void HIPToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args,
Action::OffloadKind DeviceOffloadingKind) const {
HostTC.addClangTargetOptions(DriverArgs, CC1Args, DeviceOffloadingKind);
StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
(void) GpuArch;
assert(DeviceOffloadingKind == Action::OFK_HIP &&
"Only HIP offloading kinds are supported for GPUs.");
CC1Args.push_back("-fcuda-is-device");
if (DriverArgs.hasFlag(options::OPT_fcuda_flush_denormals_to_zero,
options::OPT_fno_cuda_flush_denormals_to_zero, false))
CC1Args.push_back("-fcuda-flush-denormals-to-zero");
if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
options::OPT_fno_cuda_approx_transcendentals, false))
CC1Args.push_back("-fcuda-approx-transcendentals");
if (DriverArgs.hasFlag(options::OPT_fcuda_rdc, options::OPT_fno_cuda_rdc,
false))
CC1Args.push_back("-fcuda-rdc");
}
void CudaToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args,
Action::OffloadKind DeviceOffloadingKind) const {
HostTC.addClangTargetOptions(DriverArgs, CC1Args, DeviceOffloadingKind);
StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
assert((DeviceOffloadingKind == Action::OFK_OpenMP ||
DeviceOffloadingKind == Action::OFK_Cuda) &&
"Only OpenMP or CUDA offloading kinds are supported for NVIDIA GPUs.");
if (DeviceOffloadingKind == Action::OFK_Cuda) {
CC1Args.push_back("-fcuda-is-device");
if (DriverArgs.hasFlag(options::OPT_fcuda_flush_denormals_to_zero,
options::OPT_fno_cuda_flush_denormals_to_zero, false))
CC1Args.push_back("-fcuda-flush-denormals-to-zero");
if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
options::OPT_fno_cuda_approx_transcendentals, false))
CC1Args.push_back("-fcuda-approx-transcendentals");
}
if (DriverArgs.hasArg(options::OPT_nocudalib))
return;
std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(GpuArch);
if (LibDeviceFile.empty()) {
if (DeviceOffloadingKind == Action::OFK_OpenMP &&
DriverArgs.hasArg(options::OPT_S))
return;
getDriver().Diag(diag::err_drv_no_cuda_libdevice) << GpuArch;
return;
}
CC1Args.push_back("-mlink-cuda-bitcode");
CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
if (CudaInstallation.version() >= CudaVersion::CUDA_90) {
// CUDA-9 uses new instructions that are only available in PTX6.0
CC1Args.push_back("-target-feature");
CC1Args.push_back("+ptx60");
} else {
// Libdevice in CUDA-7.0 requires PTX version that's more recent
// than LLVM defaults to. Use PTX4.2 which is the PTX version that
// came with CUDA-7.0.
CC1Args.push_back("-target-feature");
CC1Args.push_back("+ptx42");
}
}
CudaInstallationDetector::CudaInstallationDetector(
const Driver &D, const llvm::Triple &HostTriple,
const llvm::opt::ArgList &Args)
: D(D) {
struct Candidate {
std::string Path;
bool StrictChecking;
Candidate(std::string Path, bool StrictChecking = false)
: Path(Path), StrictChecking(StrictChecking) {}
};
SmallVector<Candidate, 4> Candidates;
// In decreasing order so we prefer newer versions to older versions.
std::initializer_list<const char *> Versions = {"8.0", "7.5", "7.0"};
if (Args.hasArg(clang::driver::options::OPT_cuda_path_EQ)) {
Candidates.emplace_back(
Args.getLastArgValue(clang::driver::options::OPT_cuda_path_EQ).str());
} else if (HostTriple.isOSWindows()) {
for (const char *Ver : Versions)
Candidates.emplace_back(
D.SysRoot + "/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v" +
Ver);
} else {
if (!Args.hasArg(clang::driver::options::OPT_cuda_path_ignore_env)) {
// Try to find ptxas binary. If the executable is located in a directory
// called 'bin/', its parent directory might be a good guess for a valid
// CUDA installation.
