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

7 files changed, 213 insertions, 25 deletions

diff --git a/llvm/include/llvm/CodeGen/ParallelCG.h b/llvm/include/llvm/CodeGen/ParallelCG.h
new file mode 100644
index 00000000000..73ac46125c9
--- /dev/null
+++ b/llvm/include/llvm/CodeGen/ParallelCG.h
@@ -0,0 +1,41 @@
+//===-- llvm/CodeGen/ParallelCG.h - Parallel code generation ----*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This header declares functions that can be used for parallel code generation.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_PARALLELCG_H
+#define LLVM_CODEGEN_PARALLELCG_H
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/Support/CodeGen.h"
+
+namespace llvm {
+
+class Module;
+class TargetOptions;
+class raw_pwrite_stream;
+
+/// Split M into OSs.size() partitions, and generate code for each. Writes
+/// OSs.size() object files to the output streams in OSs. The resulting object
+/// files if linked together are intended to be equivalent to the single object
+/// file that would have been code generated from M.
+///
+/// \returns M if OSs.size() == 1, otherwise returns std::unique_ptr<Module>().
+std::unique_ptr<Module>
+splitCodeGen(std::unique_ptr<Module> M, ArrayRef<raw_pwrite_stream *> OSs,
+             StringRef CPU, StringRef Features, const TargetOptions &Options,
+             Reloc::Model RM = Reloc::Default,
+             CodeModel::Model CM = CodeModel::Default,
+             CodeGenOpt::Level OL = CodeGenOpt::Default);
+
+} // namespace llvm
+
+#endif
diff --git a/llvm/include/llvm/LTO/LTOCodeGenerator.h b/llvm/include/llvm/LTO/LTOCodeGenerator.h
index ca0578fdc7d..0047a10247a 100644
--- a/llvm/include/llvm/LTO/LTOCodeGenerator.h
+++ b/llvm/include/llvm/LTO/LTOCodeGenerator.h
@@ -133,6 +133,12 @@ struct LTOCodeGenerator {
   // if the compilation was not successful.
   std::unique_ptr<MemoryBuffer> compileOptimized(std::string &errMsg);
 
+  // Compile the merged optimized module into out.size() object files each
+  // representing a linkable partition of the module. If out contains more than
+  // one element, code generation is done in parallel with out.size() threads.
+  // Object files will be written to members of out. Returns true on success.
+  bool compileOptimized(ArrayRef<raw_pwrite_stream *> out, std::string &errMsg);
+
   void setDiagnosticHandler(lto_diagnostic_handler_t, void *);
 
   LLVMContext &getContext() { return Context; }
@@ -140,7 +146,6 @@ struct LTOCodeGenerator {
 private:
   void initializeLTOPasses();
 
-  bool compileOptimized(raw_pwrite_stream &out, std::string &errMsg);
   bool compileOptimizedToFile(const char **name, std::string &errMsg);
   void applyScopeRestrictions();
   void applyRestriction(GlobalValue &GV, ArrayRef<StringRef> Libcalls,
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 {};
+}
diff --git a/llvm/lib/LTO/LTOCodeGenerator.cpp b/llvm/lib/LTO/LTOCodeGenerator.cpp
index 60ce4f67e03..eaec47ee682 100644
--- a/llvm/lib/LTO/LTOCodeGenerator.cpp
+++ b/llvm/lib/LTO/LTOCodeGenerator.cpp
@@ -18,6 +18,7 @@
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Bitcode/ReaderWriter.h"
+#include "llvm/CodeGen/ParallelCG.h"
 #include "llvm/CodeGen/RuntimeLibcalls.h"
 #include "llvm/Config/config.h"
 #include "llvm/IR/Constants.h"
@@ -218,7 +219,7 @@ bool LTOCodeGenerator::compileOptimizedToFile(const char **name,
   // generate object file
   tool_output_file objFile(Filename.c_str(), FD);
 
-  bool genResult = compileOptimized(objFile.os(), errMsg);
+  bool genResult = compileOptimized(&objFile.os(), errMsg);
   objFile.os().close();
   if (objFile.os().has_error()) {
     objFile.os().clear_error();
@@ -495,25 +496,26 @@ bool LTOCodeGenerator::optimize(bool DisableInline,
   return true;
 }
 
-bool LTOCodeGenerator::compileOptimized(raw_pwrite_stream &out,
+bool LTOCodeGenerator::compileOptimized(ArrayRef<raw_pwrite_stream *> out,
                                         std::string &errMsg) {
   if (!this->determineTarget(errMsg))
     return false;
 
-  legacy::PassManager codeGenPasses;
+  legacy::PassManager preCodeGenPasses;
 
