[clang] [Clang][SYCL] Introduce clang-sycl-link-wrapper to link SYCL offloading device code (Part 1 of many) (PR #112245)

[Joseph Huber via cfe-commits]

================
@@ -0,0 +1,528 @@
+//=-- clang-sycl-link-wrapper/ClangSYCLLinkWrapper.cpp - SYCL linker util --=//
+//
+// 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
+//
+//===---------------------------------------------------------------------===//
+//
+// This tool wraps around the sequence of steps required to link device code in
+// SYCL fat objects. SYCL device code linking requires a complex sequence of
+// steps that include linking of llvm bitcode files, linking device library
+// files with the fully linked source bitcode file(s), running several SYCL
+// specific post-link steps on the fully linked bitcode file(s), and finally
+// generating target-specific device code. This tool can be removed once SYCL
+// linking is ported to `ld.lld`.
+//
+//===---------------------------------------------------------------------===//
+
+#include "clang/Basic/Version.h"
+
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/BinaryFormat/Magic.h"
+#include "llvm/Bitcode/BitcodeWriter.h"
+#include "llvm/CodeGen/CommandFlags.h"
+#include "llvm/IR/DiagnosticPrinter.h"
+#include "llvm/IRReader/IRReader.h"
+#include "llvm/LTO/LTO.h"
+#include "llvm/Object/Archive.h"
+#include "llvm/Object/ArchiveWriter.h"
+#include "llvm/Object/Binary.h"
+#include "llvm/Object/ELFObjectFile.h"
+#include "llvm/Object/IRObjectFile.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Object/OffloadBinary.h"
+#include "llvm/Option/ArgList.h"
+#include "llvm/Option/OptTable.h"
+#include "llvm/Option/Option.h"
+#include "llvm/Remarks/HotnessThresholdParser.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/FileOutputBuffer.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/InitLLVM.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/Program.h"
+#include "llvm/Support/Signals.h"
+#include "llvm/Support/StringSaver.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/TimeProfiler.h"
+#include "llvm/Support/WithColor.h"
+
+using namespace llvm;
+using namespace llvm::opt;
+using namespace llvm::object;
+
+/// Save intermediary results.
+static bool SaveTemps = false;
+
+/// Print arguments without executing.
+static bool DryRun = false;
+
+/// Print verbose output.
+static bool Verbose = false;
+
+/// Filename of the output being created.
+static StringRef OutputFile;
+
+/// Directory to dump SPIR-V IR if requested by user.
+static SmallString<128> SPIRVDumpDir;
+
+static void printVersion(raw_ostream &OS) {
+  OS << clang::getClangToolFullVersion("clang-sycl-link-wrapper") << '\n';
+}
+
+/// The value of `argv[0]` when run.
+static const char *Executable;
+
+/// Temporary files to be cleaned up.
+static SmallVector<SmallString<128>> TempFiles;
+
+namespace {
+// Must not overlap with llvm::opt::DriverFlag.
+enum WrapperFlags { WrapperOnlyOption = (1 << 4) };
+
+enum ID {
+  OPT_INVALID = 0, // This is not an option ID.
+#define OPTION(...) LLVM_MAKE_OPT_ID(__VA_ARGS__),
+#include "SYCLLinkOpts.inc"
+  LastOption
+#undef OPTION
+};
+
+#define PREFIX(NAME, VALUE)                                                    \
+  static constexpr StringLiteral NAME##_init[] = VALUE;                        \
+  static constexpr ArrayRef<StringLiteral> NAME(NAME##_init,                   \
+                                                std::size(NAME##_init) - 1);
+#include "SYCLLinkOpts.inc"
+#undef PREFIX
+
+static constexpr OptTable::Info InfoTable[] = {
+#define OPTION(...) LLVM_CONSTRUCT_OPT_INFO(__VA_ARGS__),
+#include "SYCLLinkOpts.inc"
+#undef OPTION
+};
+
+class WrapperOptTable : public opt::GenericOptTable {
+public:
+  WrapperOptTable() : opt::GenericOptTable(InfoTable) {}
+};
+
+const OptTable &getOptTable() {
+  static const WrapperOptTable *Table = []() {
+    auto Result = std::make_unique<WrapperOptTable>();
+    return Result.release();
+  }();
+  return *Table;
+}
+
+[[noreturn]] void reportError(Error E) {
+  outs().flush();
+  logAllUnhandledErrors(std::move(E), WithColor::error(errs(), Executable));
+  exit(EXIT_FAILURE);
+}
+
+std::string getMainExecutable(const char *Name) {
+  void *Ptr = (void *)(intptr_t)&getMainExecutable;
+  auto COWPath = sys::fs::getMainExecutable(Name, Ptr);
+  return sys::path::parent_path(COWPath).str();
+}
+
+Expected<StringRef> createTempFile(const ArgList &Args, const Twine &Prefix,
+                                   StringRef Extension) {
+  SmallString<128> OutputFile;
+  if (Args.hasArg(OPT_save_temps)) {
