[ThinLTO][NFC] Refactor ThinBackend (#110461)

kyulee-com · web-flow · commit 1b53aaec55b6 · 2024-10-07T22:24:04.000-07:00
This is a prep for #90933. - Change `ThinBackend` from a function to a type. - Store the parallelism level in the type, which will be used when creating two-codegen round backends that inherit this value. - `ThinBackendProc` is hoisted to `LTO.h` from `LTO.cpp` to provide its body for `ThinBackend`. However, `emitFiles()` is still implemented separately in `LTO.cpp`, distinct from its parent class.
diff --git a/llvm/include/llvm/LTO/LTO.h b/llvm/include/llvm/LTO/LTO.h
@@ -26,6 +26,7 @@
 #include "llvm/Support/Caching.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/StringSaver.h"
+#include "llvm/Support/ThreadPool.h"
 #include "llvm/Support/thread.h"
 #include "llvm/Transforms/IPO/FunctionAttrs.h"
 #include "llvm/Transforms/IPO/FunctionImport.h"
@@ -105,7 +106,6 @@ void updateMemProfAttributes(Module &Mod, const ModuleSummaryIndex &Index);
 
 class LTO;
 struct SymbolResolution;
-class ThinBackendProc;
 
 /// An input file. This is a symbol table wrapper that only exposes the
 /// information that an LTO client should need in order to do symbol resolution.
@@ -194,14 +194,90 @@ class InputFile {
   }
 };
 
-/// A ThinBackend defines what happens after the thin-link phase during ThinLTO.
-/// The details of this type definition aren't important; clients can only
-/// create a ThinBackend using one of the create*ThinBackend() functions below.
-using ThinBackend = std::function<std::unique_ptr<ThinBackendProc>(
+using IndexWriteCallback = std::function<void(const std::string &)>;
+
+/// This class defines the interface to the ThinLTO backend.
+class ThinBackendProc {
+protected:
+  const Config &Conf;
+  ModuleSummaryIndex &CombinedIndex;
+  const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries;
+  IndexWriteCallback OnWrite;
+  bool ShouldEmitImportsFiles;
+  DefaultThreadPool BackendThreadPool;
+  std::optional<Error> Err;
+  std::mutex ErrMu;
+
+public:
+  ThinBackendProc(
+      const Config &Conf, ModuleSummaryIndex &CombinedIndex,
+      const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
+      lto::IndexWriteCallback OnWrite, bool ShouldEmitImportsFiles,
+      ThreadPoolStrategy ThinLTOParallelism)
+      : Conf(Conf), CombinedIndex(CombinedIndex),
+        ModuleToDefinedGVSummaries(ModuleToDefinedGVSummaries),
+        OnWrite(OnWrite), ShouldEmitImportsFiles(ShouldEmitImportsFiles),
+        BackendThreadPool(ThinLTOParallelism) {}
+
+  virtual ~ThinBackendProc() = default;
+  virtual Error start(
+      unsigned Task, BitcodeModule BM,
+      const FunctionImporter::ImportMapTy &ImportList,
+      const FunctionImporter::ExportSetTy &ExportList,
+      const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
+      MapVector<StringRef, BitcodeModule> &ModuleMap) = 0;
+  Error wait() {
+    BackendThreadPool.wait();
+    if (Err)
+      return std::move(*Err);
+    return Error::success();
+  }
+  unsigned getThreadCount() { return BackendThreadPool.getMaxConcurrency(); }
+  virtual bool isSensitiveToInputOrder() { return false; }
+
+  // Write sharded indices and (optionally) imports to disk
+  Error emitFiles(const FunctionImporter::ImportMapTy &ImportList,
+                  llvm::StringRef ModulePath,
+                  const std::string &NewModulePath) const;
+};
+
+/// This callable defines the behavior of a ThinLTO backend after the thin-link
+/// phase. It accepts a configuration \p C, a combined module summary index
+/// \p CombinedIndex, a map of module identifiers to global variable summaries
+/// \p ModuleToDefinedGVSummaries, a function to add output streams \p
+/// AddStream, and a file cache \p Cache. It returns a unique pointer to a
+/// ThinBackendProc, which can be used to launch backends in parallel.
+using ThinBackendFunction = std::function<std::unique_ptr<ThinBackendProc>(
     const Config &C, ModuleSummaryIndex &CombinedIndex,
-    DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
+    const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
     AddStreamFn AddStream, FileCache Cache)>;
 