// However, some distributions might installs 'ptxas' to /usr/bin. In that
// case the candidate would be '/usr' which passes the following checks
// because '/usr/include' exists as well. To avoid this case, we always
// check for the directory potentially containing files for libdevice,
// even if the user passes -nocudalib.
if (llvm::ErrorOr<std::string> ptxas =
llvm::sys::findProgramByName("ptxas")) {
SmallString<256> ptxasAbsolutePath;
llvm::sys::fs::real_path(*ptxas, ptxasAbsolutePath);
StringRef ptxasDir = llvm::sys::path::parent_path(ptxasAbsolutePath);
if (llvm::sys::path::filename(ptxasDir) == "bin")
Candidates.emplace_back(llvm::sys::path::parent_path(ptxasDir),
/*StrictChecking=*/true);
}
}
Candidates.emplace_back(D.SysRoot + "/usr/local/cuda");
for (const char *Ver : Versions)
Candidates.emplace_back(D.SysRoot + "/usr/local/cuda-" + Ver);
if (Distro(D.getVFS()).IsDebian())
// Special case for Debian to have nvidia-cuda-toolkit work
// out of the box. More info on http://bugs.debian.org/882505
Candidates.emplace_back(D.SysRoot + "/usr/lib/cuda");
}
bool NoCudaLib = Args.hasArg(options::OPT_nocudalib);
for (const auto &Candidate : Candidates) {
InstallPath = Candidate.Path;
if (InstallPath.empty() || !D.getVFS().exists(InstallPath))
continue;
BinPath = InstallPath + "/bin";
IncludePath = InstallPath + "/include";
LibDevicePath = InstallPath + "/nvvm/libdevice";
auto &FS = D.getVFS();
if (!(FS.exists(IncludePath) && FS.exists(BinPath)))
continue;
bool CheckLibDevice = (!NoCudaLib || Candidate.StrictChecking);
if (CheckLibDevice && !FS.exists(LibDevicePath))
continue;
// On Linux, we have both lib and lib64 directories, and we need to choose
// based on our triple. On MacOS, we have only a lib directory.
//
// It's sufficient for our purposes to be flexible: If both lib and lib64
// exist, we choose whichever one matches our triple. Otherwise, if only
// lib exists, we use it.
if (HostTriple.isArch64Bit() && FS.exists(InstallPath + "/lib64"))
LibPath = InstallPath + "/lib64";
else if (FS.exists(InstallPath + "/lib"))
LibPath = InstallPath + "/lib";
else
continue;
llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> VersionFile =
FS.getBufferForFile(InstallPath + "/version.txt");
if (!VersionFile) {
// CUDA 7.0 doesn't have a version.txt, so guess that's our version if
// version.txt isn't present.
Version = CudaVersion::CUDA_70;
} else {
Version = ParseCudaVersionFile((*VersionFile)->getBuffer());
}
if (Version >= CudaVersion::CUDA_90) {
// CUDA-9+ uses single libdevice file for all GPU variants.
std::string FilePath = LibDevicePath + "/libdevice.10.bc";
if (FS.exists(FilePath)) {
for (const char *GpuArchName :
{"sm_20", "sm_30", "sm_32", "sm_35", "sm_50", "sm_52", "sm_53",
"sm_60", "sm_61", "sm_62", "sm_70", "sm_72"}) {
const CudaArch GpuArch = StringToCudaArch(GpuArchName);
if (Version >= MinVersionForCudaArch(GpuArch) &&
Version <= MaxVersionForCudaArch(GpuArch))
LibDeviceMap[GpuArchName] = FilePath;
}
}
} else {
std::error_code EC;
for (llvm::sys::fs::directory_iterator LI(LibDevicePath, EC), LE;
!EC && LI != LE; LI = LI.increment(EC)) {
StringRef FilePath = LI->path();
StringRef FileName = llvm::sys::path::filename(FilePath);
// Process all bitcode filenames that look like
// libdevice.compute_XX.YY.bc
const StringRef LibDeviceName = "libdevice.";
if (!(FileName.startswith(LibDeviceName) && FileName.endswith(".bc")))
continue;
StringRef GpuArch = FileName.slice(
LibDeviceName.size(), FileName.find('.', LibDeviceName.size()));
LibDeviceMap[GpuArch] = FilePath.str();
// Insert map entries for specifc devices with this compute
// capability. NVCC's choice of the libdevice library version is
// rather peculiar and depends on the CUDA version.
if (GpuArch == "compute_20") {
LibDeviceMap["sm_20"] = FilePath;
LibDeviceMap["sm_21"] = FilePath;
LibDeviceMap["sm_32"] = FilePath;
} else if (GpuArch == "compute_30") {
LibDeviceMap["sm_30"] = FilePath;
if (Version < CudaVersion::CUDA_80) {
LibDeviceMap["sm_50"] = FilePath;
LibDeviceMap["sm_52"] = FilePath;
LibDeviceMap["sm_53"] = FilePath;
}
LibDeviceMap["sm_60"] = FilePath;
LibDeviceMap["sm_61"] = FilePath;
LibDeviceMap["sm_62"] = FilePath;
} else if (GpuArch == "compute_35") {
LibDeviceMap["sm_35"] = FilePath;
LibDeviceMap["sm_37"] = FilePath;
} else if (GpuArch == "compute_50") {
if (Version >= CudaVersion::CUDA_80) {
LibDeviceMap["sm_50"] = FilePath;
LibDeviceMap["sm_52"] = FilePath;
LibDeviceMap["sm_53"] = FilePath;
}
}
}
}
// Check that we have found at least one libdevice that we can link in if
// -nocudalib hasn't been specified.
