[Clang] Accept and forward `-fconvergent-functions` in the driver

[jhuber6]

Summary

Currently the -fconvergent-functions option is primarily used by GPU
toolchains to enforce convergent operations in line with the semantics.
This option previously was only supported via -Xclang and would show
up as unused if passed to the driver. This patch allows the driver to
forward it. This is mostly useful for users wishing to target GPU
toolchains directly via --target= without an offloading runtime.

[JonChesterfield]

Can't reasonably see the semantic change between all the whitespace reformat, please split those two. E.g. use git-clang-format to only fix formatting in the part you're changing, or commit a clang-format only change first and then rebase this.

[jhuber6]

In D149019#4290573, @JonChesterfield wrote:

Can't reasonably see the semantic change between all the whitespace reformat, please split those two. E.g. use git-clang-format to only fix formatting in the part you're changing, or commit a clang-format only change first and then rebase this.

Sorry that was an accidental format, I'll fix it.

[jhuber6]

Fix formatting

[JonChesterfield]

Thanks!

[MaskRay]

clang/include/clang/Driver/Options.td

972

Only one of the positive and negative options need to be a cc1 option.

clang/lib/Driver/ToolChains/Clang.cpp

5703

Only pass the positive option as cc1 option.

[jhuber6]

Remove cc1 negative option

clang/include/clang/Driver/Options.td

 def coverage : Flag<["-", "--"], "coverage">, Group<Link_Group>, Flags<[CoreOption]>;
 def cpp_precomp : Flag<["-"], "cpp-precomp">, Group<clang_ignored_f_Group>;
 def current__version : JoinedOrSeparate<["-"], "current_version">;
 def cxx_isystem : JoinedOrSeparate<["-"], "cxx-isystem">, Group<clang_i_Group>,
   HelpText<"Add directory to the C++ SYSTEM include search path">, Flags<[CC1Option]>,
   MetaVarName<"<directory>">;
 def c : Flag<["-"], "c">, Flags<[NoXarchOption, FlangOption]>, Group<Action_Group>,
   HelpText<"Only run preprocess, compile, and assemble steps">;
-def fconvergent_functions : Flag<["-"], "fconvergent-functions">, Group<f_Group>, Flags<[CC1Option]>,
-  HelpText<"Assume functions may be convergent">;
+defm convergent_functions : BoolFOption<"convergent-functions",
+  LangOpts<"ConvergentFunctions">, DefaultFalse,
+  NegFlag<SetFalse, [], "Assume all functions may be convergent.">,
+  PosFlag<SetTrue, [CC1Option]>>;
 
 def gpu_use_aux_triple_only : Flag<["--"], "gpu-use-aux-triple-only">,
   InternalDriverOpt, HelpText<"Prepare '-aux-triple' only without populating "
                               "'-aux-target-cpu' and '-aux-target-feature'.">;
 def cuda_include_ptx_EQ : Joined<["--"], "cuda-include-ptx=">, Flags<[NoXarchOption]>,
   HelpText<"Include PTX for the following GPU architecture (e.g. sm_35) or 'all'. May be specified more than once.">;
 def no_cuda_include_ptx_EQ : Joined<["--"], "no-cuda-include-ptx=">, Flags<[NoXarchOption]>,
   HelpText<"Do not include PTX for the following GPU architecture (e.g. sm_35) or 'all'. May be specified more than once.">;

clang/lib/Driver/ToolChains/Clang.cpp

#endif
   }
 
   Args.addOptOutFlag(CmdArgs, options::OPT_funique_section_names,
                      options::OPT_fno_unique_section_names);
   Args.addOptInFlag(CmdArgs, options::OPT_funique_internal_linkage_names,
                     options::OPT_fno_unique_internal_linkage_names);
   Args.addOptInFlag(CmdArgs, options::OPT_funique_basic_block_section_names,
                     options::OPT_fno_unique_basic_block_section_names);
+  Args.addOptInFlag(CmdArgs, options::OPT_fconvergent_functions,
+                    options::OPT_fno_convergent_functions);
 
   if (Arg *A = Args.getLastArg(options::OPT_fsplit_machine_functions,
                                options::OPT_fno_split_machine_functions)) {
     // This codegen pass is only available on x86-elf targets.
     if (Triple.isX86() && Triple.isOSBinFormatELF()) {
       if (A->getOption().matches(options::OPT_fsplit_machine_functions))
         A->render(Args, CmdArgs);
     } else {

clang/lib/Frontend/CompilerInvocation.cpp

#undef LANG_OPTION_WITH_MARSHALLING
   Opts.Trigraphs =
       (!Opts.GNUMode && !Opts.MSVCCompat && !Opts.CPlusPlus17) || T.isOSzOS();
   Opts.Trigraphs =
       Args.hasFlag(OPT_ftrigraphs, OPT_fno_trigraphs, Opts.Trigraphs);
 
   Opts.Blocks = Args.hasArg(OPT_fblocks) || (Opts.OpenCL
     && Opts.OpenCLVersion == 200);
 
-  Opts.ConvergentFunctions = Opts.OpenCL || (Opts.CUDA && Opts.CUDAIsDevice) ||
-                             Opts.SYCLIsDevice ||
-                             Args.hasArg(OPT_fconvergent_functions);
+  Opts.ConvergentFunctions = Args.hasArg(OPT_fconvergent_functions) ||
+                             Opts.OpenCL || (Opts.CUDA && Opts.CUDAIsDevice) ||
+                             Opts.SYCLIsDevice;
 
   Opts.NoBuiltin = Args.hasArg(OPT_fno_builtin) || Opts.Freestanding;
   if (!Opts.NoBuiltin)
     getAllNoBuiltinFuncValues(Args, Opts.NoBuiltinFuncs);
   if (Arg *A = Args.getLastArg(options::OPT_LongDouble_Group)) {
     if (A->getOption().matches(options::OPT_mlong_double_64))
       Opts.LongDoubleSize = 64;
     else if (A->getOption().matches(options::OPT_mlong_double_80))

clang/test/Driver/amdgpu-toolchain.c

 // RUN: %clang -### --target=amdgcn--amdhsa -x assembler -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=AS_LINK %s
 // RUN: %clang -### -g --target=amdgcn--amdhsa -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=DWARF_VER %s
 // RUN: %clang -### --target=amdgcn-amd-amdpal -x assembler -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=AS_LINK %s
 // RUN: %clang -### -g --target=amdgcn-amd-amdpal -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=DWARF_VER %s
 // RUN: %clang -### --target=amdgcn-mesa-mesa3d -x assembler -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=AS_LINK %s
 // RUN: %clang -### -g --target=amdgcn-mesa-mesa3d -mcpu=kaveri %s 2>&1 | FileCheck -check-prefix=DWARF_VER %s
 
 // AS_LINK: "-cc1as"
 // AS_LINK: ld.lld{{.*}} "--no-undefined" "-shared"
 
 // DWARF_VER: "-dwarf-version=5"
 
 // RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx906 -nogpulib \
-// RUN:   -flto %s 2>&1 | FileCheck -check-prefix=LTO %s
-// LTO: clang{{.*}} "-flto=full"
+// RUN:   -flto -fconvergent-functions %s 2>&1 | FileCheck -check-prefix=LTO %s
+// LTO: clang{{.*}} "-flto=full"{{.*}}"-fconvergent-functions"
 // LTO: ld.lld{{.*}}-plugin-opt=mcpu=gfx906