+/// This type defines the behavior following the thin-link phase during ThinLTO.
+/// It encapsulates a backend function and a strategy for thread pool
+/// parallelism. Clients should use one of the provided create*ThinBackend()
+/// functions to instantiate a ThinBackend. Parallelism defines the thread pool
+/// strategy to be used for processing.
+struct ThinBackend {
+  ThinBackend(ThinBackendFunction Func, ThreadPoolStrategy Parallelism)
+      : Func(std::move(Func)), Parallelism(std::move(Parallelism)) {}
+  ThinBackend() = default;
+
+  std::unique_ptr<ThinBackendProc> operator()(
+      const Config &Conf, ModuleSummaryIndex &CombinedIndex,
+      const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
+      AddStreamFn AddStream, FileCache Cache) {
+    assert(isValid() && "Invalid backend function");
+    return Func(Conf, CombinedIndex, ModuleToDefinedGVSummaries,
+                std::move(AddStream), std::move(Cache));
+  }
+  ThreadPoolStrategy getParallelism() const { return Parallelism; }
+  bool isValid() const { return static_cast<bool>(Func); }
+
+private:
+  ThinBackendFunction Func = nullptr;
+  ThreadPoolStrategy Parallelism;
+};
+
 /// This ThinBackend runs the individual backend jobs in-process.
 /// The default value means to use one job per hardware core (not hyper-thread).
 /// OnWrite is callback which receives module identifier and notifies LTO user
@@ -210,7 +286,6 @@ using ThinBackend = std::function<std::unique_ptr<ThinBackendProc>(
 /// to the same path as the input module, with suffix ".thinlto.bc"
 /// ShouldEmitImportsFiles is true it also writes a list of imported files to a
 /// similar path with ".imports" appended instead.
-using IndexWriteCallback = std::function<void(const std::string &)>;
 ThinBackend createInProcessThinBackend(ThreadPoolStrategy Parallelism,
                                        IndexWriteCallback OnWrite = nullptr,
                                        bool ShouldEmitIndexFiles = false,
@@ -276,7 +351,7 @@ class LTO {
   /// this constructor.
   /// FIXME: We do currently require the DiagHandler field to be set in Conf.
   /// Until that is fixed, a Config argument is required.
-  LTO(Config Conf, ThinBackend Backend = nullptr,
+  LTO(Config Conf, ThinBackend Backend = {},
       unsigned ParallelCodeGenParallelismLevel = 1,
       LTOKind LTOMode = LTOK_Default);
   ~LTO();
diff --git a/llvm/lib/LTO/LTO.cpp b/llvm/lib/LTO/LTO.cpp
@@ -578,10 +578,10 @@ LTO::RegularLTOState::RegularLTOState(unsigned ParallelCodeGenParallelismLevel,
   CombinedModule->IsNewDbgInfoFormat = UseNewDbgInfoFormat;
 }
 
-LTO::ThinLTOState::ThinLTOState(ThinBackend Backend)
-    : Backend(Backend), CombinedIndex(/*HaveGVs*/ false) {
-  if (!Backend)
-    this->Backend =
+LTO::ThinLTOState::ThinLTOState(ThinBackend BackendParam)
+    : Backend(std::move(BackendParam)), CombinedIndex(/*HaveGVs*/ false) {
+  if (!Backend.isValid())
+    Backend =
         createInProcessThinBackend(llvm::heavyweight_hardware_concurrency());
 }
 
@@ -1368,75 +1368,33 @@ SmallVector<const char *> LTO::getRuntimeLibcallSymbols(const Triple &TT) {
   return LibcallSymbols;
 }
 
-/// This class defines the interface to the ThinLTO backend.
-class lto::ThinBackendProc {
-protected:
-  const Config &Conf;
-  ModuleSummaryIndex &CombinedIndex;
-  const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries;
-  lto::IndexWriteCallback OnWrite;
-  bool ShouldEmitImportsFiles;
-  DefaultThreadPool BackendThreadPool;
-  std::optional<Error> Err;
-  std::mutex ErrMu;
+Error ThinBackendProc::emitFiles(
+    const FunctionImporter::ImportMapTy &ImportList, llvm::StringRef ModulePath,
+    const std::string &NewModulePath) const {
+  ModuleToSummariesForIndexTy ModuleToSummariesForIndex;
+  GVSummaryPtrSet DeclarationSummaries;
 