   // If the bitcode files contain ARC code and were compiled with optimization,
   // the ObjCARCContractPass must be run, so do it unconditionally here.
-  codeGenPasses.add(createObjCARCContractPass());
-
-  if (TargetMach->addPassesToEmitFile(codeGenPasses, out,
-                                      TargetMachine::CGFT_ObjectFile)) {
-    errMsg = "target file type not supported";
-    return false;
-  }
-
-  // Run the code generator, and write object file
-  codeGenPasses.run(*MergedModule);
+  preCodeGenPasses.add(createObjCARCContractPass());
+  preCodeGenPasses.run(*MergedModule);
+
+  // Do code generation. We need to preserve the module in case the client calls
+  // writeMergedModules() after compilation, but we only need to allow this at
+  // parallelism level 1. This is achieved by having splitCodeGen return the
+  // original module at parallelism level 1 which we then assign back to
+  // MergedModule.
+  MergedModule =
+      splitCodeGen(std::move(MergedModule), out, MCpu, FeatureStr, Options,
+                   RelocModel, CodeModel::Default, CGOptLevel);
 
   return true;
 }
diff --git a/llvm/test/LTO/X86/parallel.ll b/llvm/test/LTO/X86/parallel.ll
new file mode 100644
index 00000000000..15e89ea59a5
--- /dev/null
+++ b/llvm/test/LTO/X86/parallel.ll
@@ -0,0 +1,22 @@
+; RUN: llvm-as -o %t.bc %s
+; RUN: llvm-lto -exported-symbol=foo -exported-symbol=bar -j2 -o %t.o %t.bc
+; RUN: llvm-nm %t.o.0 | FileCheck --check-prefix=CHECK0 %s
+; RUN: llvm-nm %t.o.1 | FileCheck --check-prefix=CHECK1 %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+; CHECK0-NOT: bar
+; CHECK0: T foo
+; CHECK0-NOT: bar
+define void @foo() {
+  call void @bar()
+  ret void
+}
+
+; CHECK1-NOT: foo
+; CHECK1: T bar
+; CHECK1-NOT: foo
+define void @bar() {
+  call void @foo()
+  ret void
+}
diff --git a/llvm/tools/llvm-lto/llvm-lto.cpp b/llvm/tools/llvm-lto/llvm-lto.cpp
index 52e45296126..ddde23175a3 100644
--- a/llvm/tools/llvm-lto/llvm-lto.cpp
+++ b/llvm/tools/llvm-lto/llvm-lto.cpp
@@ -22,7 +22,9 @@
 #include "llvm/Support/PrettyStackTrace.h"
 #include "llvm/Support/Signals.h"
 #include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/ToolOutputFile.h"
 #include "llvm/Support/raw_ostream.h"
+#include <list>
 
 using namespace llvm;
 
@@ -77,6 +79,9 @@ static cl::opt<bool> SetMergedModule(
     "set-merged-module", cl::init(false),
     cl::desc("Use the first input module as the merged module"));
 
+static cl::opt<unsigned> Parallelism("j", cl::Prefix, cl::init(1),
+                                     cl::desc("Number of backend threads"));
+
 namespace {
 struct ModuleInfo {
   std::vector<bool> CanBeHidden;
@@ -240,24 +245,41 @@ int main(int argc, char **argv) {
 
   if (!OutputFilename.empty()) {
     std::string ErrorInfo;
-    std::unique_ptr<MemoryBuffer> Code = CodeGen.compile(
-        DisableInline, DisableGVNLoadPRE, DisableLTOVectorization, ErrorInfo);
-    if (!Code) {
-      errs() << argv[0]
-             << ": error compiling the code: " << ErrorInfo << "\n";
+    if (!CodeGen.optimize(DisableInline, DisableGVNLoadPRE,
+                          DisableLTOVectorization, ErrorInfo)) {
+      errs() << argv[0] << ": error optimizing the code: " << ErrorInfo << "\n";
       return 1;
     }
 
-    std::error_code EC;
-    raw_fd_ostream FileStream(OutputFilename, EC, sys::fs::F_None);
-    if (EC) {
-      errs() << argv[0] << ": error opening the file '" << OutputFilename
-             << "': " << EC.message() << "\n";
+    std::list<tool_output_file> OSs;
+    std::vector<raw_pwrite_stream *> OSPtrs;
+    for (unsigned I = 0; I != Parallelism; ++I) {
+      std::string PartFilename = OutputFilename;
+      if (Parallelism != 1)
+        PartFilename += "." + utostr(I);
+      std::error_code EC;
+      OSs.emplace_back(PartFilename, EC, sys::fs::F_None);
+      if (EC) {
+        errs() << argv[0] << ": error opening the file '" << PartFilename
+               << "': " << EC.message() << "\n";
+        return 1;
+      }
+      OSPtrs.push_back(&OSs.back().os());
+    }
+
+    if (!CodeGen.compileOptimized(OSPtrs, ErrorInfo)) {
+      errs() << argv[0] << ": error compiling the code: " << ErrorInfo << "\n";
       return 1;
     }
 
-    FileStream.write(Code->getBufferStart(), Code->getBufferSize());
+    for (tool_output_file &OS : OSs)
+      OS.keep();
   } else {
+    if (Parallelism != 1) {
+      errs() << argv[0] << ": -j must be specified together with -o\n";
+      return 1;
+    }
+
     std::string ErrorInfo;
     const char *OutputName = nullptr;
     if (!CodeGen.compile_to_file(&OutputName, DisableInline,