[clang][cli] Port GPU-related language options to marshalling system

[jansvoboda11]

Summary

Port some GPU-related language options to the marshalling system for automatic command line parsing and generation.

[jansvoboda11]

Remove diagnostics from ParseLangArgs

[dexonsmith]

LGTM.

clang/include/clang/Driver/Options.td

NormalizedValues<["DefaultVisibility", "HiddenVisibility",
                       "HiddenVisibility", "ProtectedVisibility"]>,
     AutoNormalizeEnum {}
 
 // Key paths that are constant during parsing of options with the same key path prefix.
 defvar cplusplus = LangOpts<"CPlusPlus">;
 defvar c99 = LangOpts<"C99">;
 defvar lang_std = LangOpts<"LangStd">;
 defvar open_cl = LangOpts<"OpenCL">;
+defvar render_script = LangOpts<"RenderScript">;
+defvar hip = LangOpts<"HIP">;
 defvar gnu_mode = LangOpts<"GNUMode">;
 
 defvar std = !strconcat("LangStandard::getLangStandardForKind(", lang_std.KeyPath, ")");
 
 /////////
 // Options
 
 // The internal option ID must be a valid C++ identifier and results in a
def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
   HelpText<"CUDA installation path">;
 def cuda_path_ignore_env : Flag<["--"], "cuda-path-ignore-env">, Group<i_Group>,
   HelpText<"Ignore environment variables to detect CUDA installation">;
 def ptxas_path_EQ : Joined<["--"], "ptxas-path=">, Group<i_Group>,
   HelpText<"Path to ptxas (used for compiling CUDA code)">;
 def fcuda_flush_denormals_to_zero : Flag<["-"], "fcuda-flush-denormals-to-zero">,
   HelpText<"Flush denormal floating point values to zero in CUDA device mode.">;
 def fno_cuda_flush_denormals_to_zero : Flag<["-"], "fno-cuda-flush-denormals-to-zero">;
-defm cuda_approx_transcendentals : OptInFFlag<"cuda-approx-transcendentals", "Use", "Don't use",
-  " approximate transcendental functions">;
 defm gpu_rdc : BoolFOption<"gpu-rdc",
   LangOpts<"GPURelocatableDeviceCode">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option], "Generate relocatable device code, also known as separate compilation mode">,
   NegFlag<SetFalse>>;
 def : Flag<["-"], "fcuda-rdc">, Alias<fgpu_rdc>;
 def : Flag<["-"], "fno-cuda-rdc">, Alias<fno_gpu_rdc>;
 defm cuda_short_ptr : OptInFFlag<"cuda-short-ptr",
   "Use 32-bit pointers for accessing const/local/shared address spaces", "", "",
   [], TargetOpts<"NVPTXUseShortPointers">>;
 def rocm_path_EQ : Joined<["--"], "rocm-path=">, Group<i_Group>,
   HelpText<"ROCm installation path, used for finding and automatically linking required bitcode libraries.">;
 def rocm_device_lib_path_EQ : Joined<["--"], "rocm-device-lib-path=">, Group<Link_Group>,
   HelpText<"ROCm device library path. Alternative to rocm-path.">;
 def : Joined<["--"], "hip-device-lib-path=">, Alias<rocm_device_lib_path_EQ>;
 def hip_device_lib_EQ : Joined<["--"], "hip-device-lib=">, Group<Link_Group>,
   HelpText<"HIP device library">;
 def hip_version_EQ : Joined<["--"], "hip-version=">,
   HelpText<"HIP version in the format of major.minor.patch">;
 def fhip_dump_offload_linker_script : Flag<["-"], "fhip-dump-offload-linker-script">,
   Group<f_Group>, Flags<[NoArgumentUnused, HelpHidden]>;
 defm hip_new_launch_api : BoolFOption<"hip-new-launch-api",
   LangOpts<"HIPUseNewLaunchAPI">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option], "Use">, NegFlag<SetFalse, [], "Don't use">,
   BothFlags<[], " new kernel launching API for HIP">>;
-defm gpu_allow_device_init : OptInFFlag<"gpu-allow-device-init",
-  "Allow", "Don't allow", " device side init function in HIP">;
+defm gpu_allow_device_init : BoolFOption<"gpu-allow-device-init",
+  LangOpts<"GPUAllowDeviceInit">, DefaultFalse,
+  PosFlag<SetTrue, [CC1Option], "Allow">, NegFlag<SetFalse, [], "Don't allow">,
+  BothFlags<[], " device side init function in HIP">>,
+  ShouldParseIf<hip.KeyPath>;
