/// Add OpenMP linker script arguments at the end of the argument list so that
/// the fat binary is built by embedding each of the device images into the
/// host. The linker script also defines a few symbols required by the code
/// generation so that the images can be easily retrieved at runtime by the
/// offloading library. This should be used only in tool chains that support
/// linker scripts.
void tools::AddOpenMPLinkerScript(const ToolChain &TC, Compilation &C,
const InputInfo &Output,
const InputInfoList &Inputs,
const ArgList &Args, ArgStringList &CmdArgs,
const JobAction &JA) {
// If this is not an OpenMP host toolchain, we don't need to do anything.
if (!JA.isHostOffloading(Action::OFK_OpenMP))
return;
// Create temporary linker script. Keep it if save-temps is enabled.
const char *LKS;
SmallString<256> Name = llvm::sys::path::filename(Output.getFilename());
if (C.getDriver().isSaveTempsEnabled()) {
llvm::sys::path::replace_extension(Name, "lk");
LKS = C.getArgs().MakeArgString(Name.c_str());
} else {
llvm::sys::path::replace_extension(Name, "");
Name = C.getDriver().GetTemporaryPath(Name, "lk");
LKS = C.addTempFile(C.getArgs().MakeArgString(Name.c_str()));
}
// Add linker script option to the command.
CmdArgs.push_back("-T");
CmdArgs.push_back(LKS);
// Create a buffer to write the contents of the linker script.
std::string LksBuffer;
llvm::raw_string_ostream LksStream(LksBuffer);
// Get the OpenMP offload tool chains so that we can extract the triple
// associated with each device input.
auto OpenMPToolChains = C.getOffloadToolChains<Action::OFK_OpenMP>();
assert(OpenMPToolChains.first != OpenMPToolChains.second &&
"No OpenMP toolchains??");
// Track the input file name and device triple in order to build the script,
// inserting binaries in the designated sections.
SmallVector<std::pair<std::string, const char *>, 8> InputBinaryInfo;
// Add commands to embed target binaries. We ensure that each section and
// image is 16-byte aligned. This is not mandatory, but increases the
// likelihood of data to be aligned with a cache block in several main host
// machines.
LksStream << "/*\n";
LksStream << " OpenMP Offload Linker Script\n";
LksStream << " *** Automatically generated by Clang ***\n";
LksStream << "*/\n";
LksStream << "TARGET(binary)\n";
auto DTC = OpenMPToolChains.first;
for (auto &II : Inputs) {
const Action *A = II.getAction();
// Is this a device linking action?
if (A && isa<LinkJobAction>(A) &&
A->isDeviceOffloading(Action::OFK_OpenMP)) {
assert(DTC != OpenMPToolChains.second &&
"More device inputs than device toolchains??");
InputBinaryInfo.push_back(std::make_pair(
DTC->second->getTriple().normalize(), II.getFilename()));
++DTC;
LksStream << "INPUT(" << II.getFilename() << ")\n";
}
}
assert(DTC == OpenMPToolChains.second &&
"Less device inputs than device toolchains??");
LksStream << "SECTIONS\n";
LksStream << "{\n";
// Put each target binary into a separate section.
for (const auto &BI : InputBinaryInfo) {
LksStream << " .omp_offloading." << BI.first << " :\n";
LksStream << " ALIGN(0x10)\n";
LksStream << " {\n";
LksStream << " PROVIDE_HIDDEN(.omp_offloading.img_start." << BI.first
<< " = .);\n";
LksStream << " " << BI.second << "\n";
LksStream << " PROVIDE_HIDDEN(.omp_offloading.img_end." << BI.first
<< " = .);\n";
LksStream << " }\n";
}
// Add commands to define host entries begin and end. We use 1-byte subalign
// so that the linker does not add any padding and the elements in this
// section form an array.
LksStream << " .omp_offloading.entries :\n";
LksStream << " ALIGN(0x10)\n";
LksStream << " SUBALIGN(0x01)\n";
LksStream << " {\n";
LksStream << " PROVIDE_HIDDEN(.omp_offloading.entries_begin = .);\n";
LksStream << " *(.omp_offloading.entries)\n";
LksStream << " PROVIDE_HIDDEN(.omp_offloading.entries_end = .);\n";
LksStream << " }\n";
LksStream << "}\n";
LksStream << "INSERT BEFORE .data\n";
LksStream.flush();
// Dump the contents of the linker script if the user requested that. We
// support this option to enable testing of behavior with -###.
if (C.getArgs().hasArg(options::OPT_fopenmp_dump_offload_linker_script))
llvm::errs() << LksBuffer;
// If this is a dry run, do not create the linker script file.
if (C.getArgs().hasArg(options::OPT__HASH_HASH_HASH))
return;
// Open script file and write the contents.
std::error_code EC;
llvm::raw_fd_ostream Lksf(LKS, EC, llvm::sys::fs::F_None);
if (EC) {
C.getDriver().Diag(clang::diag::err_unable_to_make_temp) << EC.message();
return;
}
Lksf << LksBuffer;
}
void NVPTX::OpenMPLinker::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");
ArgStringList CmdArgs;
// OpenMP uses nvlink to link cubin files. The result will be embedded in the
// host binary by the host linker.
assert(!JA.isHostOffloading(Action::OFK_OpenMP) &&
"CUDA toolchain not expected for an OpenMP host device.");
if (Output.isFilename()) {
CmdArgs.push_back("-o");
CmdArgs.push_back(Output.getFilename());
} else
assert(Output.isNothing() && "Invalid output.");
if (Args.hasArg(options::OPT_g_Flag))
CmdArgs.push_back("-g");
if (Args.hasArg(options::OPT_v))
CmdArgs.push_back("-v");
StringRef GPUArch =
Args.getLastArgValue(options::OPT_march_EQ);
assert(!GPUArch.empty() && "At least one GPU Arch required for ptxas.");
CmdArgs.push_back("-arch");
CmdArgs.push_back(Args.MakeArgString(GPUArch));
// Add paths specified in LIBRARY_PATH environment variable as -L options.
addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
// Add paths for the default clang library path.
