Index: llvm/include/llvm/Support/TargetOpcodes.def
===================================================================
--- llvm/include/llvm/Support/TargetOpcodes.def
+++ llvm/include/llvm/Support/TargetOpcodes.def
@@ -700,6 +700,9 @@
 /// llvm.memcpy intrinsic
 HANDLE_TARGET_OPCODE(G_MEMCPY)
 
+/// llvm.memcpy.inline intrinsic
+HANDLE_TARGET_OPCODE(G_MEMCPY_INLINE)
+
 /// llvm.memmove intrinsic
 HANDLE_TARGET_OPCODE(G_MEMMOVE)
 
Index: llvm/include/llvm/Target/GenericOpcodes.td
===================================================================
--- llvm/include/llvm/Target/GenericOpcodes.td
+++ llvm/include/llvm/Target/GenericOpcodes.td
@@ -1285,6 +1285,14 @@
   let mayStore = 1;
 }
 
+def G_MEMCPY_INLINE : GenericInstruction {
+  let OutOperandList = (outs);
+  let InOperandList = (ins ptype0:$dst_addr, ptype1:$src_addr, type2:$size, untyped_imm_0:$tailcall);
+  let hasSideEffects = 0;
+  let mayLoad = 1;
+  let mayStore = 1;
+}
+
 def G_MEMMOVE : GenericInstruction {
   let OutOperandList = (outs);
   let InOperandList = (ins ptype0:$dst_addr, ptype1:$src_addr, type2:$size, untyped_imm_0:$tailcall);
Index: llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
===================================================================
--- llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -1731,6 +1731,8 @@
     return true;
   case Intrinsic::memcpy:
     return translateMemFunc(CI, MIRBuilder, TargetOpcode::G_MEMCPY);
+  case Intrinsic::memcpy_inline:
+    return translateMemFunc(CI, MIRBuilder, TargetOpcode::G_MEMCPY_INLINE);
   case Intrinsic::memmove:
     return translateMemFunc(CI, MIRBuilder, TargetOpcode::G_MEMMOVE);
   case Intrinsic::memset:
Index: llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
===================================================================
--- llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -744,6 +744,8 @@
     MI.eraseFromParent();
     return Result;
   }
+  case TargetOpcode::G_MEMCPY_INLINE:
+    llvm_unreachable("emitting a libcall is illegal for memcpy_inline");
   }
 
   MI.eraseFromParent();
Index: llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-memory-intrinsics.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-memory-intrinsics.ll
+++ llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-memory-intrinsics.ll
@@ -109,6 +109,23 @@
   ret void
 }
 
+define void @test_memcpy_inline_p1_p3_i32(i8 addrspace(1)* %dst, i8 addrspace(3)* %src) {
+  ; CHECK-LABEL: name: test_memcpy_inline_p1_p3_i32
+  ; CHECK: bb.1 (%ir-block.0):
+  ; CHECK:   liveins: $vgpr0, $vgpr1, $vgpr2, $sgpr30_sgpr31
+  ; CHECK:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+  ; CHECK:   [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+  ; CHECK:   [[COPY2:%[0-9]+]]:_(p3) = COPY $vgpr2
+  ; CHECK:   [[COPY3:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
+  ; CHECK:   [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
+  ; CHECK:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 256
+  ; CHECK:   G_MEMCPY_INLINE [[MV]](p1), [[COPY2]](p3), [[C]](s32), 0 :: (store 1 into %ir.dst, addrspace 1), (load 1 from %ir.src, addrspace 3)
+  ; CHECK:   [[COPY4:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY3]]
+  ; CHECK:   S_SETPC_B64_return [[COPY4]]
+  call void @llvm.memcpy.inline.p1i8.p3i8.i32(i8 addrspace(1)* %dst, i8 addrspace(3)* %src, i32 256, i1 false)
+  ret void
+}
+
 define void @test_memmove_p1_p3_i64(i8 addrspace(1)* %dst, i8 addrspace(3)* %src) {
   ; CHECK-LABEL: name: test_memmove_p1_p3_i64
   ; CHECK: bb.1 (%ir-block.0):
@@ -274,6 +291,9 @@
 declare void @llvm.memcpy.p3i8.p1i8.i64(i8 addrspace(3)* noalias nocapture writeonly, i8 addrspace(1)* noalias nocapture readonly, i64, i1 immarg) #0
 declare void @llvm.memcpy.p3i8.p1i8.i32(i8 addrspace(3)* noalias nocapture writeonly, i8 addrspace(1)* noalias nocapture readonly, i32, i1 immarg) #0
 declare void @llvm.memcpy.p3i8.p1i8.i16(i8 addrspace(3)* noalias nocapture writeonly, i8 addrspace(1)* noalias nocapture readonly, i16, i1 immarg) #0
+
+declare void @llvm.memcpy.inline.p1i8.p3i8.i32(i8 addrspace(1)* noalias nocapture writeonly, i8 addrspace(3)* noalias nocapture readonly, i32, i1 immarg) #0
+
 declare void @llvm.memmove.p1i8.p3i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(3)* nocapture readonly, i64, i1 immarg) #0
 declare void @llvm.memmove.p1i8.p3i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(3)* nocapture readonly, i32, i1 immarg) #0
 declare void @llvm.memmove.p1i8.p3i8.i16(i8 addrspace(1)* nocapture, i8 addrspace(3)* nocapture readonly, i16, i1 immarg) #0