 defm gpu_defer_diag : BoolFOption<"gpu-defer-diag",
   LangOpts<"GPUDeferDiag">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option], "Defer">, NegFlag<SetFalse, [], "Don't defer">,
   BothFlags<[], " host/device related diagnostic messages for CUDA/HIP">>;
 defm gpu_exclude_wrong_side_overloads : BoolFOption<"gpu-exclude-wrong-side-overloads",
   LangOpts<"GPUExcludeWrongSideOverloads">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option], "Always exclude wrong side overloads">,
   NegFlag<SetFalse, [], "Exclude wrong side overloads only if there are same side overloads">,
   BothFlags<[HelpHidden], " in overloading resolution for CUDA/HIP">>;
 def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
   Flags<[CC1Option]>,
-  HelpText<"Default max threads per block for kernel launch bounds for HIP">;
+  HelpText<"Default max threads per block for kernel launch bounds for HIP">,
+  MarshallingInfoStringInt<LangOpts<"GPUMaxThreadsPerBlock">, "256">,
+  ShouldParseIf<hip.KeyPath>;
 def gpu_instrument_lib_EQ : Joined<["--"], "gpu-instrument-lib=">,
   HelpText<"Instrument device library for HIP, which is a LLVM bitcode containing "
   "__cyg_profile_func_enter and __cyg_profile_func_exit">;
 def libomptarget_nvptx_path_EQ : Joined<["--"], "libomptarget-nvptx-path=">, Group<i_Group>,
   HelpText<"Path to libomptarget-nvptx libraries">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
 def dI : Flag<["-"], "dI">, Group<d_Group>, Flags<[CC1Option]>,
def fno_deprecated_macro : Flag<["-"], "fno-deprecated-macro">,
   HelpText<"Undefines the __DEPRECATED macro">;
 def fobjc_subscripting_legacy_runtime : Flag<["-"], "fobjc-subscripting-legacy-runtime">,
   HelpText<"Allow Objective-C array and dictionary subscripting in legacy runtime">;
 // TODO: Enforce values valid for MSVtorDispMode.
 def vtordisp_mode_EQ : Joined<["-"], "vtordisp-mode=">,
   HelpText<"Control vtordisp placement on win32 targets">,
   MarshallingInfoStringInt<LangOpts<"VtorDispMode">, "1">;
 def fnative_half_type: Flag<["-"], "fnative-half-type">,
-  HelpText<"Use the native half type for __fp16 instead of promoting to float">;
+  HelpText<"Use the native half type for __fp16 instead of promoting to float">,
+  MarshallingInfoFlag<LangOpts<"NativeHalfType">>,
+  ImpliedByAnyOf<[open_cl.KeyPath, render_script.KeyPath]>;
 def fnative_half_arguments_and_returns : Flag<["-"], "fnative-half-arguments-and-returns">,
-  HelpText<"Use the native __fp16 type for arguments and returns (and skip ABI-specific lowering)">;
+  HelpText<"Use the native __fp16 type for arguments and returns (and skip ABI-specific lowering)">,
+  MarshallingInfoFlag<LangOpts<"NativeHalfArgsAndReturns">>,
+  ImpliedByAnyOf<[open_cl.KeyPath, render_script.KeyPath]>;
 def fallow_half_arguments_and_returns : Flag<["-"], "fallow-half-arguments-and-returns">,
-  HelpText<"Allow function arguments and returns of type half">;
+  HelpText<"Allow function arguments and returns of type half">,
+  MarshallingInfoFlag<LangOpts<"HalfArgsAndReturns">>,
+  ImpliedByAnyOf<[fnative_half_arguments_and_returns.KeyPath]>;
 def fdefault_calling_conv_EQ : Joined<["-"], "fdefault-calling-conv=">,
   HelpText<"Set default calling convention">, Values<"cdecl,fastcall,stdcall,vectorcall,regcall">,
   NormalizedValuesScope<"LangOptions">,
   NormalizedValues<["DCC_CDecl", "DCC_FastCall", "DCC_StdCall", "DCC_VectorCall", "DCC_RegCall"]>,
   MarshallingInfoString<LangOpts<"DefaultCallingConv">, "DCC_None">, AutoNormalizeEnum;
 
 // These options cannot be marshalled, because they are used to set up the LangOptions defaults.
 def finclude_default_header : Flag<["-"], "finclude-default-header">,

 def fopenmp_host_ir_file_path : Separate<["-"], "fopenmp-host-ir-file-path">,
   HelpText<"Path to the IR file produced by the frontend for the host.">;
 
