Esempio n. 1
0
// For amdgcn the inputs of the linker job are device bitcode and output is
// object file. It calls llvm-link, opt, llc, then lld steps.
void AMDGCN::Linker::ConstructJob(Compilation &C, const JobAction &JA,
                                   const InputInfo &Output,
                                   const InputInfoList &Inputs,
                                   const ArgList &Args,
                                   const char *LinkingOutput) const {

  assert(getToolChain().getTriple().getArch() == llvm::Triple::amdgcn &&
         "Unsupported target");

  std::string SubArchName = JA.getOffloadingArch();
  assert(StringRef(SubArchName).startswith("gfx") && "Unsupported sub arch");

  // Prefix for temporary file name.
  std::string Prefix =
      llvm::sys::path::stem(Inputs[0].getFilename()).str() + "-" + SubArchName;

  // Each command outputs different files.
  const char *LLVMLinkCommand =
      constructLLVMLinkCommand(C, JA, Inputs, Args, SubArchName, Prefix);
  const char *OptCommand = constructOptCommand(C, JA, Inputs, Args, SubArchName,
                                               Prefix, LLVMLinkCommand);
  const char *LlcCommand =
      constructLlcCommand(C, JA, Inputs, Args, SubArchName, Prefix, OptCommand);
  constructLldCommand(C, JA, Inputs, Output, Args, LlcCommand);
}
Esempio n. 2
0
void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
                                    const InputInfo &Output,
                                    const InputInfoList &Inputs,
                                    const ArgList &Args,
                                    const char *LinkingOutput) const {
  const auto &TC =
      static_cast<const toolchains::CudaToolChain &>(getToolChain());
  assert(TC.getTriple().isNVPTX() && "Wrong platform");

  StringRef GPUArchName;
  // If this is an OpenMP action we need to extract the device architecture
  // from the -march=arch option. This option may come from -Xopenmp-target
  // flag or the default value.
  if (JA.isDeviceOffloading(Action::OFK_OpenMP)) {
    GPUArchName = Args.getLastArgValue(options::OPT_march_EQ);
    assert(!GPUArchName.empty() && "Must have an architecture passed in.");
  } else
    GPUArchName = JA.getOffloadingArch();

  // Obtain architecture from the action.
  CudaArch gpu_arch = StringToCudaArch(GPUArchName);
  assert(gpu_arch != CudaArch::UNKNOWN &&
         "Device action expected to have an architecture.");

  // Check that our installation's ptxas supports gpu_arch.
  if (!Args.hasArg(options::OPT_no_cuda_version_check)) {
    TC.CudaInstallation.CheckCudaVersionSupportsArch(gpu_arch);
  }

  ArgStringList CmdArgs;
  CmdArgs.push_back(TC.getTriple().isArch64Bit() ? "-m64" : "-m32");
  if (Args.hasFlag(options::OPT_cuda_noopt_device_debug,
                   options::OPT_no_cuda_noopt_device_debug, false)) {
    // ptxas does not accept -g option if optimization is enabled, so
    // we ignore the compiler's -O* options if we want debug info.
    CmdArgs.push_back("-g");
    CmdArgs.push_back("--dont-merge-basicblocks");
    CmdArgs.push_back("--return-at-end");
  } else if (Arg *A = Args.getLastArg(options::OPT_O_Group)) {
    // Map the -O we received to -O{0,1,2,3}.
    //
    // TODO: Perhaps we should map host -O2 to ptxas -O3. -O3 is ptxas's
    // default, so it may correspond more closely to the spirit of clang -O2.

    // -O3 seems like the least-bad option when -Osomething is specified to
    // clang but it isn't handled below.
    StringRef OOpt = "3";
    if (A->getOption().matches(options::OPT_O4) ||
        A->getOption().matches(options::OPT_Ofast))
      OOpt = "3";
    else if (A->getOption().matches(options::OPT_O0))
      OOpt = "0";
    else if (A->getOption().matches(options::OPT_O)) {
      // -Os, -Oz, and -O(anything else) map to -O2, for lack of better options.
      OOpt = llvm::StringSwitch<const char *>(A->getValue())
                 .Case("1", "1")
                 .Case("2", "2")
                 .Case("3", "3")
                 .Case("s", "2")
                 .Case("z", "2")
                 .Default("2");
    }
    CmdArgs.push_back(Args.MakeArgString(llvm::Twine("-O") + OOpt));
  } else {
    // If no -O was passed, pass -O0 to ptxas -- no opt flag should correspond
    // to no optimizations, but ptxas's default is -O3.
    CmdArgs.push_back("-O0");
  }

  // Pass -v to ptxas if it was passed to the driver.
  if (Args.hasArg(options::OPT_v))
    CmdArgs.push_back("-v");

  CmdArgs.push_back("--gpu-name");
  CmdArgs.push_back(Args.MakeArgString(CudaArchToString(gpu_arch)));
  CmdArgs.push_back("--output-file");
  CmdArgs.push_back(Args.MakeArgString(TC.getInputFilename(Output)));
  for (const auto& II : Inputs)
    CmdArgs.push_back(Args.MakeArgString(II.getFilename()));

  for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_ptxas))
    CmdArgs.push_back(Args.MakeArgString(A));

  // In OpenMP we need to generate relocatable code.
  if (JA.isOffloading(Action::OFK_OpenMP) &&
      Args.hasFlag(options::OPT_fopenmp_relocatable_target,
                   options::OPT_fnoopenmp_relocatable_target,
                   /*Default=*/ true))
    CmdArgs.push_back("-c");

  const char *Exec;
  if (Arg *A = Args.getLastArg(options::OPT_ptxas_path_EQ))
    Exec = A->getValue();
  else
    Exec = Args.MakeArgString(TC.GetProgramPath("ptxas"));
  C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
}