[llvm] [DTLTO][LLVM] Integrated Distributed ThinLTO (DTLTO) (PR #127749)

[Teresa Johnson via llvm-commits]

================
@@ -2142,3 +2196,324 @@ std::vector<int> lto::generateModulesOrdering(ArrayRef<BitcodeModule *> R) {
   });
   return ModulesOrdering;
 }
+
+namespace {
+// For this out-of-process backend no codegen is done when invoked for each
+// task. Instead we generate the required information (e.g. the summary index
+// shard, import list, etc..) to allow for the codegen to be performed
+// externally . This backend's `wait` function then invokes an external
+// distributor process to do backend compilations.
+class OutOfProcessThinBackend : public CGThinBackend {
+  using SString = SmallString<128>;
+
+  AddBufferFn AddBuffer;
+
+  BumpPtrAllocator Alloc;
+  StringSaver Saver{Alloc};
+
+  SString LinkerOutputFile;
+  SString DistributorPath;
+  bool SaveTemps;
+
+  SmallVector<StringRef, 0> CodegenOptions;
+  DenseSet<StringRef> AdditionalInputs;
+
+  // Information specific to individual backend compilation job.
+  struct Job {
+    unsigned Task;
+    StringRef ModuleID;
+    StringRef Triple;
+    StringRef NativeObjectPath;
+    StringRef SummaryIndexPath;
+    ImportsFilesContainer ImportFiles;
+  };
+  // The set of backend compilations jobs.
+  SmallVector<Job> Jobs;
+
+  // A unique string to identify the current link.
+  SmallString<8> UID;
+
+  // The first ReservedTasks entries in the task range are used for Full LTO.
+  unsigned ReservedTasks;
+
+public:
+  OutOfProcessThinBackend(
+      const Config &Conf, ModuleSummaryIndex &CombinedIndex,
+      ThreadPoolStrategy ThinLTOParallelism,
+      const DenseMap<StringRef, GVSummaryMapTy> &ModuleToDefinedGVSummaries,
+      AddStreamFn AddStream, AddBufferFn AddBuffer,
+      lto::IndexWriteCallback OnWrite, bool ShouldEmitIndexFiles,
+      bool ShouldEmitImportsFiles, StringRef LinkerOutputFile,
+      StringRef Distributor, bool SaveTemps)
+      : CGThinBackend(Conf, CombinedIndex, ModuleToDefinedGVSummaries, OnWrite,
+                      ShouldEmitIndexFiles, ShouldEmitImportsFiles,
+                      ThinLTOParallelism),
+        AddBuffer(std::move(AddBuffer)), LinkerOutputFile(LinkerOutputFile),
+        DistributorPath(Distributor), SaveTemps(SaveTemps) {}
+
+  virtual void setup(unsigned MaxTasks, unsigned ReservedTasks) override {
+    UID = itostr(sys::Process::getProcessId());
+    Jobs.resize((size_t)MaxTasks);
+    this->ReservedTasks = ReservedTasks;
+  }
+
+  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,
+      DenseMap<StringRef, std::string> &ModuleTriples) override {
+
+    StringRef ModulePath = BM.getModuleIdentifier();
+
+    SString ObjFilePath = sys::path::parent_path(LinkerOutputFile);
+    sys::path::append(ObjFilePath, sys::path::stem(ModulePath) + "." +
+                                       itostr(Task) + "." + UID + ".native.o");
+
+    Job &J = Jobs[Task - ReservedTasks];
+    J = {Task,
+         ModulePath,
+         ModuleTriples[ModulePath],
+         Saver.save(ObjFilePath.str()),
+         Saver.save(ObjFilePath.str() + ".thinlto.bc"),
+         {}};
+
+    assert(ModuleToDefinedGVSummaries.count(ModulePath));
+    BackendThreadPool.async(
+        [=](Job &J, const FunctionImporter::ImportMapTy &ImportList) {
+          if (LLVM_ENABLE_THREADS && Conf.TimeTraceEnabled)
+            timeTraceProfilerInitialize(Conf.TimeTraceGranularity,
+                                        "thin backend");
+          if (auto E = emitFiles(ImportList, J.ModuleID, J.SummaryIndexPath,
+                                 J.ModuleID.str(), J.ImportFiles)) {
+            std::unique_lock<std::mutex> L(ErrMu);
+            if (Err)
+              Err = joinErrors(std::move(*Err), std::move(E));
+            else
+              Err = std::move(E);
+          }
+          if (LLVM_ENABLE_THREADS && Conf.TimeTraceEnabled)
+            timeTraceProfilerFinishThread();
+        },
+        std::ref(J), std::ref(ImportList));
+
+    return Error::success();
+  }
+
+  // Derive a set of Clang options that will be shared/common for all DTLTO
+  // backend compilations. We are intentionally minimal here as these options
+  // must remain synchronized with the behavior of Clang. DTLTO does not support
+  // all the features available with in-process LTO. More features are expected
+  // to be added over time. Users can specify Clang options directly if a
+  // feature is not supported. Note that explicitly specified options that imply
+  // additional input or output file dependencies must be communicated to the
+  // distribution system, potentially by setting extra options on the
+  // distributor program.
+  // TODO: If this strategy of deriving options proves insufficient, alternative
+  // approaches should be considered, such as:
+  //   - A serialization/deserialization format for LTO configuration.
----------------
teresajohnson wrote:

This comes from the perspective of migrating in-process ThinLTO to DTLTO. An alternative perspective is that it should be consistent with a non-LTO compile, which means that you would want to communicate the options given to the `-c` compile step. That would need to be done either by encoding the option behavior in the bitcode (e.g. as module flags - an approach taken for a bunch of options already), or embedding the options in some other way that can be extracted/communicated.

https://github.com/llvm/llvm-project/pull/127749