SmallString<256> DefaultLibPath =
llvm::sys::path::parent_path(TC.getDriver().Dir);
llvm::sys::path::append(DefaultLibPath, "lib" CLANG_LIBDIR_SUFFIX);
CmdArgs.push_back(Args.MakeArgString(Twine("-L") + DefaultLibPath));
// Add linking against library implementing OpenMP calls on NVPTX target.
CmdArgs.push_back("-lomptarget-nvptx");
for (const auto &II : Inputs) {
if (II.getType() == types::TY_LLVM_IR ||
II.getType() == types::TY_LTO_IR ||
II.getType() == types::TY_LTO_BC ||
II.getType() == types::TY_LLVM_BC) {
C.getDriver().Diag(diag::err_drv_no_linker_llvm_support)
<< getToolChain().getTripleString();
continue;
}
// Currently, we only pass the input files to the linker, we do not pass
// any libraries that may be valid only for the host.
if (!II.isFilename())
continue;
const char *CubinF = C.addTempFile(
C.getArgs().MakeArgString(getToolChain().getInputFilename(II)));
CmdArgs.push_back(CubinF);
}
AddOpenMPLinkerScript(getToolChain(), C, Output, Inputs, Args, CmdArgs, JA);
const char *Exec =
Args.MakeArgString(getToolChain().GetProgramPath("nvlink"));
C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
}
static
void ExecuteTemplightJobs(Driver &TheDriver, DiagnosticsEngine &Diags,
Compilation &C, Job &J, const char* Argv0,
SmallVector<std::pair<int, const Command *>, 4>& FailingCommands) {
if (JobList *jobs = dyn_cast<JobList>(&J)) {
for (JobList::iterator it = jobs->begin(), it_end = jobs->end(); it != it_end; ++it)
ExecuteTemplightJobs(TheDriver, Diags, C, *it, Argv0, FailingCommands);
return;
}
Command *command = dyn_cast<Command>(&J);
// Since argumentsFitWithinSystemLimits() may underestimate system's capacity
// if the tool does not support response files, there is a chance/ that things
// will just work without a response file, so we silently just skip it.
if ( command &&
command->getCreator().getResponseFilesSupport() != Tool::RF_None &&
llvm::sys::argumentsFitWithinSystemLimits(command->getArguments()) ) {
std::string TmpName = TheDriver.GetTemporaryPath("response", "txt");
command->setResponseFile(C.addTempFile(C.getArgs().MakeArgString(
TmpName.c_str())));
}
if ( command && (StringRef(command->getCreator().getName()) == "clang") ) {
// Initialize a compiler invocation object from the clang (-cc1) arguments.
const ArgStringList &cc_arguments = command->getArguments();
const char** args_start = const_cast<const char**>(cc_arguments.data());
const char** args_end = args_start + cc_arguments.size();
std::unique_ptr<CompilerInstance> Clang(new CompilerInstance());
int Res = !CompilerInvocation::CreateFromArgs(
Clang->getInvocation(), args_start, args_end, Diags);
if(Res)
FailingCommands.push_back(std::make_pair(Res, command));
Clang->getFrontendOpts().DisableFree = false;
// Infer the builtin include path if unspecified.
void *GetExecutablePathVP = (void *)(intptr_t) GetExecutablePath;
if (Clang->getHeaderSearchOpts().UseBuiltinIncludes &&
Clang->getHeaderSearchOpts().ResourceDir.empty())
Clang->getHeaderSearchOpts().ResourceDir =
CompilerInvocation::GetResourcesPath(Argv0, GetExecutablePathVP);
// Create the compilers actual diagnostics engine.
Clang->createDiagnostics();
if (!Clang->hasDiagnostics()) {
FailingCommands.push_back(std::make_pair(1, command));
return;
}
LocalOutputFilename = ""; // Let the filename be created from options or output file name.
std::string TemplightOutFile = TemplightAction::CreateOutputFilename(
Clang.get(), "", InstProfiler, OutputToStdOut, MemoryProfile);
// Check if templight filename is in a temporary path:
llvm::SmallString<128> TDir;
llvm::sys::path::system_temp_directory(true, TDir);
if ( TDir.equals(llvm::sys::path::parent_path(llvm::StringRef(TemplightOutFile))) ) {
C.addTempFile(TemplightOutFile.c_str());
TempOutputFiles.push_back(TemplightOutFile);
}
// Execute the frontend actions.
Res = ExecuteTemplightInvocation(Clang.get());
if(Res)
FailingCommands.push_back(std::make_pair(Res, command));
} else {
C.ExecuteJob(J, FailingCommands);
}
}