diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -672,6 +672,9 @@
 def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
   Flags<[CC1Option]>,
   HelpText<"Default max threads per block for kernel launch bounds for HIP">;
+def gpu_instrument_lib_EQ : Joined<["--"], "gpu-instrument-lib=">,
+  HelpText<"Instrument device library for HIP, which is a LLVM bitcode containing "
+  "__cyg_profile_func_enter and __cyg_profile_func_exit">;
 def libomptarget_nvptx_path_EQ : Joined<["--"], "libomptarget-nvptx-path=">, Group<i_Group>,
   HelpText<"Path to libomptarget-nvptx libraries">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
diff --git a/clang/lib/Driver/ToolChains/HIP.cpp b/clang/lib/Driver/ToolChains/HIP.cpp
--- a/clang/lib/Driver/ToolChains/HIP.cpp
+++ b/clang/lib/Driver/ToolChains/HIP.cpp
@@ -330,6 +330,17 @@
     RocmInstallation.addCommonBitcodeLibCC1Args(
       DriverArgs, CC1Args, LibDeviceFile, Wave64, DAZ, FiniteOnly,
       UnsafeMathOpt, FastRelaxedMath, CorrectSqrt);
+
+    // Add instrument lib.
+    auto InstLib =
+        DriverArgs.getLastArgValue(options::OPT_gpu_instrument_lib_EQ);
+    if (InstLib.empty())
+      return;
+    if (llvm::sys::fs::exists(InstLib)) {
+      CC1Args.push_back("-mlink-builtin-bitcode");
+      CC1Args.push_back(DriverArgs.MakeArgString(InstLib));
+    } else
+      getDriver().Diag(diag::err_drv_no_such_file) << InstLib;
   }
 }
 
diff --git a/clang/test/Driver/Inputs/hip_multiple_inputs/instrument.bc b/clang/test/Driver/Inputs/hip_multiple_inputs/instrument.bc
new file mode 100644
diff --git a/clang/test/Driver/hip-device-libs.hip b/clang/test/Driver/hip-device-libs.hip
--- a/clang/test/Driver/hip-device-libs.hip
+++ b/clang/test/Driver/hip-device-libs.hip
@@ -105,6 +105,15 @@
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s --check-prefixes=ALL
 
+// Test --gpu-instrument-lib
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx900 \
+// RUN:   --rocm-path=%S/Inputs/rocm \
+// RUN:   --gpu-instrument-lib=%S/Inputs/hip_multiple_inputs/instrument.bc \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=ALL,INST
+
+// ALL-NOT: error:
 // ALL: {{"[^"]*clang[^"]*"}}
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}hip.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}ocml.bc"
@@ -118,3 +127,4 @@
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_correctly_rounded_sqrt_on.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_on.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_isa_version_{{[0-9]+}}.bc"
+// INST-SAME: "-mlink-builtin-bitcode" "{{.*}}instrument.bc"