[clang] bc768aa - [OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

[via cfe-commits]

Author: Joseph Huber
Date: 2021-06-22T15:10:19-04:00
New Revision: bc768aac2e4ebc3613f1e5601b15f663a6385044

URL: https://github.com/llvm/llvm-project/commit/bc768aac2e4ebc3613f1e5601b15f663a6385044
DIFF: https://github.com/llvm/llvm-project/commit/bc768aac2e4ebc3613f1e5601b15f663a6385044.diff

LOG: [OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

Summary:
The changes introduced in D97680 turns this command line option into a no-op so
it can be removed entirely.

Reviewed By: tianshilei1992

Differential Revision: https://reviews.llvm.org/D102940

Added: 
    

Modified: 
    clang/include/clang/Basic/LangOptions.def
    clang/include/clang/Driver/Options.td
    clang/lib/Driver/ToolChains/Clang.cpp
    clang/lib/Frontend/CompilerInvocation.cpp

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Basic/LangOptions.def b/clang/include/clang/Basic/LangOptions.def
index fff5fe23dc80d..32429f019064d 100644
--- a/clang/include/clang/Basic/LangOptions.def
+++ b/clang/include/clang/Basic/LangOptions.def
@@ -237,7 +237,6 @@ LANGOPT(OpenMPCUDANumSMs  , 32, 0, "Number of SMs for CUDA devices.")
 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(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
-LANGOPT(OpenMPCUDATargetParallel, 1, 0, "Support parallel execution of target region on Cuda-based devices.")
 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")

diff  --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index ede7405964ff3..016a565e77a57 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2363,12 +2363,6 @@ def fopenmp_cuda_teams_reduction_recs_num_EQ : Joined<["-"], "fopenmp-cuda-teams
 defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
   LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option]>, NegFlag<SetFalse>, BothFlags<[NoArgumentUnused, HelpHidden]>>;
-def fopenmp_cuda_parallel_target_regions : Flag<["-"], "fopenmp-cuda-parallel-target-regions">, Group<f_Group>,
-  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support parallel execution of target regions on Cuda-based devices.">;
-def fno_openmp_cuda_parallel_target_regions : Flag<["-"], "fno-openmp-cuda-parallel-target-regions">, Group<f_Group>,
-  Flags<[NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support only serial execution of target regions on Cuda-based devices.">;
 def static_openmp: Flag<["-"], "static-openmp">,
   HelpText<"Use the static host OpenMP runtime while linking.">;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;

diff  --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index f6e3447eccb02..eafe5de8eedb8 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5714,13 +5714,6 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                        options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
         CmdArgs.push_back("-fopenmp-cuda-mode");
 
-      // When in OpenMP offloading mode with NVPTX target, forward
-      // cuda-parallel-target-regions flag
-      if (Args.hasFlag(options::OPT_fopenmp_cuda_parallel_target_regions,
-                       options::OPT_fno_openmp_cuda_parallel_target_regions,
-                       /*Default=*/true))
-        CmdArgs.push_back("-fopenmp-cuda-parallel-target-regions");
-
       // When in OpenMP offloading mode with NVPTX target, check if full runtime
       // is required.
       if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,

diff  --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 54904443958ac..5bbb954c7d4d7 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -3475,9 +3475,6 @@ void CompilerInvocation::GenerateLangArgs(const LangOptions &Opts,
   if (Opts.OpenMPCUDAMode)
     GenerateArg(Args, OPT_fopenmp_cuda_mode, SA);
 
-  if (Opts.OpenMPCUDATargetParallel)
-    GenerateArg(Args, OPT_fopenmp_cuda_parallel_target_regions, SA);
-
   if (Opts.OpenMPCUDAForceFullRuntime)
     GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
 
@@ -3910,12 +3907,6 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
                         Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
-  // Set CUDA support for parallel execution of target regions for OpenMP target
-  // NVPTX/AMDGCN if specified in options.
-  Opts.OpenMPCUDATargetParallel =
-      Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
-      Args.hasArg(options::OPT_fopenmp_cuda_parallel_target_regions);
-
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAForceFullRuntime =
       Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&