 //===----------------------------------------------------------------------===//
 // SYCL Options
 //===----------------------------------------------------------------------===//
 
 def fsycl_is_device : Flag<["-"], "fsycl-is-device">,
-  HelpText<"Generate code for SYCL device.">;
+  HelpText<"Generate code for SYCL device.">,
+  MarshallingInfoFlag<LangOpts<"SYCLIsDevice">>,
+  ShouldParseIf<fsycl.KeyPath>;
 
 } // let Flags = [CC1Option, NoDriverOption]
 
+defm cuda_approx_transcendentals : BoolFOption<"cuda-approx-transcendentals",
+  LangOpts<"CUDADeviceApproxTranscendentals">, DefaultFalse,
+  PosFlag<SetTrue, [CC1Option], "Use">, NegFlag<SetFalse, [], "Don't use">,
+  BothFlags<[], " approximate transcendental functions">>,
+  ShouldParseIf<fcuda_is_device.KeyPath>;
+
 //===----------------------------------------------------------------------===//
 // Frontend Options - cc1 + fc1
 //===----------------------------------------------------------------------===//
 let Flags = [CC1Option, FC1Option, NoDriverOption] in {
 let Group = Action_Group in {
 
 def emit_obj : Flag<["-"], "emit-obj">,
   HelpText<"Emit native object files">;

clang/lib/Frontend/CompilerInvocation.cpp

 //===- CompilerInvocation.cpp ---------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
Diags.Report(diag::err_fe_invalid_alignment)
         << A->getAsString(Args) << A->getValue();
     LangOpts.NewAlignOverride = 0;
   }
 
   if (Args.hasArg(OPT_fgnu89_inline) && LangOpts.CPlusPlus)
     Diags.Report(diag::err_drv_argument_not_allowed_with)
         << "-fgnu89-inline" << GetInputKindName(IK);
 
+  if (Args.hasArg(OPT_fgpu_allow_device_init) && !LangOpts.HIP)
+    Diags.Report(diag::warn_ignored_hip_only_option)
+        << Args.getLastArg(OPT_fgpu_allow_device_init)->getAsString(Args);
+
+  if (Args.hasArg(OPT_gpu_max_threads_per_block_EQ) && !LangOpts.HIP)
+    Diags.Report(diag::warn_ignored_hip_only_option)
+        << Args.getLastArg(OPT_gpu_max_threads_per_block_EQ)->getAsString(Args);
+
+  // -cl-strict-aliasing needs to emit diagnostic in the case where CL > 1.0.
+  // This option should be deprecated for CL > 1.0 because
+  // this option was added for compatibility with OpenCL 1.0.
+  if (Args.getLastArg(OPT_cl_strict_aliasing) && LangOpts.OpenCLVersion > 100)
+    Diags.Report(diag::warn_option_invalid_ocl_version)
+        << LangOpts.getOpenCLVersionTuple().getAsString()
+        << Args.getLastArg(OPT_cl_strict_aliasing)->getAsString(Args);
+
   if (Arg *A = Args.getLastArg(OPT_fdefault_calling_conv_EQ)) {
     auto DefaultCC = LangOpts.getDefaultCallingConv();
 
     bool emitError = (DefaultCC == LangOptions::DCC_FastCall ||
                       DefaultCC == LangOptions::DCC_StdCall) &&
                      Arch != llvm::Triple::x86;
     emitError |= (DefaultCC == LangOptions::DCC_VectorCall ||
                   DefaultCC == LangOptions::DCC_RegCall) &&
#endif
   else if (LangStd == LangStandard::lang_openclcpp)
     Opts.OpenCLCPlusPlusVersion = 100;
 
   // OpenCL has some additional defaults.
   if (Opts.OpenCL) {
     Opts.AltiVec = 0;
     Opts.ZVector = 0;
     Opts.setDefaultFPContractMode(LangOptions::FPM_On);
-    Opts.NativeHalfType = 1;
-    Opts.NativeHalfArgsAndReturns = 1;
     Opts.OpenCLCPlusPlus = Opts.CPlusPlus;
 
     // Include default header file for OpenCL.
     if (Opts.IncludeDefaultHeader) {
       if (Opts.DeclareOpenCLBuiltins) {
         // Only include base header file for builtin types and constants.
         Includes.push_back("opencl-c-base.h");
       } else {
if (Opts.HIP) {
     // whereas respecting contract flag in backend.
     Opts.setDefaultFPContractMode(LangOptions::FPM_FastHonorPragmas);
   } else if (Opts.CUDA) {
     // Allow fuse across statements disregarding pragmas.
     Opts.setDefaultFPContractMode(LangOptions::FPM_Fast);
   }
 