if (LibDeviceMap.empty() && !NoCudaLib)
continue;
IsValid = true;
break;
}
}
CudaInstallationDetector::CudaInstallationDetector(
const Driver &D, const llvm::Triple &HostTriple,
const llvm::opt::ArgList &Args)
: D(D) {
SmallVector<std::string, 4> CudaPathCandidates;
// In decreasing order so we prefer newer versions to older versions.
std::initializer_list<const char *> Versions = {"8.0", "7.5", "7.0"};
if (Args.hasArg(clang::driver::options::OPT_cuda_path_EQ)) {
CudaPathCandidates.push_back(
Args.getLastArgValue(clang::driver::options::OPT_cuda_path_EQ));
} else if (HostTriple.isOSWindows()) {
for (const char *Ver : Versions)
CudaPathCandidates.push_back(
D.SysRoot + "/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v" +
Ver);
} else {
CudaPathCandidates.push_back(D.SysRoot + "/usr/local/cuda");
for (const char *Ver : Versions)
CudaPathCandidates.push_back(D.SysRoot + "/usr/local/cuda-" + Ver);
}
for (const auto &CudaPath : CudaPathCandidates) {
if (CudaPath.empty() || !D.getVFS().exists(CudaPath))
continue;
InstallPath = CudaPath;
BinPath = CudaPath + "/bin";
IncludePath = InstallPath + "/include";
LibDevicePath = InstallPath + "/nvvm/libdevice";
auto &FS = D.getVFS();
if (!(FS.exists(IncludePath) && FS.exists(BinPath) &&
FS.exists(LibDevicePath)))
continue;
// On Linux, we have both lib and lib64 directories, and we need to choose
// based on our triple. On MacOS, we have only a lib directory.
//
// It's sufficient for our purposes to be flexible: If both lib and lib64
// exist, we choose whichever one matches our triple. Otherwise, if only
// lib exists, we use it.
if (HostTriple.isArch64Bit() && FS.exists(InstallPath + "/lib64"))
LibPath = InstallPath + "/lib64";
else if (FS.exists(InstallPath + "/lib"))
LibPath = InstallPath + "/lib";
else
continue;
llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> VersionFile =
FS.getBufferForFile(InstallPath + "/version.txt");
if (!VersionFile) {
// CUDA 7.0 doesn't have a version.txt, so guess that's our version if
// version.txt isn't present.
Version = CudaVersion::CUDA_70;
} else {
Version = ParseCudaVersionFile((*VersionFile)->getBuffer());
}
std::error_code EC;
for (llvm::sys::fs::directory_iterator LI(LibDevicePath, EC), LE;
!EC && LI != LE; LI = LI.increment(EC)) {
StringRef FilePath = LI->path();
StringRef FileName = llvm::sys::path::filename(FilePath);
// Process all bitcode filenames that look like libdevice.compute_XX.YY.bc
const StringRef LibDeviceName = "libdevice.";
if (!(FileName.startswith(LibDeviceName) && FileName.endswith(".bc")))
continue;
StringRef GpuArch = FileName.slice(
LibDeviceName.size(), FileName.find('.', LibDeviceName.size()));
LibDeviceMap[GpuArch] = FilePath.str();
// Insert map entries for specifc devices with this compute
// capability. NVCC's choice of the libdevice library version is
// rather peculiar and depends on the CUDA version.
