// 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);
}
void tools::SHAVE::Compiler::ConstructJob(Compilation &C, const JobAction &JA,
const InputInfo &Output,
const InputInfoList &Inputs,
const ArgList &Args,
const char *LinkingOutput) const {
ArgStringList CmdArgs;
assert(Inputs.size() == 1);
const InputInfo &II = Inputs[0];
assert(II.getType() == types::TY_C || II.getType() == types::TY_CXX ||
II.getType() == types::TY_PP_CXX);
if (JA.getKind() == Action::PreprocessJobClass) {
Args.ClaimAllArgs();
CmdArgs.push_back("-E");
} else {
assert(Output.getType() == types::TY_PP_Asm); // Require preprocessed asm.
CmdArgs.push_back("-S");
CmdArgs.push_back("-fno-exceptions"); // Always do this even if unspecified.
}
CmdArgs.push_back("-DMYRIAD2");
// Append all -I, -iquote, -isystem paths, defines/undefines, 'f'
// flags, 'g' flags, 'M' flags, optimize flags, warning options,
// mcpu flags, mllvm flags, and Xclang flags.
// These are spelled the same way in clang and moviCompile.
Args.AddAllArgsExcept(
CmdArgs,
{options::OPT_I_Group, options::OPT_clang_i_Group, options::OPT_std_EQ,
options::OPT_D, options::OPT_U, options::OPT_f_Group,
options::OPT_f_clang_Group, options::OPT_g_Group, options::OPT_M_Group,
options::OPT_O_Group, options::OPT_W_Group, options::OPT_mcpu_EQ,
options::OPT_mllvm, options::OPT_Xclang},
{options::OPT_fno_split_dwarf_inlining});
Args.hasArg(options::OPT_fno_split_dwarf_inlining); // Claim it if present.
// If we're producing a dependency file, and assembly is the final action,
// then the name of the target in the dependency file should be the '.o'
// file, not the '.s' file produced by this step. For example, instead of
// /tmp/mumble.s: mumble.c .../someheader.h
// the filename on the lefthand side should be "mumble.o"
if (Args.getLastArg(options::OPT_MF) && !Args.getLastArg(options::OPT_MT) &&
C.getActions().size() == 1 &&
C.getActions()[0]->getKind() == Action::AssembleJobClass) {
Arg *A = Args.getLastArg(options::OPT_o);
if (A) {
CmdArgs.push_back("-MT");
CmdArgs.push_back(Args.MakeArgString(A->getValue()));
}
}
CmdArgs.push_back(II.getFilename());
CmdArgs.push_back("-o");
CmdArgs.push_back(Output.getFilename());
std::string Exec =
Args.MakeArgString(getToolChain().GetProgramPath("moviCompile"));
C.addCommand(llvm::make_unique<Command>(JA, *this, Args.MakeArgString(Exec),
CmdArgs, Inputs));
}
bool Driver::ShouldUseClangCompiler(const Compilation &C, const JobAction &JA,
const std::string &ArchNameStr) const {
// FIXME: Remove this hack.
const char *ArchName = ArchNameStr.c_str();
if (ArchNameStr == "powerpc")
ArchName = "ppc";
else if (ArchNameStr == "powerpc64")
ArchName = "ppc64";
// Check if user requested no clang, or clang doesn't understand
// this type (we only handle single inputs for now).
if (!CCCUseClang || JA.size() != 1 ||
!types::isAcceptedByClang((*JA.begin())->getType()))
return false;
// Otherwise make sure this is an action clang understands.
if (isa<PreprocessJobAction>(JA)) {
if (!CCCUseClangCPP) {
Diag(clang::diag::warn_drv_not_using_clang_cpp);
return false;
}
} else if (!isa<PrecompileJobAction>(JA) && !isa<CompileJobAction>(JA))
return false;
// Use clang for C++?