   Opts.RenderScript = IK.getLanguage() == Language::RenderScript;
-  if (Opts.RenderScript) {
-    Opts.NativeHalfType = 1;
-    Opts.NativeHalfArgsAndReturns = 1;
-  }
 
   // OpenCL and C++ both have bool, true, false keywords.
   Opts.Bool = Opts.OpenCL || Opts.CPlusPlus;
 
   // OpenCL has half keyword
   Opts.Half = Opts.OpenCL;
 
   // C++ has wchar_t keyword.
#undef LANG_OPTION_WITH_MARSHALLING
 
   if (const Arg *A = Args.getLastArg(OPT_fcf_protection_EQ)) {
     StringRef Name = A->getValue();
     if (Name == "full" || Name == "branch") {
       Opts.CFProtectionBranch = 1;
     }
   }
 
-  Opts.SYCLIsDevice = Opts.SYCL && Args.hasArg(options::OPT_fsycl_is_device);
-
   // -cl-strict-aliasing needs to emit diagnostic in the case where CL > 1.0.
   // This option should be deprecated for CL > 1.0 because
   // this option was added for compatibility with OpenCL 1.0.
   if (Args.getLastArg(OPT_cl_strict_aliasing)
        && Opts.OpenCLVersion > 100) {
     Diags.Report(diag::warn_option_invalid_ocl_version)
         << Opts.getOpenCLVersionTuple().getAsString()
         << Args.getLastArg(OPT_cl_strict_aliasing)->getAsString(Args);
   }
 
   if (Args.hasArg(OPT_fno_operator_names))
     Opts.CXXOperatorNames = 0;
 
-  if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_approx_transcendentals))
-    Opts.CUDADeviceApproxTranscendentals = 1;
-
-  if (Args.hasArg(OPT_fgpu_allow_device_init)) {
-    if (Opts.HIP)
-      Opts.GPUAllowDeviceInit = 1;
-    else
-      Diags.Report(diag::warn_ignored_hip_only_option)
-          << Args.getLastArg(OPT_fgpu_allow_device_init)->getAsString(Args);
-  }
-  if (Opts.HIP)
-    Opts.GPUMaxThreadsPerBlock = getLastArgIntValue(
-        Args, OPT_gpu_max_threads_per_block_EQ, Opts.GPUMaxThreadsPerBlock);
-  else if (Args.hasArg(OPT_gpu_max_threads_per_block_EQ))
-    Diags.Report(diag::warn_ignored_hip_only_option)
-        << Args.getLastArg(OPT_gpu_max_threads_per_block_EQ)->getAsString(Args);
-
   if (Opts.ObjC) {
     if (Arg *arg = Args.getLastArg(OPT_fobjc_runtime_EQ)) {
       StringRef value = arg->getValue();
       if (Opts.ObjCRuntime.tryParse(value))
         Diags.Report(diag::err_drv_unknown_objc_runtime) << value;
     }
 
     if (Args.hasArg(OPT_fobjc_gc_only))
#undef LANG_OPTION_WITH_MARSHALLING
   Opts.EnableAIXExtendedAltivecABI = Args.hasArg(OPT_mabi_EQ_vec_extabi);
   Opts.PICLevel = getLastArgIntValue(Args, OPT_pic_level, 0, Diags);
   Opts.DumpRecordLayouts = Opts.DumpRecordLayoutsSimple
                         || Args.hasArg(OPT_fdump_record_layouts);
   if (Opts.FastRelaxedMath)
     Opts.setDefaultFPContractMode(LangOptions::FPM_Fast);
   Opts.XLPragmaPack = Args.hasArg(OPT_fxl_pragma_pack);
   llvm::sort(Opts.ModuleFeatures);
-  Opts.NativeHalfType |= Args.hasArg(OPT_fnative_half_type);
-  Opts.NativeHalfArgsAndReturns |= Args.hasArg(OPT_fnative_half_arguments_and_returns);
-  // Enable HalfArgsAndReturns if present in Args or if NativeHalfArgsAndReturns
-  // is enabled.
-  Opts.HalfArgsAndReturns = Args.hasArg(OPT_fallow_half_arguments_and_returns)
-                            | Opts.NativeHalfArgsAndReturns;
 
   Opts.ArmSveVectorBits =
       getLastArgIntValue(Args, options::OPT_msve_vector_bits_EQ, 0, Diags);
 
   // __declspec is enabled by default for the PS4 by the driver, and also
   // enabled for Microsoft Extensions or Borland Extensions, here.
   //
   // FIXME: __declspec is also currently enabled for CUDA, but isn't really a