diff --git a/lib/Driver/ToolChains/Clang.cpp b/lib/Driver/ToolChains/Clang.cpp
index 22f4ad1..0745560 100644
--- a/lib/Driver/ToolChains/Clang.cpp
+++ b/lib/Driver/ToolChains/Clang.cpp
@@ -4159,7 +4159,9 @@
   // include as part of the module. All other jobs are expected to have exactly
   // one input.
   bool IsCuda = JA.isOffloading(Action::OFK_Cuda);
+  bool IsCudaDevice = JA.isDeviceOffloading(Action::OFK_Cuda);
   bool IsHIP = JA.isOffloading(Action::OFK_HIP);
+  bool IsHIPDevice = JA.isDeviceOffloading(Action::OFK_HIP);
   bool IsOpenMPDevice = JA.isDeviceOffloading(Action::OFK_OpenMP);
   bool IsHeaderModulePrecompile = isa<HeaderModulePrecompileJobAction>(JA);
 
@@ -5003,8 +5005,7 @@
   // Prepare `-aux-target-cpu` and `-aux-target-feature` unless
   // `--gpu-use-aux-triple-only` is specified.
   if (!Args.getLastArg(options::OPT_gpu_use_aux_triple_only) &&
-      ((IsCuda && JA.isDeviceOffloading(Action::OFK_Cuda)) ||
-       (IsHIP && JA.isDeviceOffloading(Action::OFK_HIP)))) {
+      (IsCudaDevice || IsHIPDevice)) {
     const ArgList &HostArgs =
         C.getArgsForToolChain(nullptr, StringRef(), Action::OFK_None);
     std::string HostCPU =
@@ -5824,29 +5825,32 @@
         Args.MakeArgString(Twine("-fcf-protection=") + A->getValue()));
   }
 
-  // Forward -f options with positive and negative forms; we translate
-  // these by hand.
-  if (Arg *A = getLastProfileSampleUseArg(Args)) {
-    auto *PGOArg = Args.getLastArg(
-        options::OPT_fprofile_generate, options::OPT_fprofile_generate_EQ,
-        options::OPT_fcs_profile_generate, options::OPT_fcs_profile_generate_EQ,
-        options::OPT_fprofile_use, options::OPT_fprofile_use_EQ);
-    if (PGOArg)
-      D.Diag(diag::err_drv_argument_not_allowed_with)
-          << "SampleUse with PGO options";
+  // Forward -f options with positive and negative forms; we translate these by
+  // hand.  Do not propagate PGO options to the GPU-side compilations as the
+  // profile info is for the host-side compilation only.
+  if (!(IsCudaDevice || IsHIPDevice)) {
+    if (Arg *A = getLastProfileSampleUseArg(Args)) {
+      auto *PGOArg = Args.getLastArg(
+          options::OPT_fprofile_generate, options::OPT_fprofile_generate_EQ,
+          options::OPT_fcs_profile_generate,
+          options::OPT_fcs_profile_generate_EQ, options::OPT_fprofile_use,
+          options::OPT_fprofile_use_EQ);
+      if (PGOArg)
+        D.Diag(diag::err_drv_argument_not_allowed_with)
+            << "SampleUse with PGO options";
 
-    StringRef fname = A->getValue();
-    if (!llvm::sys::fs::exists(fname))
-      D.Diag(diag::err_drv_no_such_file) << fname;
-    else
-      A->render(Args, CmdArgs);
+      StringRef fname = A->getValue();
+      if (!llvm::sys::fs::exists(fname))
+        D.Diag(diag::err_drv_no_such_file) << fname;
+      else
+        A->render(Args, CmdArgs);
+    }
+    Args.AddLastArg(CmdArgs, options::OPT_fprofile_remapping_file_EQ);
+
+    if (Args.hasFlag(options::OPT_fpseudo_probe_for_profiling,
+                     options::OPT_fno_pseudo_probe_for_profiling, false))
+      CmdArgs.push_back("-fpseudo-probe-for-profiling");
   }
-  Args.AddLastArg(CmdArgs, options::OPT_fprofile_remapping_file_EQ);
-
-  if (Args.hasFlag(options::OPT_fpseudo_probe_for_profiling,
-                   options::OPT_fno_pseudo_probe_for_profiling, false))
-    CmdArgs.push_back("-fpseudo-probe-for-profiling");
-
   RenderBuiltinOptions(TC, RawTriple, Args, CmdArgs);
 
   if (!Args.hasFlag(options::OPT_fassume_sane_operator_new,
diff --git a/test/Driver/clang_f_opts.c b/test/Driver/clang_f_opts.c
index 9da9f5e..6077058 100644
--- a/test/Driver/clang_f_opts.c
+++ b/test/Driver/clang_f_opts.c
@@ -58,6 +58,19 @@
 // RUN: %clang -### -S -fprofile-sample-use=%S/Inputs/file.prof %s 2>&1 | FileCheck -check-prefix=CHECK-SAMPLE-PROFILE %s
 // CHECK-SAMPLE-PROFILE: "-fprofile-sample-use={{.*}}/file.prof"
 
+//
+// RUN: %clang -### -x cuda -nocudainc -nocudalib \
+// RUN:    -c -fprofile-sample-use=%S/Inputs/file.prof %s 2>&1 \
+// RUN:  | FileCheck -check-prefix=CHECK-CUDA-SAMPLE-PROFILE %s
+// -fprofile-sample-use should not be passed to the GPU compilation
+// CHECK-CUDA-SAMPLE-PROFILE: "-cc1"
+// CHECK-CUDA-SAMPLE-PROFILE-SAME: "-triple" "nvptx
+// CHECK-CUDA-SAMPLE-PROFILE-NOT: "-fprofile-sample-use={{.*}}/file.prof"
+// Host compilation should still have the option.
+// CHECK-CUDA-SAMPLE-PROFILE: "-cc1"
+// CHECK-CUDA-SAMPLE-PROFILE-SAME: "-fprofile-sample-use={{.*}}/file.prof"
+
+
 // RUN: %clang -### -S -fauto-profile=%S/Inputs/file.prof %s 2>&1 | FileCheck -check-prefix=CHECK-AUTO-PROFILE %s
 // CHECK-AUTO-PROFILE: "-fprofile-sample-use={{.*}}/file.prof"