Index: llvm/include/llvm/CodeGen/GlobalISel/IRTranslator.h
===================================================================
--- llvm/include/llvm/CodeGen/GlobalISel/IRTranslator.h
+++ llvm/include/llvm/CodeGen/GlobalISel/IRTranslator.h
@@ -523,6 +523,8 @@
 
   FunctionLoweringInfo FuncInfo;
 
+  const TargetLibraryInfo *LibInfo;
+
   // True when either the Target Machine specifies no optimizations or the
   // function has the optnone attribute.
   bool EnableOpts = false;
Index: llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
===================================================================
--- llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -18,6 +18,7 @@
 #include "llvm/Analysis/BranchProbabilityInfo.h"
 #include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/Analysis.h"
 #include "llvm/CodeGen/GlobalISel/CallLowering.h"
@@ -89,6 +90,7 @@
 
 INITIALIZE_PASS_BEGIN(IRTranslator, DEBUG_TYPE, "IRTranslator LLVM IR -> MI",
                 false, false)
+INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetPassConfig)
 INITIALIZE_PASS_DEPENDENCY(GISelCSEAnalysisWrapperPass)
 INITIALIZE_PASS_END(IRTranslator, DEBUG_TYPE, "IRTranslator LLVM IR -> MI",
@@ -153,6 +155,7 @@
 
 void IRTranslator::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<StackProtector>();
+  AU.addRequired<TargetLibraryInfoWrapperPass>();
   AU.addRequired<TargetPassConfig>();
   AU.addRequired<GISelCSEAnalysisWrapperPass>();
   getSelectionDAGFallbackAnalysisUsage(AU);
@@ -1780,6 +1783,8 @@
 
   assert(ID != Intrinsic::not_intrinsic && "unknown intrinsic");
 
+  if (ID == Intrinsic::memcpy && !LibInfo->has(LibFunc_memcpy))
+    return false;
   if (translateKnownIntrinsic(CI, ID, MIRBuilder))
     return true;
 
@@ -2413,6 +2418,8 @@
   SL = std::make_unique<GISelSwitchLowering>(this, FuncInfo);
   SL->init(TLI, TM, *DL);
 
+  LibInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
+
   EnableOpts = TM.getOptLevel() != CodeGenOpt::None && !skipFunction(F);
 
   assert(PendingPHIs.empty() && "stale PHIs");
Index: llvm/lib/CodeGen/SelectionDAG/FastISel.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/FastISel.cpp
+++ llvm/lib/CodeGen/SelectionDAG/FastISel.cpp
@@ -1509,6 +1509,10 @@
     return selectXRayCustomEvent(II);
   case Intrinsic::xray_typedevent:
     return selectXRayTypedEvent(II);
+  case Intrinsic::memcpy:
+    if (!LibInfo->has(LibFunc_memcpy))
+      return false;
+    break;
   }
 
   return fastLowerIntrinsicCall(II);
Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -27,6 +27,7 @@
 #include "llvm/Analysis/BlockFrequencyInfo.h"
 #include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
@@ -6434,7 +6435,7 @@
 
   // If we really need inline code and the target declined to provide it,
   // use a (potentially long) sequence of loads and stores.
-  if (AlwaysInline) {
+  if (AlwaysInline || (!LibInfo->has(LibFunc_memcpy) && ConstantSize)) {
     assert(ConstantSize && "AlwaysInline requires a constant size!");
     return getMemcpyLoadsAndStores(*this, dl, Chain, Dst, Src,
                                    ConstantSize->getZExtValue(), Alignment,
Index: llvm/test/CodeGen/AArch64/intrinsic-memcpy-nobuiltin.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AArch64/intrinsic-memcpy-nobuiltin.ll
@@ -0,0 +1,19 @@
+; RUN: llc -mtriple=aarch64-linux-gnu < %s -o - | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -O0 -global-isel < %s -o - | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -O0 -fast-isel   < %s -o - | FileCheck %s
+
+%struct.s = type { [512 x i8] }
+
+define void @copy(%struct.s* readonly %src, %struct.s* %dst) #0 {
+entry:
+; CHECK-LABEL: copy
+; CHECK-NOT: memcpy
+  %0 = getelementptr %struct.s, %struct.s* %dst, i64 0, i32 0, i64 0
+  %1 = getelementptr %struct.s, %struct.s* %src, i64 0, i32 0, i64 0
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 1 dereferenceable(512) %0, i8* nonnull align 1 dereferenceable(512) %1, i64 512, i1 false)
+  ret void
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg)
+
+attributes #0 = { "no-builtins" }