if (GpuArch == "compute_20") {
LibDeviceMap["sm_20"] = FilePath;
LibDeviceMap["sm_21"] = FilePath;
LibDeviceMap["sm_32"] = FilePath;
} else if (GpuArch == "compute_30") {
LibDeviceMap["sm_30"] = FilePath;
if (Version < CudaVersion::CUDA_80) {
LibDeviceMap["sm_50"] = FilePath;
LibDeviceMap["sm_52"] = FilePath;
LibDeviceMap["sm_53"] = FilePath;
}
LibDeviceMap["sm_60"] = FilePath;
LibDeviceMap["sm_61"] = FilePath;
LibDeviceMap["sm_62"] = FilePath;
} else if (GpuArch == "compute_35") {
LibDeviceMap["sm_35"] = FilePath;
LibDeviceMap["sm_37"] = FilePath;
} else if (GpuArch == "compute_50") {
if (Version >= CudaVersion::CUDA_80) {
LibDeviceMap["sm_50"] = FilePath;
LibDeviceMap["sm_52"] = FilePath;
LibDeviceMap["sm_53"] = FilePath;
}
}
}
IsValid = true;
break;
}
}
void CudaToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args,
Action::OffloadKind DeviceOffloadingKind) const {
HostTC.addClangTargetOptions(DriverArgs, CC1Args, DeviceOffloadingKind);
StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
assert((DeviceOffloadingKind == Action::OFK_OpenMP ||
DeviceOffloadingKind == Action::OFK_Cuda) &&
"Only OpenMP or CUDA offloading kinds are supported for NVIDIA GPUs.");
if (DeviceOffloadingKind == Action::OFK_Cuda) {
CC1Args.push_back("-fcuda-is-device");
if (DriverArgs.hasFlag(options::OPT_fcuda_flush_denormals_to_zero,
options::OPT_fno_cuda_flush_denormals_to_zero, false))
CC1Args.push_back("-fcuda-flush-denormals-to-zero");
if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
options::OPT_fno_cuda_approx_transcendentals, false))
CC1Args.push_back("-fcuda-approx-transcendentals");
if (DriverArgs.hasFlag(options::OPT_fcuda_rdc, options::OPT_fno_cuda_rdc,
false))
CC1Args.push_back("-fcuda-rdc");
}
if (DriverArgs.hasArg(options::OPT_nocudalib))
return;
std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(GpuArch);
if (LibDeviceFile.empty()) {
if (DeviceOffloadingKind == Action::OFK_OpenMP &&
DriverArgs.hasArg(options::OPT_S))
return;
getDriver().Diag(diag::err_drv_no_cuda_libdevice) << GpuArch;
return;
}
CC1Args.push_back("-mlink-cuda-bitcode");
CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
// Libdevice in CUDA-7.0 requires PTX version that's more recent than LLVM
// defaults to. Use PTX4.2 by default, which is the PTX version that came with
// CUDA-7.0.
const char *PtxFeature = "+ptx42";
if (CudaInstallation.version() >= CudaVersion::CUDA_91) {
// CUDA-9.1 uses new instructions that are only available in PTX6.1+
PtxFeature = "+ptx61";
} else if (CudaInstallation.version() >= CudaVersion::CUDA_90) {
// CUDA-9.0 uses new instructions that are only available in PTX6.0+
PtxFeature = "+ptx60";
}
CC1Args.append({"-target-feature", PtxFeature});
if (DriverArgs.hasFlag(options::OPT_fcuda_short_ptr,
options::OPT_fno_cuda_short_ptr, false))
CC1Args.append({"-mllvm", "--nvptx-short-ptr"});
if (DeviceOffloadingKind == Action::OFK_OpenMP) {
SmallVector<StringRef, 8> LibraryPaths;
// Add path to lib and/or lib64 folders.
SmallString<256> DefaultLibPath =
llvm::sys::path::parent_path(getDriver().Dir);
llvm::sys::path::append(DefaultLibPath,
Twine("lib") + CLANG_LIBDIR_SUFFIX);
LibraryPaths.emplace_back(DefaultLibPath.c_str());
// Add user defined library paths from LIBRARY_PATH.
llvm::Optional<std::string> LibPath =
llvm::sys::Process::GetEnv("LIBRARY_PATH");
if (LibPath) {
SmallVector<StringRef, 8> Frags;
const char EnvPathSeparatorStr[] = {llvm::sys::EnvPathSeparator, '\0'};
llvm::SplitString(*LibPath, Frags, EnvPathSeparatorStr);
for (StringRef Path : Frags)
LibraryPaths.emplace_back(Path.trim());
}
std::string LibOmpTargetName =
"libomptarget-nvptx-" + GpuArch.str() + ".bc";
bool FoundBCLibrary = false;
for (StringRef LibraryPath : LibraryPaths) {
SmallString<128> LibOmpTargetFile(LibraryPath);
llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
if (llvm::sys::fs::exists(LibOmpTargetFile)) {
CC1Args.push_back("-mlink-cuda-bitcode");
CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
FoundBCLibrary = true;
break;
}
}
if (!FoundBCLibrary)
getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime)
<< LibOmpTargetName;
}
}