if (!CCCUseClangCXX && types::isCXX((*JA.begin())->getType())) {
Diag(clang::diag::warn_drv_not_using_clang_cxx);
return false;
}
// Always use clang for precompiling, regardless of archs. PTH is
// platform independent, and this allows the use of the static
// analyzer on platforms we don't have full IRgen support for.
if (isa<PrecompileJobAction>(JA))
return true;
// Finally, don't use clang if this isn't one of the user specified
// archs to build.
if (!CCCClangArchs.empty() && !CCCClangArchs.count(ArchName)) {
Diag(clang::diag::warn_drv_not_using_clang_arch) << ArchName;
return false;
}
return true;
}
void tools::AddLinkerInputs(const ToolChain &TC, const InputInfoList &Inputs,
const ArgList &Args, ArgStringList &CmdArgs,
const JobAction &JA) {
const Driver &D = TC.getDriver();
// Add extra linker input arguments which are not treated as inputs
// (constructed via -Xarch_).
Args.AddAllArgValues(CmdArgs, options::OPT_Zlinker_input);
for (const auto &II : Inputs) {
// If the current tool chain refers to an OpenMP offloading host, we should
// ignore inputs that refer to OpenMP offloading devices - they will be
// embedded according to a proper linker script.
if (auto *IA = II.getAction())
if (JA.isHostOffloading(Action::OFK_OpenMP) &&
IA->isDeviceOffloading(Action::OFK_OpenMP))
continue;
if (!TC.HasNativeLLVMSupport() && types::isLLVMIR(II.getType()))
// Don't try to pass LLVM inputs unless we have native support.
D.Diag(diag::err_drv_no_linker_llvm_support) << TC.getTripleString();
// Add filenames immediately.
if (II.isFilename()) {
CmdArgs.push_back(II.getFilename());
continue;
}
// Otherwise, this is a linker input argument.
const Arg &A = II.getInputArg();
// Handle reserved library options.
if (A.getOption().matches(options::OPT_Z_reserved_lib_stdcxx))
TC.AddCXXStdlibLibArgs(Args, CmdArgs);
else if (A.getOption().matches(options::OPT_Z_reserved_lib_cckext))
TC.AddCCKextLibArgs(Args, CmdArgs);
else if (A.getOption().matches(options::OPT_z)) {
// Pass -z prefix for gcc linker compatibility.
A.claim();
A.render(Args, CmdArgs);
} else {
A.renderAsInput(Args, CmdArgs);
}
}
// LIBRARY_PATH - included following the user specified library paths.
// and only supported on native toolchains.
if (!TC.isCrossCompiling()) {
addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
}
}
bool Driver::ShouldUseClangCompiler(const Compilation &C, const JobAction &JA,
const llvm::Triple &Triple) const {
// Check if user requested no clang, or clang doesn't understand this type (we
// only handle single inputs for now).
if (!CCCUseClang || JA.size() != 1 ||
!types::isAcceptedByClang((*JA.begin())->getType()))
return false;
// Otherwise make sure this is an action clang understands.
if (isa<PreprocessJobAction>(JA)) {
if (!CCCUseClangCPP) {
Diag(clang::diag::warn_drv_not_using_clang_cpp);
return false;
}
} else if (!isa<PrecompileJobAction>(JA) && !isa<CompileJobAction>(JA))
return false;
// Use clang for C++?
if (!CCCUseClangCXX && types::isCXX((*JA.begin())->getType())) {
Diag(clang::diag::warn_drv_not_using_clang_cxx);
return false;
}
// Always use clang for precompiling, AST generation, and rewriting,
// regardless of archs.
if (isa<PrecompileJobAction>(JA) || JA.getType() == types::TY_AST ||
JA.getType() == types::TY_RewrittenObjC)
return true;
// Finally, don't use clang if this isn't one of the user specified archs to
// build.
if (!CCCClangArchs.empty() && !CCCClangArchs.count(Triple.getArch())) {
Diag(clang::diag::warn_drv_not_using_clang_arch) << Triple.getArchName();
return false;
}
return true;
}
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));
}
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));
}
/// 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;
}