+    // Generate a unique path name without creating a file
+    sys::fs::createUniquePath(Prefix + "-%%%%%%." + Extension, OutputFile,
+                              /*MakeAbsolute=*/false);
+  } else {
+    if (std::error_code EC =
+            sys::fs::createTemporaryFile(Prefix, Extension, OutputFile))
+      return createFileError(OutputFile, EC);
+  }
+
+  TempFiles.emplace_back(std::move(OutputFile));
+  return TempFiles.back();
+}
+
+Expected<std::string> findProgram(const ArgList &Args, StringRef Name,
+                                  ArrayRef<StringRef> Paths) {
+  if (Args.hasArg(OPT_dry_run))
+    return Name.str();
+  ErrorOr<std::string> Path = sys::findProgramByName(Name, Paths);
+  if (!Path)
+    Path = sys::findProgramByName(Name);
+  if (!Path)
+    return createStringError(Path.getError(),
+                             "Unable to find '" + Name + "' in path");
+  return *Path;
+}
+
+std::optional<std::string> findFile(StringRef Dir, StringRef Root,
+                                    const Twine &Name) {
+  SmallString<128> Path;
+  if (Dir.starts_with("="))
+    sys::path::append(Path, Root, Dir.substr(1), Name);
+  else
+    sys::path::append(Path, Dir, Name);
+
+  if (sys::fs::exists(Path))
+    return static_cast<std::string>(Path);
+  return std::nullopt;
+}
+
+void printCommands(ArrayRef<StringRef> CmdArgs) {
+  if (CmdArgs.empty())
+    return;
+
+  llvm::errs() << " \"" << CmdArgs.front() << "\" ";
+  llvm::errs() << llvm::join(std::next(CmdArgs.begin()), CmdArgs.end(), " ")
+               << "\n";
+}
+
+/// Execute the command \p ExecutablePath with the arguments \p Args.
+Error executeCommands(StringRef ExecutablePath, ArrayRef<StringRef> Args) {
+  if (Verbose || DryRun)
+    printCommands(Args);
+
+  if (!DryRun)
+    if (sys::ExecuteAndWait(ExecutablePath, Args))
+      return createStringError(
+          "'%s' failed", sys::path::filename(ExecutablePath).str().c_str());
+  return Error::success();
+}
+
+Expected<SmallVector<std::string>> getInput(const ArgList &Args) {
+  // Collect all input bitcode files to be passed to llvm-link.
+  SmallVector<std::string> BitcodeFiles;
+  for (const opt::Arg *Arg : Args.filtered(OPT_INPUT)) {
+    std::optional<std::string> Filename = std::string(Arg->getValue());
+    if (!Filename || !sys::fs::exists(*Filename) ||
+        sys::fs::is_directory(*Filename))
+      continue;
+    file_magic Magic;
+    if (auto EC = identify_magic(*Filename, Magic))
+      return createStringError("Failed to open file " + *Filename);
+    if (Magic != file_magic::bitcode)
+      return createStringError("Unsupported file type");
+    BitcodeFiles.push_back(*Filename);
+  }
+  return BitcodeFiles;
+}
+
+/// Link all SYCL device input files into one before adding device library
+/// files. Device linking is performed using llvm-link tool.
+/// 'InputFiles' is the list of all LLVM IR device input files.
+/// 'Args' encompasses all arguments required for linking and wrapping device
+/// code and will be parsed to generate options required to be passed into the
+/// llvm-link tool.
+Expected<StringRef> linkDeviceInputFiles(ArrayRef<std::string> InputFiles,
+                                         const ArgList &Args) {
+  llvm::TimeTraceScope TimeScope("SYCL LinkDeviceInputFiles");
+  Expected<std::string> LLVMLinkPath =
+      findProgram(Args, "llvm-link", {getMainExecutable("llvm-link")});
+  if (!LLVMLinkPath)
+    return LLVMLinkPath.takeError();
+
+  SmallVector<StringRef> CmdArgs;
+  CmdArgs.push_back(*LLVMLinkPath);
+  for (auto &File : InputFiles)
+    CmdArgs.push_back(File);
+  // Create a new file to write the linked device file to.
+  auto OutFileOrErr =
+      createTempFile(Args, sys::path::filename(OutputFile), "bc");
+  if (!OutFileOrErr)
+    return OutFileOrErr.takeError();
+  CmdArgs.push_back("-o");
+  CmdArgs.push_back(*OutFileOrErr);
+  CmdArgs.push_back("--suppress-warnings");
+  if (Error Err = executeCommands(*LLVMLinkPath, CmdArgs))
+    return std::move(Err);
+  return *OutFileOrErr;
+}
+
+const SmallVector<std::string> SYCLDeviceLibNames = {
----------------
jhuber6 wrote:

If these are part of the ToolChain they should be passed in by default when the `clang-sycl-linker` is created. Pretty similar to the CUDA libdevice and ROCm Device Libs except we're doing it at the link step instead of hacking it in per TU with `-mlink-builtin-bitcode`. Same reason that `clang` is responsible for putting `-lc` in the link job and not `ld.lld`.

https://github.com/llvm/llvm-project/pull/112245