Files
clang-p2996/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
Joseph Huber 12e8e0b10c [AMDGPU] Correctly use the auxiliary toolchain to include libc++ (#109366)
Summary:
Now that we have a functional build for `libc++` on the GPU, it will now
find the target specific headers in `include/amdgcn-amd-amdhsa`. This is
a problem for offloading via OpenMP because we need the CPU and GPU
headers to match exactly. All the other toolchains forward this
correctly except the AMDGPU OpenMP one, fix this by overriding it to use
the host toolchain instead of the device one, so the triple is not
returned as `amdgcn-amd-amdhsa`.
2024-09-20 09:29:59 -07:00

177 lines
6.1 KiB
C++

//===- AMDGPUOpenMP.cpp - AMDGPUOpenMP ToolChain Implementation -*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "AMDGPUOpenMP.h"
#include "AMDGPU.h"
#include "CommonArgs.h"
#include "ToolChains/ROCm.h"
#include "clang/Basic/DiagnosticDriver.h"
#include "clang/Driver/Compilation.h"
#include "clang/Driver/Driver.h"
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/InputInfo.h"
#include "clang/Driver/Options.h"
#include "clang/Driver/Tool.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/FormatAdapters.h"
#include "llvm/Support/FormatVariadic.h"
#include "llvm/Support/Path.h"
using namespace clang::driver;
using namespace clang::driver::toolchains;
using namespace clang::driver::tools;
using namespace clang;
using namespace llvm::opt;
AMDGPUOpenMPToolChain::AMDGPUOpenMPToolChain(const Driver &D,
const llvm::Triple &Triple,
const ToolChain &HostTC,
const ArgList &Args)
: ROCMToolChain(D, Triple, Args), HostTC(HostTC) {
// Lookup binaries into the driver directory, this is used to
// discover the 'amdgpu-arch' executable.
getProgramPaths().push_back(getDriver().Dir);
}
void AMDGPUOpenMPToolChain::addClangTargetOptions(
const llvm::opt::ArgList &DriverArgs, llvm::opt::ArgStringList &CC1Args,
Action::OffloadKind DeviceOffloadingKind) const {
HostTC.addClangTargetOptions(DriverArgs, CC1Args, DeviceOffloadingKind);
assert(DeviceOffloadingKind == Action::OFK_OpenMP &&
"Only OpenMP offloading kinds are supported.");
if (DriverArgs.hasArg(options::OPT_nogpulib))
return;
for (auto BCFile : getDeviceLibs(DriverArgs)) {
CC1Args.push_back(BCFile.ShouldInternalize ? "-mlink-builtin-bitcode"
: "-mlink-bitcode-file");
CC1Args.push_back(DriverArgs.MakeArgString(BCFile.Path));
}
// Link the bitcode library late if we're using device LTO.
if (getDriver().isUsingOffloadLTO())
return;
}
llvm::opt::DerivedArgList *AMDGPUOpenMPToolChain::TranslateArgs(
const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
Action::OffloadKind DeviceOffloadKind) const {
DerivedArgList *DAL =
HostTC.TranslateArgs(Args, BoundArch, DeviceOffloadKind);
if (!DAL)
DAL = new DerivedArgList(Args.getBaseArgs());
const OptTable &Opts = getDriver().getOpts();
if (DeviceOffloadKind == Action::OFK_OpenMP) {
for (Arg *A : Args)
if (!llvm::is_contained(*DAL, A))
DAL->append(A);
if (!DAL->hasArg(options::OPT_march_EQ)) {
StringRef Arch = BoundArch;
if (Arch.empty()) {
auto ArchsOrErr = getSystemGPUArchs(Args);
if (!ArchsOrErr) {
std::string ErrMsg =
llvm::formatv("{0}", llvm::fmt_consume(ArchsOrErr.takeError()));
getDriver().Diag(diag::err_drv_undetermined_gpu_arch)
<< llvm::Triple::getArchTypeName(getArch()) << ErrMsg << "-march";
Arch = OffloadArchToString(OffloadArch::HIPDefault);
} else {
Arch = Args.MakeArgString(ArchsOrErr->front());
}
}
DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), Arch);
}
return DAL;
}
for (Arg *A : Args) {
DAL->append(A);
}
if (!BoundArch.empty()) {
DAL->eraseArg(options::OPT_march_EQ);
DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ),
BoundArch);
}
return DAL;
}
void AMDGPUOpenMPToolChain::addClangWarningOptions(
ArgStringList &CC1Args) const {
AMDGPUToolChain::addClangWarningOptions(CC1Args);
HostTC.addClangWarningOptions(CC1Args);
}
ToolChain::CXXStdlibType
AMDGPUOpenMPToolChain::GetCXXStdlibType(const ArgList &Args) const {
return HostTC.GetCXXStdlibType(Args);
}
void AMDGPUOpenMPToolChain::AddClangCXXStdlibIncludeArgs(
const llvm::opt::ArgList &Args, llvm::opt::ArgStringList &CC1Args) const {
HostTC.AddClangCXXStdlibIncludeArgs(Args, CC1Args);
}
void AMDGPUOpenMPToolChain::AddClangSystemIncludeArgs(
const ArgList &DriverArgs, ArgStringList &CC1Args) const {
HostTC.AddClangSystemIncludeArgs(DriverArgs, CC1Args);
}
void AMDGPUOpenMPToolChain::AddIAMCUIncludeArgs(const ArgList &Args,
ArgStringList &CC1Args) const {
HostTC.AddIAMCUIncludeArgs(Args, CC1Args);
}
SanitizerMask AMDGPUOpenMPToolChain::getSupportedSanitizers() const {
// The AMDGPUOpenMPToolChain only supports sanitizers in the sense that it
// allows sanitizer arguments on the command line if they are supported by the
// host toolchain. The AMDGPUOpenMPToolChain will actually ignore any command
// line arguments for any of these "supported" sanitizers. That means that no
// sanitization of device code is actually supported at this time.
//
// This behavior is necessary because the host and device toolchains
// invocations often share the command line, so the device toolchain must
// tolerate flags meant only for the host toolchain.
return HostTC.getSupportedSanitizers();
}
VersionTuple
AMDGPUOpenMPToolChain::computeMSVCVersion(const Driver *D,
const ArgList &Args) const {
return HostTC.computeMSVCVersion(D, Args);
}
llvm::SmallVector<ToolChain::BitCodeLibraryInfo, 12>
AMDGPUOpenMPToolChain::getDeviceLibs(const llvm::opt::ArgList &Args) const {
if (Args.hasArg(options::OPT_nogpulib))
return {};
if (!RocmInstallation->hasDeviceLibrary()) {
getDriver().Diag(diag::err_drv_no_rocm_device_lib) << 0;
return {};
}
StringRef GpuArch = getProcessorFromTargetID(
getTriple(), Args.getLastArgValue(options::OPT_march_EQ));
SmallVector<BitCodeLibraryInfo, 12> BCLibs;
for (auto BCLib : getCommonDeviceLibNames(Args, GpuArch.str(),
/*IsOpenMP=*/true))
BCLibs.emplace_back(BCLib);
return BCLibs;
}