[Clang] Make the GPU toolchains implicitly link -lm and -lc

Summary:
The previous patches (The other commits in this chain) allow the
offloading toolchain to directly invoke the device linker. Because of
this, we can now just have the toolchain implicitly include `-lc` and
`-lm` like a standard target does. This removes the old handling that
went through the fat binary `-lcgpu`.

Author: jhuber6

clang/lib/Driver/ToolChains/AMDGPU.cpp

@@ -633,6 +633,9 @@ void amdgpu::Linker::ConstructJob(Compilation &C, const JobAction &JA,
   else if (Args.hasArg(options::OPT_mcpu_EQ))
     CmdArgs.push_back(Args.MakeArgString(
         "-plugin-opt=mcpu=" + Args.getLastArgValue(options::OPT_mcpu_EQ)));
+
+  addGPULibraries(getToolChain(), Args, CmdArgs);
+
   CmdArgs.push_back("-o");
   CmdArgs.push_back(Output.getFilename());
   C.addCommand(std::make_unique<Command>(

clang/lib/Driver/ToolChains/CommonArgs.cpp

@@ -509,6 +509,22 @@ void tools::addLinkerCompressDebugSectionsOption(
   }
 }
 
+void tools::addGPULibraries(const ToolChain &TC, const llvm::opt::ArgList &Args,
+                            llvm::opt::ArgStringList &CmdArgs) {
+  if (Args.hasArg(options::OPT_nostdlib, options::OPT_r,
+                  options::OPT_nodefaultlibs, options::OPT_nolibc,
+                  options::OPT_nogpulibc))
+    return;
+
+  // If the user's toolchain has the 'include/<triple>/` path, we assume it
+  // supports the standard C libraries for the GPU and include them.
+  bool HasLibC = TC.getStdlibIncludePath().has_value();
+  if (HasLibC) {
+    CmdArgs.push_back("-lc");
+    CmdArgs.push_back("-lm");
+  }
+}
+
 void tools::AddTargetFeature(const ArgList &Args,
                              std::vector<StringRef> &Features,
                              OptSpecifier OnOpt, OptSpecifier OffOpt,
@@ -1257,6 +1273,7 @@ bool tools::addOpenMPRuntime(const Compilation &C, ArgStringList &CmdArgs,
     addOpenMPDeviceLibC(C, Args, CmdArgs);
 
   addArchSpecificRPath(TC, Args, CmdArgs);
+
   addOpenMPRuntimeLibraryPath(TC, Args, CmdArgs);
 
   return true;

clang/lib/Driver/ToolChains/CommonArgs.h

@@ -35,6 +35,9 @@ void addLinkerCompressDebugSectionsOption(const ToolChain &TC,
                                           const llvm::opt::ArgList &Args,
                                           llvm::opt::ArgStringList &CmdArgs);
 
+void addGPULibraries(const ToolChain &TC, const llvm::opt::ArgList &Args,
+                     llvm::opt::ArgStringList &CmdArgs);
+
 void claimNoWarnArgs(const llvm::opt::ArgList &Args);
 
 bool addSanitizerRuntimes(const ToolChain &TC, const llvm::opt::ArgList &Args,

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -625,6 +625,8 @@ void NVPTX::Linker::ConstructJob(Compilation &C, const JobAction &JA,
     addLTOOptions(getToolChain(), Args, CmdArgs, Output, Inputs[0],
                   C.getDriver().getLTOMode() == LTOK_Thin);
 
+  addGPULibraries(getToolChain(), Args, CmdArgs);
+
   // Add paths for the default clang library path.
   SmallString<256> DefaultLibPath =
       llvm::sys::path::parent_path(TC.getDriver().Dir);