From c269ed511584d9044a4e28a25fa6a0d24df68a9f Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <peter@pcc.me.uk>
Date: Thu, 27 Aug 2015 23:37:36 +0000
Subject: CodeGen: Introduce splitCodeGen and teach LTOCodeGenerator to use it.

llvm::splitCodeGen is a function that implements the core of parallel LTO
code generation. It uses llvm::SplitModule to split the module into linkable
partitions and spawning one code generation thread per partition. The function
produces multiple object files which can be linked in the usual way.

This has been threaded through to LTOCodeGenerator (and llvm-lto for testing
purposes). Separate patches will add parallel LTO support to the gold plugin
and lld.

Differential Revision: http://reviews.llvm.org/D12260

llvm-svn: 246236
---
 llvm/lib/CodeGen/CMakeLists.txt |  1 +
 llvm/lib/CodeGen/ParallelCG.cpp | 95 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)
 create mode 100644 llvm/lib/CodeGen/ParallelCG.cpp

(limited to 'llvm/lib/CodeGen')

diff --git a/llvm/lib/CodeGen/CMakeLists.txt b/llvm/lib/CodeGen/CMakeLists.txt
index eb7552970d3..f77141b3f30 100644
--- a/llvm/lib/CodeGen/CMakeLists.txt
+++ b/llvm/lib/CodeGen/CMakeLists.txt
@@ -80,6 +80,7 @@ add_llvm_library(LLVMCodeGen
   OptimizePHIs.cpp
   PHIElimination.cpp
   PHIEliminationUtils.cpp
+  ParallelCG.cpp
   Passes.cpp
   PeepholeOptimizer.cpp
   PostRASchedulerList.cpp
diff --git a/llvm/lib/CodeGen/ParallelCG.cpp b/llvm/lib/CodeGen/ParallelCG.cpp
new file mode 100644
index 00000000000..3e6a71d602b
--- /dev/null
+++ b/llvm/lib/CodeGen/ParallelCG.cpp
@@ -0,0 +1,95 @@
+//===-- ParallelCG.cpp ----------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines functions that can be used for parallel code generation.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/ParallelCG.h"
+#include "llvm/Bitcode/ReaderWriter.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/LegacyPassManager.h"
+#include "llvm/IR/Module.h"
+#include "llvm/Support/ErrorOr.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/thread.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Transforms/Utils/SplitModule.h"
+
+using namespace llvm;
+
+static void codegen(Module *M, llvm::raw_pwrite_stream &OS,
+                    const Target *TheTarget, StringRef CPU, StringRef Features,
+                    const TargetOptions &Options, Reloc::Model RM,
+                    CodeModel::Model CM, CodeGenOpt::Level OL) {
+  std::unique_ptr<TargetMachine> TM(TheTarget->createTargetMachine(
+      M->getTargetTriple(), CPU, Features, Options, RM, CM, OL));
+
+  legacy::PassManager CodeGenPasses;
+  if (TM->addPassesToEmitFile(CodeGenPasses, OS,
+                              TargetMachine::CGFT_ObjectFile))
+    report_fatal_error("Failed to setup codegen");
+  CodeGenPasses.run(*M);
+}
+
+std::unique_ptr<Module>
+llvm::splitCodeGen(std::unique_ptr<Module> M,
+                   ArrayRef<llvm::raw_pwrite_stream *> OSs, StringRef CPU,
+                   StringRef Features, const TargetOptions &Options,
+                   Reloc::Model RM, CodeModel::Model CM, CodeGenOpt::Level OL) {
+  StringRef TripleStr = M->getTargetTriple();
+  std::string ErrMsg;
+  const Target *TheTarget = TargetRegistry::lookupTarget(TripleStr, ErrMsg);
+  if (!TheTarget)
+    report_fatal_error(Twine("Target not found: ") + ErrMsg);
+
+  if (OSs.size() == 1) {
+    codegen(M.get(), *OSs[0], TheTarget, CPU, Features, Options, RM, CM,
+            OL);
+    return M;
+  }
+
+  std::vector<std::thread> Threads;
+  SplitModule(std::move(M), OSs.size(), [&](std::unique_ptr<Module> MPart) {
+    // We want to clone the module in a new context to multi-thread the codegen.
+    // We do it by serializing partition modules to bitcode (while still on the
+    // main thread, in order to avoid data races) and spinning up new threads
+    // which deserialize the partitions into separate contexts.
+    // FIXME: Provide a more direct way to do this in LLVM.
+    SmallVector<char, 0> BC;
+    raw_svector_ostream BCOS(BC);
+    WriteBitcodeToFile(MPart.get(), BCOS);
+
+    llvm::raw_pwrite_stream *ThreadOS = OSs[Threads.size()];
+    Threads.emplace_back(
+        [TheTarget, CPU, Features, Options, RM, CM, OL,
+         ThreadOS](const SmallVector<char, 0> &BC) {
+          LLVMContext Ctx;
+          ErrorOr<std::unique_ptr<Module>> MOrErr =
+              parseBitcodeFile(MemoryBufferRef(StringRef(BC.data(), BC.size()),
+                                               "<split-module>"),
+                               Ctx);
+          if (!MOrErr)
+            report_fatal_error("Failed to read bitcode");
+          std::unique_ptr<Module> MPartInCtx = std::move(MOrErr.get());
+
+          codegen(MPartInCtx.get(), *ThreadOS, TheTarget, CPU, Features,
+                  Options, RM, CM, OL);
+        },
+        // Pass BC using std::move to ensure that it get moved rather than
+        // copied into the thread's context.
+        std::move(BC));
+  });
+
+  for (std::thread &T : Threads)
+    T.join();
+
+  return {};
+}
-- 
cgit v1.2.3