[OPENMP][NVPTX] Add options -f[no-]openmp-cuda-force-full-runtime.

Added options -f[no-]openmp-cuda-force-full-runtime to [not] force use
of the full runtime for OpenMP offloading to CUDA devices.

llvm-svn: 341073

3 files changed, 18 insertions, 4 deletions

diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
index 14845b58620..9dce947e17a 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -1218,7 +1218,8 @@ void CGOpenMPRuntimeNVPTX::emitSPMDEntryHeader(
   EST.ExitBB = CGF.createBasicBlock(".exit");
 
   // Initialize the OMP state in the runtime; called by all active threads.
-  bool RequiresFullRuntime = !supportsLightweightRuntime(CGF.getContext(), D);
+  bool RequiresFullRuntime = CGM.getLangOpts().OpenMPCUDAForceFullRuntime ||
+                             !supportsLightweightRuntime(CGF.getContext(), D);
   llvm::Value *Args[] = {
       getThreadLimit(CGF, /*IsInSPMDExecutionMode=*/true),
       /*RequiresOMPRuntime=*/
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 923c950b89e..68706588d99 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -4039,8 +4039,16 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
 
       // When in OpenMP offloading mode with NVPTX target, forward
       // cuda-mode flag
-      Args.AddLastArg(CmdArgs, options::OPT_fopenmp_cuda_mode,
-                      options::OPT_fno_openmp_cuda_mode);
+      if (Args.hasFlag(options::OPT_fopenmp_cuda_mode,
+                       options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
+        CmdArgs.push_back("-fopenmp-cuda-mode");
+
+      // When in OpenMP offloading mode with NVPTX target, check if full runtime
+      // is required.
+      if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,
+                       options::OPT_fno_openmp_cuda_force_full_runtime,
+                       /*Default=*/false))
+        CmdArgs.push_back("-fopenmp-cuda-force-full-runtime");
       break;
     default:
       // By default, if Clang doesn't know how to generate useful OpenMP code
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 97ac6c9dc91..b25d92bad6e 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -2677,10 +2677,15 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
           << Opts.OMPHostIRFile;
   }
 
-  // set CUDA mode for OpenMP target NVPTX if specified in options
+  // Set CUDA mode for OpenMP target NVPTX if specified in options
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && T.isNVPTX() &&
                         Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
+  // Set CUDA mode for OpenMP target NVPTX if specified in options
+  Opts.OpenMPCUDAForceFullRuntime =
+      Opts.OpenMPIsDevice && T.isNVPTX() &&
+      Args.hasArg(options::OPT_fopenmp_cuda_force_full_runtime);
+
   // Record whether the __DEPRECATED define was requested.
   Opts.Deprecated = Args.hasFlag(OPT_fdeprecated_macro,
                                  OPT_fno_deprecated_macro,