[ThinLTO] Clang support for emitting minimized bitcode for thin link

[tejohnson]

Summary

Clang companion patch to LLVM patch D31027, which adds support
for emitting minimized bitcode file for use in the thin link step.
Add a cc1 option -fthin-link-bitcode=<file> to trigger this behavior.

Depends on D31027.

[tejohnson]

Update as per review comments on llvm side patch D31027.

[pcc]

LGTM

include/clang/Driver/CC1Options.td

def fprofile_instrument_use_path_EQ :
     Joined<["-"], "fprofile-instrument-use-path=">,
     HelpText<"Specify the profile path in PGO use compilation">;
 def flto_visibility_public_std:
     Flag<["-"], "flto-visibility-public-std">,
     HelpText<"Use public LTO visibility for classes in std and stdext namespaces">;
 def flto_unit: Flag<["-"], "flto-unit">,
     HelpText<"Emit IR to support LTO unit features (CFI, whole program vtable opt)">;
 def fno_lto_unit: Flag<["-"], "fno-lto-unit">;
+def fthin_link_bitcode_EQ : Joined<["-"], "fthin-link-bitcode=">,
+    HelpText<"Write minimized bitcode to <file> for the ThinLTO thin link only">;
 
 //===----------------------------------------------------------------------===//
 // Dependency Output Options
 //===----------------------------------------------------------------------===//
 
 def sys_header_deps : Flag<["-"], "sys-header-deps">,
   HelpText<"Include system headers in dependency output">;
 def module_file_deps : Flag<["-"], "module-file-deps">,

include/clang/Frontend/CodeGenOptions.h

public:
 
   /// Name of the profile file to use as input for -fprofile-instr-use
   std::string ProfileInstrumentUsePath;
 
   /// Name of the function summary index file to use for ThinLTO function
   /// importing.
   std::string ThinLTOIndexFile;
 
+  /// Name of a file that can optionally be written with minimized bitcode
+  /// to be used as input for the ThinLTO thin link step, which only needs
+  /// the summary and module symbol table (and not, e.g. any debug metadata).
+  std::string ThinLinkBitcodeFile;
+
   /// A list of file names passed with -fcuda-include-gpubinary options to
   /// forward to CUDA runtime back-end for incorporating them into host-side
   /// object file.
   std::vector<std::string> CudaGpuBinaryFileNames;
 
   /// The name of the file to which the backend should save YAML optimization
   /// records.
   std::string OptRecordFile;

lib/CodeGen/BackendUtil.cpp

CodeGenPasses.add(
       createTargetTransformInfoWrapperPass(getTargetIRAnalysis()));
 
   switch (Action) {
   case Backend_EmitNothing:
     break;
 
   case Backend_EmitBC:
     if (CodeGenOpts.EmitSummaryIndex)
-      PerModulePasses.add(createWriteThinLTOBitcodePass(*OS));
+      PerModulePasses.add(
+          createWriteThinLTOBitcodePass(*OS, CodeGenOpts.ThinLinkBitcodeFile));
     else
       PerModulePasses.add(
           createBitcodeWriterPass(*OS, CodeGenOpts.EmitLLVMUseLists));
     break;
 
   case Backend_EmitLL:
     PerModulePasses.add(
         createPrintModulePass(*OS, "", CodeGenOpts.EmitLLVMUseLists));

lib/Frontend/CompilerInvocation.cpp

static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
   Opts.EmitSummaryIndex = A && A->containsValue("thin");
   Opts.LTOUnit = Args.hasFlag(OPT_flto_unit, OPT_fno_lto_unit, false);
   if (Arg *A = Args.getLastArg(OPT_fthinlto_index_EQ)) {
     if (IK != IK_LLVM_IR)
       Diags.Report(diag::err_drv_argument_only_allowed_with)
           << A->getAsString(Args) << "-x ir";
     Opts.ThinLTOIndexFile = Args.getLastArgValue(OPT_fthinlto_index_EQ);
   }
+  Opts.ThinLinkBitcodeFile = Args.getLastArgValue(OPT_fthin_link_bitcode_EQ);
 
   Opts.MSVolatile = Args.hasArg(OPT_fms_volatile);
 
   Opts.VectorizeBB = Args.hasArg(OPT_vectorize_slp_aggressive);
   Opts.VectorizeLoop = Args.hasArg(OPT_vectorize_loops);
   Opts.VectorizeSLP = Args.hasArg(OPT_vectorize_slp);
 
   Opts.MainFileName = Args.getLastArgValue(OPT_main_file_name);

test/CodeGen/thin_link_bitcode.c

+// RUN: %clang_cc1 -o %t -flto=thin -fthin-link-bitcode=%t.nodebug -triple x86_64-unknown-linux-gnu -emit-llvm-bc -debug-info-kind=limited %s
+// RUN: llvm-bcanalyzer -dump %t | FileCheck %s
+// RUN: llvm-bcanalyzer -dump %t.nodebug | FileCheck %s --check-prefix=NO_DEBUG
+int main (void) {
+  return 0;
+}
+
+// CHECK: COMPILE_UNIT
+// NO_DEBUG-NOT: COMPILE_UNIT