[OpenMP] Don't set device runtime debugging flags if using '-nogpulib'

[jhuber6]

Summary

We use globals to configure debugging at compile-time for the device
runtime. Because these are only used by the OpenMP runtime we shouldn't
define them if we aren't using the device runtime. When a user passes in
'-nogpulib' this indicates that we are not using the device runtime, so
we should check for the precense of this flag and not emit these globals
if used.

[jdoerfert]

Not actually tested, is it?

[jhuber6]

In D125314#3503453, @jdoerfert wrote:

Not actually tested, is it?

Should be, we already have a test for not emitting these when the host-or file path is empty, I just reused the same tests but set the flags to use nogpulib instead

[jdoerfert]

LG

clang/include/clang/Basic/LangOptions.def

 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA devices.")
 LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records in the intermediate reduction buffer used for the teams reductions.")
 LANGOPT(OpenMPTargetDebug , 32, 0, "Enable debugging in the OpenMP offloading device RTL")
 LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
 LANGOPT(OpenMPThreadSubscription  , 1, 0, "Assume work-shared loops do not have more iterations than participating threads.")
 LANGOPT(OpenMPTeamSubscription  , 1, 0, "Assume distributed loops do not have more iterations than participating teams.")
 LANGOPT(OpenMPNoThreadState  , 1, 0, "Assume that no thread in a parallel region will modify an ICV.")
 LANGOPT(OpenMPOffloadMandatory  , 1, 0, "Assert that offloading is mandatory and do not create a host fallback.")
+LANGOPT(NoGPULib  , 1, 0, "Indicate a build without the standard GPU libraries.")
 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(HLSL, 1, 0, "HLSL")
 ENUM_LANGOPT(HLSLVersion, HLSLLangStd, 16, HLSL_Unset, "HLSL Version")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")
 LANGOPT(CUDAAllowVariadicFunctions, 1, 0, "allowing variadic functions in CUDA device code")
 LANGOPT(CUDAHostDeviceConstexpr, 1, 1, "treating unattributed constexpr functions as __host__ __device__")

clang/include/clang/Driver/Options.td

 def nobuiltininc : Flag<["-"], "nobuiltininc">, Flags<[CC1Option, CoreOption]>,
   HelpText<"Disable builtin #include directories">,
   MarshallingInfoNegativeFlag<HeaderSearchOpts<"UseBuiltinIncludes">>;
 def nogpuinc : Flag<["-"], "nogpuinc">, HelpText<"Do not add include paths for CUDA/HIP and"
   " do not include the default CUDA/HIP wrapper headers">;
 def nohipwrapperinc : Flag<["-"], "nohipwrapperinc">,
   HelpText<"Do not include the default HIP wrapper headers and include paths">;
 def : Flag<["-"], "nocudainc">, Alias<nogpuinc>;
-def nogpulib : Flag<["-"], "nogpulib">,
-  HelpText<"Do not link device library for CUDA/HIP device compilation">;
+def nogpulib : Flag<["-"], "nogpulib">, MarshallingInfoFlag<LangOpts<"NoGPULib">>,
+  Flags<[CC1Option]>, HelpText<"Do not link device library for CUDA/HIP device compilation">;
 def : Flag<["-"], "nocudalib">, Alias<nogpulib>;
 def nodefaultlibs : Flag<["-"], "nodefaultlibs">;
 def nofixprebinding : Flag<["-"], "nofixprebinding">;
 def nolibc : Flag<["-"], "nolibc">;
 def nomultidefs : Flag<["-"], "nomultidefs">;
 def nopie : Flag<["-"], "nopie">;
 def no_pie : Flag<["-"], "no-pie">, Alias<nopie>;
 def noprebind : Flag<["-"], "noprebind">;

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

 }
 
 CGOpenMPRuntimeGPU::CGOpenMPRuntimeGPU(CodeGenModule &CGM)
     : CGOpenMPRuntime(CGM, "_", "$") {
   if (!CGM.getLangOpts().OpenMPIsDevice)
     llvm_unreachable("OpenMP can only handle device code.");
 
   llvm::OpenMPIRBuilder &OMPBuilder = getOMPBuilder();
-  if (!CGM.getLangOpts().OMPHostIRFile.empty()) {
-    OMPBuilder.createGlobalFlag(CGM.getLangOpts().OpenMPTargetDebug,
-                                "__omp_rtl_debug_kind");
-    OMPBuilder.createGlobalFlag(CGM.getLangOpts().OpenMPTeamSubscription,
-                                "__omp_rtl_assume_teams_oversubscription");
-    OMPBuilder.createGlobalFlag(CGM.getLangOpts().OpenMPThreadSubscription,
-                                "__omp_rtl_assume_threads_oversubscription");
-    OMPBuilder.createGlobalFlag(CGM.getLangOpts().OpenMPNoThreadState,
-                                "__omp_rtl_assume_no_thread_state");
-  }
-}
+  if (CGM.getLangOpts().NoGPULib || CGM.getLangOpts().OMPHostIRFile.empty())
+    return;
+
 
 void CGOpenMPRuntimeGPU::emitProcBindClause(CodeGenFunction &CGF,
                                               ProcBindKind ProcBind,
                                               SourceLocation Loc) {
   // Do nothing in case of SPMD mode and L0 parallel.
   if (getExecutionMode() == CGOpenMPRuntimeGPU::EM_SPMD)
     return;
 

clang/lib/Driver/ToolChains/Clang.cpp

if (IsCuda || IsHIP) {
     if (Args.hasFlag(options::OPT_fgpu_exclude_wrong_side_overloads,
                      options::OPT_fno_gpu_exclude_wrong_side_overloads,
                      false)) {
       CmdArgs.push_back("-fgpu-exclude-wrong-side-overloads");
       CmdArgs.push_back("-fgpu-defer-diag");
     }
   }
 
+  // Forward -nogpulib to -cc1.
+  if (Args.hasArg(options::OPT_nogpulib))
+    CmdArgs.push_back("-nogpulib");
+
   if (Arg *A = Args.getLastArg(options::OPT_fcf_protection_EQ)) {
     CmdArgs.push_back(
         Args.MakeArgString(Twine("-fcf-protection=") + A->getValue()));
   }
 
   if (IsUsingLTO)
     Args.AddLastArg(CmdArgs, options::OPT_mibt_seal);
 

clang/test/OpenMP/target_globals_codegen.cpp

 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals --global-value-regex "__omp_rtl_"
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-target-debug -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-target-debug=111 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-EQ
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-DEFAULT
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-assume-threads-oversubscription -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-THREADS
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-assume-teams-oversubscription -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-TEAMS
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-assume-no-thread-state -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-STATE
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -nogpulib -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=CHECK-RUNTIME
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-assume-teams-oversubscription -fopenmp-is-device -o - | FileCheck %s --check-prefix=CHECK-RUNTIME
 // expected-no-diagnostics
 
 #ifndef HEADER
 #define HEADER
 
 //.
 // CHECK: @__omp_rtl_debug_kind = weak_odr hidden constant i32 1