[CUDA, FDO] Filter out profiling options from GPU-side compilations.

[tra]

clang/lib/Driver/ToolChains/Clang.cpp

5828–5848

@yaxunl Should I add isHipDevice here too? I don't think host-side profiling info is of much use for GPU compilation.

[yaxunl]

clang/lib/Driver/ToolChains/Clang.cpp

5828–5848

Yes pls do the same for HIP. Thanks.

[tra]

filter the options for AMD GPUs too.

[yaxunl]

LGTM. Thanks!

clang/lib/Driver/ToolChains/Clang.cpp

void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   // Check number of inputs for sanity. We need at least one input.
   assert(Inputs.size() >= 1 && "Must have at least one input.");
   // CUDA/HIP compilation may have multiple inputs (source file + results of
   // device-side compilations). OpenMP device jobs also take the host IR as a
   // second input. Module precompilation accepts a list of header files to
   // 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);
 
   // A header module compilation doesn't have a main input file, so invent a
   // fake one as a placeholder.
   const char *ModuleName = [&]{
     auto *ModuleNameArg = Args.getLastArg(options::OPT_fmodule_name_EQ);
     return ModuleNameArg ? ModuleNameArg->getValue() : "";
#endif
   UnwindTables = Args.hasFlag(options::OPT_funwind_tables,
                               options::OPT_fno_unwind_tables, UnwindTables);
   if (UnwindTables)
     CmdArgs.push_back("-munwind-tables");
 
   // 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 =
         getCPUName(HostArgs, *TC.getAuxTriple(), /*FromAs*/ false);
     if (!HostCPU.empty()) {
       CmdArgs.push_back("-aux-target-cpu");
       CmdArgs.push_back(Args.MakeArgString(HostCPU));
     }
if (IsCuda || IsHIP) {
     }
   }
 
   if (Arg *A = Args.getLastArg(options::OPT_fcf_protection_EQ)) {
     CmdArgs.push_back(
         Args.MakeArgString(Twine("-fcf-protection=") + A->getValue()));
   }
 
-  // Forward -f options with positive and negative forms; we translate
-  // these by hand.
+  // 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);
+          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);
     }
     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,
                     options::OPT_fno_assume_sane_operator_new))
     CmdArgs.push_back("-fno-assume-sane-operator-new");
 
   // -fblocks=0 is default.
   if (Args.hasFlag(options::OPT_fblocks, options::OPT_fno_blocks,

clang/test/Driver/clang_f_opts.c

 // CHECK-NO-REROLL-LOOPS-NOT: "-freroll-loops"
 
 // RUN: %clang -### -S -fprofile-sample-accurate %s 2>&1 | FileCheck -check-prefix=CHECK-PROFILE-SAMPLE-ACCURATE %s
 // CHECK-PROFILE-SAMPLE-ACCURATE: "-fprofile-sample-accurate"
 
 // 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"
 
 // RUN: %clang -### -S -fauto-profile=%S/Inputs/file.prof -fno-profile-sample-use %s 2>&1 | FileCheck -check-prefix=CHECK-NO-AUTO-PROFILE %s
 // RUN: %clang -### -S -fauto-profile=%S/Inputs/file.prof -fno-auto-profile %s 2>&1 | FileCheck -check-prefix=CHECK-NO-AUTO-PROFILE %s
 // CHECK-NO-AUTO-PROFILE-NOT: "-fprofile-sample-use={{.*}}/file.prof"
 
 // RUN: %clang -### -S -fauto-profile=%S/Inputs/file.prof -fno-profile-sample-use -fauto-profile %s 2>&1 | FileCheck -check-prefix=CHECK-AUTO-PROFILE %s