diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -8331,28 +8331,6 @@
                                "=" + *(FeatureIt + 1)));
     }
 
-    // Pass in the bitcode library to be linked during LTO.
-    for (auto &I :
-         llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) {
-      const ToolChain *TC = I.second;
-      if (!(TC->getTriple().isNVPTX() || TC->getTriple().isAMDGPU()))
-        continue;
-
-      const Driver &TCDriver = TC->getDriver();
-      const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
-      StringRef Arch = TCArgs.getLastArgValue(options::OPT_march_EQ);
-
-      ArgStringList BitcodeLibrary;
-      addOpenMPDeviceRTL(TCDriver, TCArgs, BitcodeLibrary, Arch,
-                         TC->getTriple());
-
-      if (!BitcodeLibrary.empty())
-        CmdArgs.push_back(Args.MakeArgString(
-            "-target-library=" +
-            Action::GetOffloadKindName(Action::OFK_OpenMP) + "-" +
-            TC->getTripleString() + "-" + Arch + "=" + BitcodeLibrary.back()));
-    }
-
     // Pass in the optimization level to use for LTO.
     if (const Arg *A = Args.getLastArg(options::OPT_O_Group)) {
       StringRef OOpt;
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
--- a/clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -736,6 +736,9 @@
   if (IsOffloadingHost)
     CmdArgs.push_back("-lomptarget");
 
+  if (IsOffloadingHost && TC.getDriver().isUsingLTO(/* IsOffload */ true))
+    CmdArgs.push_back("-lomptarget.devicertl");
+
   addArchSpecificRPath(TC, Args, CmdArgs);
 
   if (RTKind == Driver::OMPRT_OMP)
diff --git a/clang/test/Driver/openmp-offload-gpu-new.c b/clang/test/Driver/openmp-offload-gpu-new.c
--- a/clang/test/Driver/openmp-offload-gpu-new.c
+++ b/clang/test/Driver/openmp-offload-gpu-new.c
@@ -94,3 +94,8 @@
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
 // RUN:     --offload-device-only -E -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY-PP
 // CHECK-DEVICE-ONLY-PP: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.*]]"], output: "-"
+
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
+// RUN:     -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-LIBRARY %s
+
+// CHECK-LTO-LIBRARY: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl