %b) #0 {
+; CHECK-LABEL: define {{[^@]+}}@byref_caller
+; CHECK-SAME: (float* nocapture align 64 [[A:%.*]], float* [[B:%.*]]) #0
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint float* [[A]] to i64
+; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 127
+; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
+; CHECK-NEXT:    call void @llvm.assume(i1 [[MASKCOND]])
+; CHECK-NEXT:    [[LOAD_I:%.*]] = load float, float* [[A]], align 4
+; CHECK-NEXT:    [[B_IDX_I:%.*]] = getelementptr inbounds float, float* [[B]], i64 8
+; CHECK-NEXT:    [[ADD_I:%.*]] = fadd float [[LOAD_I]], 2.000000e+00
+; CHECK-NEXT:    store float [[ADD_I]], float* [[B_IDX_I]], align 4
+; CHECK-NEXT:    [[CALLER_LOAD:%.*]] = load float, float* [[B]], align 4
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[A]], i64 7
+; CHECK-NEXT:    store float [[CALLER_LOAD]], float* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  call void @byref_callee(float* align(128) byref(float) %a, float* %b)
+  %caller.load = load float, float* %b, align 4
+  %arrayidx = getelementptr inbounds float, float* %a, i64 7
+  store float %caller.load, float* %arrayidx, align 4
+  ret void
+}
+
+attributes #0 = { nounwind uwtable }
diff --git a/test/Transforms/LowerConstantIntrinsics/objectsize_basic.ll b/test/Transforms/LowerConstantIntrinsics/objectsize_basic.ll
index ee5d792d532..ab59b8950d7 100644
--- a/test/Transforms/LowerConstantIntrinsics/objectsize_basic.ll
+++ b/test/Transforms/LowerConstantIntrinsics/objectsize_basic.ll
@@ -89,3 +89,11 @@ define i64 @test_objectsize_byval_arg([42 x i8]* byval([42 x i8]) %ptr) {
   %size = tail call i64 @llvm.objectsize.i64(i8* %cast, i1 true, i1 false, i1 false)
   ret i64 %size
 }
+
+; CHECK-LABEL: @test_objectsize_byref_arg(
+; CHECK: ret i64 42
+define i64 @test_objectsize_byref_arg([42 x i8]* byref([42 x i8]) %ptr) {
+  %cast = bitcast [42 x i8]* %ptr to i8*
+  %size = tail call i64 @llvm.objectsize.i64(i8* %cast, i1 true, i1 false, i1 false)
+  ret i64 %size
+}
diff --git a/test/Verifier/byref.ll b/test/Verifier/byref.ll
new file mode 100644
index 00000000000..5e7d5873a8d
--- /dev/null
+++ b/test/Verifier/byref.ll
@@ -0,0 +1,100 @@
+; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
+
+; CHECK: Attribute 'byref' type does not match parameter!
+; CHECK-NEXT: void (i32*)* @byref_mismatched_pointee_type0
+define void @byref_mismatched_pointee_type0(i32* byref(i8)) {
+  ret void
+}
+
+; CHECK: Attribute 'byref' type does not match parameter!
+; CHECK-NEXT: void (i8*)* @byref_mismatched_pointee_type1
+define void @byref_mismatched_pointee_type1(i8* byref(i32)) {
+  ret void
+}
+
+%opaque.ty = type opaque
+
+; CHECK: Attributes 'byval', 'byref', 'inalloca', and 'preallocated' do not support unsized types!
+; CHECK-NEXT: void (%opaque.ty*)* @byref_unsized
+define void @byref_unsized(%opaque.ty* byref(%opaque.ty)) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_byval
+define void @byref_byval(i32* byref(i32) byval(i32)) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_inalloca
+define void @byref_inalloca(i32* byref(i32) inalloca) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_preallocated
+define void @byref_preallocated(i32* byref(i32) preallocated(i32)) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_sret
+define void @byref_sret(i32* byref(i32) sret) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_inreg
+define void @byref_inreg(i32* byref(i32) inreg) {
+  ret void
+}
+
+; CHECK: Attributes 'byval', 'inalloca', 'preallocated', 'inreg', 'nest', 'byref', and 'sret' are incompatible!
+; CHECK-NEXT: void (i32*)* @byref_nest
+define void @byref_nest(i32* byref(i32) nest) {
+  ret void
+}
+
+; CHECK: Wrong types for attribute: inalloca nest noalias nocapture nonnull readnone readonly sret byref(i32) byval(i32) preallocated(i32) dereferenceable(1) dereferenceable_or_null(1)
+; CHECK-NEXT: void (i32)* @byref_non_pointer
+define void @byref_non_pointer(i32 byref(i32)) {
+  ret void
+}
+
+define void @byref_callee([64 x i8]* byref([64 x i8])) {
+  ret void
+}
+
+define void @no_byref_callee(i8*) {
+  ret void
+}
+
+; CHECK: cannot guarantee tail call due to mismatched ABI impacting function attributes
+; CHECK-NEXT: musttail call void @byref_callee([64 x i8]* byref([64 x i8]) %cast)
+; CHECK-NEXT: i8* %ptr
+define void @musttail_byref_caller(i8* %ptr) {
+  %cast = bitcast i8* %ptr to [64 x i8]*
+  musttail call void @byref_callee([64 x i8]* byref([64 x i8]) %cast)
+  ret void
+}
+
+; CHECK: cannot guarantee tail call due to mismatched ABI impacting function attributes
+; CHECK-NEXT: musttail call void @byref_callee([64 x i8]* %ptr)
+; CHECK-NEXT: [64 x i8]* %ptr
+define void @musttail_byref_callee([64 x i8]* byref([64 x i8]) %ptr) {
+  musttail call void @byref_callee([64 x i8]* %ptr)
+  ret void
+}
+
+define void @byref_callee_align32(i8* byref([64 x i8]) align 32) {
+  ret void
+}
+
+; CHECK: cannot guarantee tail call due to mismatched ABI impacting function attributes
+; CHECK-NEXT: musttail call void @byref_callee_align32(i8* byref([64 x i8]) align 32 %ptr)
+; CHECK-NEXT: i8* %ptr
+define void @musttail_byref_caller_mismatched_align(i8* byref([64 x i8]) align 16 %ptr) {
+  musttail call void @byref_callee_align32(i8* byref([64 x i8]) align 32 %ptr)
+  ret void
+}