-public:
-  ThinBackendProc(
-      const Config &Conf, ModuleSummaryIndex &CombinedIndex,
-      const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
-      lto::IndexWriteCallback OnWrite, bool ShouldEmitImportsFiles,
-      ThreadPoolStrategy ThinLTOParallelism)
-      : Conf(Conf), CombinedIndex(CombinedIndex),
-        ModuleToDefinedGVSummaries(ModuleToDefinedGVSummaries),
-        OnWrite(OnWrite), ShouldEmitImportsFiles(ShouldEmitImportsFiles),
-        BackendThreadPool(ThinLTOParallelism) {}
-
-  virtual ~ThinBackendProc() = default;
-  virtual Error start(
-      unsigned Task, BitcodeModule BM,
-      const FunctionImporter::ImportMapTy &ImportList,
-      const FunctionImporter::ExportSetTy &ExportList,
-      const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
-      MapVector<StringRef, BitcodeModule> &ModuleMap) = 0;
-  Error wait() {
-    BackendThreadPool.wait();
-    if (Err)
-      return std::move(*Err);
-    return Error::success();
-  }
-  unsigned getThreadCount() { return BackendThreadPool.getMaxConcurrency(); }
-  virtual bool isSensitiveToInputOrder() { return false; }
-
-  // Write sharded indices and (optionally) imports to disk
-  Error emitFiles(const FunctionImporter::ImportMapTy &ImportList,
-                  llvm::StringRef ModulePath,
-                  const std::string &NewModulePath) const {
-    ModuleToSummariesForIndexTy ModuleToSummariesForIndex;
-    GVSummaryPtrSet DeclarationSummaries;
-
-    std::error_code EC;
-    gatherImportedSummariesForModule(ModulePath, ModuleToDefinedGVSummaries,
-                                     ImportList, ModuleToSummariesForIndex,
-                                     DeclarationSummaries);
-
-    raw_fd_ostream OS(NewModulePath + ".thinlto.bc", EC,
-                      sys::fs::OpenFlags::OF_None);
-    if (EC)
-      return createFileError("cannot open " + NewModulePath + ".thinlto.bc",
-                             EC);
-
-    writeIndexToFile(CombinedIndex, OS, &ModuleToSummariesForIndex,
-                     &DeclarationSummaries);
-
-    if (ShouldEmitImportsFiles) {
-      Error ImportFilesError = EmitImportsFiles(
-          ModulePath, NewModulePath + ".imports", ModuleToSummariesForIndex);
-      if (ImportFilesError)
-        return ImportFilesError;
-    }
-    return Error::success();
+  std::error_code EC;
+  gatherImportedSummariesForModule(ModulePath, ModuleToDefinedGVSummaries,
+                                   ImportList, ModuleToSummariesForIndex,
+                                   DeclarationSummaries);
+
+  raw_fd_ostream OS(NewModulePath + ".thinlto.bc", EC,
+                    sys::fs::OpenFlags::OF_None);
+  if (EC)
+    return createFileError("cannot open " + NewModulePath + ".thinlto.bc", EC);
+
+  writeIndexToFile(CombinedIndex, OS, &ModuleToSummariesForIndex,
+                   &DeclarationSummaries);
+
+  if (ShouldEmitImportsFiles) {
+    Error ImportFilesError = EmitImportsFiles(
+        ModulePath, NewModulePath + ".imports", ModuleToSummariesForIndex);
+    if (ImportFilesError)
+      return ImportFilesError;
   }
-};
+  return Error::success();
+}
 
 namespace {
 class InProcessThinBackend : public ThinBackendProc {
@@ -1561,7 +1519,7 @@ ThinBackend lto::createInProcessThinBackend(ThreadPoolStrategy Parallelism,
                                             lto::IndexWriteCallback OnWrite,
                                             bool ShouldEmitIndexFiles,
                                             bool ShouldEmitImportsFiles) {
-  return
+  auto Func =
       [=](const Config &Conf, ModuleSummaryIndex &CombinedIndex,
           const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
           AddStreamFn AddStream, FileCache Cache) {
@@ -1570,6 +1528,7 @@ ThinBackend lto::createInProcessThinBackend(ThreadPoolStrategy Parallelism,
             AddStream, Cache, OnWrite, ShouldEmitIndexFiles,
             ShouldEmitImportsFiles);
       };
+  return ThinBackend(Func, Parallelism);
 }
 
 StringLiteral lto::getThinLTODefaultCPU(const Triple &TheTriple) {
@@ -1681,7 +1640,7 @@ ThinBackend lto::createWriteIndexesThinBackend(
     std::string NewPrefix, std::string NativeObjectPrefix,
     bool ShouldEmitImportsFiles, raw_fd_ostream *LinkedObjectsFile,
     IndexWriteCallback OnWrite) {
-  return
+  auto Func =
       [=](const Config &Conf, ModuleSummaryIndex &CombinedIndex,
           const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
           AddStreamFn AddStream, FileCache Cache) {
@@ -1690,6 +1649,7 @@ ThinBackend lto::createWriteIndexesThinBackend(
             OldPrefix, NewPrefix, NativeObjectPrefix, ShouldEmitImportsFiles,
             LinkedObjectsFile, OnWrite);
       };
+  return ThinBackend(Func, Parallelism);
 }
 
 Error LTO::runThinLTO(AddStreamFn AddStream, FileCache Cache,
