Index: lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -4552,6 +4552,16 @@
   return DAG.getNode(ISD::TokenFactor, dl, MVT::Other, OutChains);
 }
 
+static void checkAddrSpaceIsValidForLibcall(const TargetLowering *TLI,
+                                            unsigned AS) {
+  // Lowering memcpy / memset / memmove intrinsics to calls is only valid if all
+  // pointer operands can be losslessly bitcasted to pointers of address space 0
+  if (AS != 0 && !TLI->isNoopAddrSpaceCast(AS, 0)) {
+    report_fatal_error("cannot lower memory intrinsic in address space " +
+                       Twine(AS));
+  }
+}
+
 SDValue SelectionDAG::getMemcpy(SDValue Chain, SDLoc dl, SDValue Dst,
                                 SDValue Src, SDValue Size,
                                 unsigned Align, bool isVol, bool AlwaysInline,
@@ -4593,6 +4603,9 @@
                                    true, DstPtrInfo, SrcPtrInfo);
   }
 
+  checkAddrSpaceIsValidForLibcall(TLI, DstPtrInfo.getAddrSpace());
+  checkAddrSpaceIsValidForLibcall(TLI, SrcPtrInfo.getAddrSpace());
+
   // FIXME: If the memcpy is volatile (isVol), lowering it to a plain libc
   // memcpy is not guaranteed to be safe. libc memcpys aren't required to
   // respect volatile, so they may do things like read or write memory
@@ -4654,6 +4667,9 @@
       return Result;
   }
 
+  checkAddrSpaceIsValidForLibcall(TLI, DstPtrInfo.getAddrSpace());
+  checkAddrSpaceIsValidForLibcall(TLI, SrcPtrInfo.getAddrSpace());
+
   // FIXME: If the memmove is volatile, lowering it to plain libc memmove may
   // not be safe.  See memcpy above for more details.
 
@@ -4711,6 +4727,8 @@
       return Result;
   }
 
+  checkAddrSpaceIsValidForLibcall(TLI, DstPtrInfo.getAddrSpace());
+
   // Emit a library call.
   Type *IntPtrTy = getDataLayout().getIntPtrType(*getContext());
   TargetLowering::ArgListTy Args;
Index: lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4369,14 +4369,6 @@
   case Intrinsic::longjmp:
     return &"_longjmp"[!TLI.usesUnderscoreLongJmp()];
   case Intrinsic::memcpy: {
-    // FIXME: this definition of "user defined address space" is x86-specific
-    // Assert for address < 256 since we support only user defined address
-    // spaces.
-    assert(cast<PointerType>(I.getArgOperand(0)->getType())->getAddressSpace()
-           < 256 &&
-           cast<PointerType>(I.getArgOperand(1)->getType())->getAddressSpace()
-           < 256 &&
-           "Unknown address space");
     SDValue Op1 = getValue(I.getArgOperand(0));
     SDValue Op2 = getValue(I.getArgOperand(1));
     SDValue Op3 = getValue(I.getArgOperand(2));
@@ -4393,12 +4385,6 @@
     return nullptr;
   }
   case Intrinsic::memset: {
-    // FIXME: this definition of "user defined address space" is x86-specific
-    // Assert for address < 256 since we support only user defined address
-    // spaces.
-    assert(cast<PointerType>(I.getArgOperand(0)->getType())->getAddressSpace()
-           < 256 &&
-           "Unknown address space");
     SDValue Op1 = getValue(I.getArgOperand(0));
     SDValue Op2 = getValue(I.getArgOperand(1));
     SDValue Op3 = getValue(I.getArgOperand(2));
@@ -4413,14 +4399,6 @@
     return nullptr;
   }
   case Intrinsic::memmove: {
-    // FIXME: this definition of "user defined address space" is x86-specific
-    // Assert for address < 256 since we support only user defined address
-    // spaces.
-    assert(cast<PointerType>(I.getArgOperand(0)->getType())->getAddressSpace()
-           < 256 &&
-           cast<PointerType>(I.getArgOperand(1)->getType())->getAddressSpace()
-           < 256 &&
-           "Unknown address space");
     SDValue Op1 = getValue(I.getArgOperand(0));
     SDValue Op2 = getValue(I.getArgOperand(1));
     SDValue Op3 = getValue(I.getArgOperand(2));
Index: test/CodeGen/X86/memcpy.ll
===================================================================
--- test/CodeGen/X86/memcpy.ll
+++ test/CodeGen/X86/memcpy.ll
@@ -2,6 +2,7 @@
 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=DARWIN
 
 declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p256i8.p256i8.i64(i8 addrspace(256)* nocapture, i8 addrspace(256)* nocapture, i64, i32, i1) nounwind
 
 
 ; Variable memcpy's should lower to calls.
@@ -138,3 +139,15 @@
   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 17, i32 0, i1 false)
   ret void
 }
+
+; Memcpys from / to address space 256 should be lowered to appropriate loads /
+; stores if small enough.
+define void @addrspace256(i8 addrspace(256)* %a, i8 addrspace(256)* %b) nounwind {
+  tail call void @llvm.memcpy.p256i8.p256i8.i64(i8 addrspace(256)* %a, i8 addrspace(256)* %b, i64 16, i32 8, i1 false)
+  ret void
+; LINUX-LABEL: addrspace256:
+; LINUX: movq %gs:
+; LINUX: movq %gs:
+; LINUX: movq {{.*}}, %gs:
+; LINUX: movq {{.*}}, %gs:
+}