Random Number Generator Refactoring (removing from Module)

This patch removes the RNG from Module. Passes should instead create a new RNG for their use as needed.

Patch by Stephen Crane @rinon.

Differential revision: http://reviews.llvm.org/D4377

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224444 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/IR/Module.h

@@ -219,8 +219,6 @@ private:
   std::string TargetTriple;       ///< Platform target triple Module compiled on
                                   ///< Format: (arch)(sub)-(vendor)-(sys0-(abi)
   void *NamedMDSymTab;            ///< NamedMDNode names.
-  // Allow lazy initialization in const method.
-  mutable RandomNumberGenerator *RNG; ///< The random number generator for this module.
 
   // We need to keep the string because the C API expects us to own the string
   // representation.
@@ -269,10 +267,16 @@ public:
   /// @returns a string containing the module-scope inline assembly blocks.
   const std::string &getModuleInlineAsm() const { return GlobalScopeAsm; }
 
-  /// Get the RandomNumberGenerator for this module. The RNG can be
-  /// seeded via -rng-seed=<uint64> and is salted with the ModuleID.
-  /// The returned RNG should not be shared across threads.
-  RandomNumberGenerator &getRNG() const;
+  /// Get a RandomNumberGenerator salted for use with this module. The
+  /// RNG can be seeded via -rng-seed=<uint64> and is salted with the
+  /// ModuleID and the provided pass salt. The returned RNG should not
+  /// be shared across threads or passes.
+  ///
+  /// A unique RNG per pass ensures a reproducible random stream even
+  /// when other randomness consuming passes are added or removed. In
+  /// addition, the random stream will be reproducible across LLVM
+  /// versions when the pass does not change.
+  RandomNumberGenerator *createRNG(const Pass* P) const;
 
 /// @}
 /// @name Module Level Mutators

include/llvm/Support/RandomNumberGenerator.h

@@ -7,9 +7,9 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file defines an abstraction for random number generation (RNG).
-// Note that the current implementation is not cryptographically secure
-// as it uses the C++11 <random> facilities.
+// This file defines an abstraction for deterministic random number
+// generation (RNG).  Note that the current implementation is not
+// cryptographically secure as it uses the C++11 <random> facilities.
 //
 //===----------------------------------------------------------------------===//
 
@@ -24,26 +24,27 @@
 namespace llvm {
 
 /// A random number generator.
-/// Instances of this class should not be shared across threads.
+///
+/// Instances of this class should not be shared across threads. The
+/// seed should be set by passing the -rng-seed=<uint64> option. Use
+/// Module::createRNG to create a new RNG instance for use with that
+/// module.
 class RandomNumberGenerator {
 public:
-  /// Seeds and salts the underlying RNG engine. The salt of type StringRef
-  /// is passed into the constructor. The seed can be set on the command
-  /// line via -rng-seed=<uint64>.
-  /// The reason for the salt is to ensure different random streams even if
-  /// the same seed is used for multiple invocations of the compiler.
-  /// A good salt value should add additional entropy and be constant across
-  /// different machines (i.e., no paths) to allow for reproducible builds.
-  /// An instance of this class can be retrieved from the current Module.
-  /// \see Module::getRNG
-  RandomNumberGenerator(StringRef Salt);
-
   /// Returns a random number in the range [0, Max).
-  uint64_t next(uint64_t Max);
+  uint_fast64_t operator()();
 
 private:
+  /// Seeds and salts the underlying RNG engine.
+  ///
+  /// This constructor should not be used directly. Instead use
+  /// Module::createRNG to create a new RNG salted with the Module ID.
+  RandomNumberGenerator(StringRef Salt);
+
   // 64-bit Mersenne Twister by Matsumoto and Nishimura, 2000
   // http://en.cppreference.com/w/cpp/numeric/random/mersenne_twister_engine
+  // This RNG is deterministically portable across C++11
+  // implementations.
   std::mt19937_64 Generator;
 
   // Noncopyable.
@@ -51,6 +52,8 @@ private:
       LLVM_DELETED_FUNCTION;
   RandomNumberGenerator &
   operator=(const RandomNumberGenerator &other) LLVM_DELETED_FUNCTION;
+
+  friend class Module;
 };
 }
 

lib/IR/Module.cpp

@@ -47,7 +47,7 @@ template class llvm::SymbolTableListTraits<GlobalAlias, Module>;
 //
 
 Module::Module(StringRef MID, LLVMContext &C)
-    : Context(C), Materializer(), ModuleID(MID), RNG(nullptr), DL("") {
+    : Context(C), Materializer(), ModuleID(MID), DL("") {
   ValSymTab = new ValueSymbolTable();
   NamedMDSymTab = new StringMap<NamedMDNode *>();
   Context.addModule(this);
@@ -62,9 +62,27 @@ Module::~Module() {
   NamedMDList.clear();
   delete ValSymTab;
   delete static_cast<StringMap<NamedMDNode *> *>(NamedMDSymTab);
-  delete RNG;
 }
 
+RandomNumberGenerator *Module::createRNG(const Pass* P) const {
+  SmallString<32> Salt(P->getPassName());
+
+  // This RNG is guaranteed to produce the same random stream only
+  // when the Module ID and thus the input filename is the same. This
+  // might be problematic if the input filename extension changes
+  // (e.g. from .c to .bc or .ll).
+  //
+  // We could store this salt in NamedMetadata, but this would make
+  // the parameter non-const. This would unfortunately make this
+  // interface unusable by any Machine passes, since they only have a
+  // const reference to their IR Module. Alternatively we can always
+  // store salt metadata from the Module constructor.
+  Salt += sys::path::filename(getModuleIdentifier());
+
+  return new RandomNumberGenerator(Salt);
+}
+
+
 /// getNamedValue - Return the first global value in the module with
 /// the specified name, of arbitrary type.  This method returns null
 /// if a global with the specified name is not found.
@@ -374,16 +392,6 @@ const DataLayout *Module::getDataLayout() const {
   return &DL;
 }
 
-// We want reproducible builds, but ModuleID may be a full path so we just use
-// the filename to salt the RNG (although it is not guaranteed to be unique).
-RandomNumberGenerator &Module::getRNG() const {
-  if (RNG == nullptr) {
-    StringRef Salt = sys::path::filename(ModuleID);
-    RNG = new RandomNumberGenerator(Salt);
-  }
-  return *RNG;
-}
-
 //===----------------------------------------------------------------------===//
 // Methods to control the materialization of GlobalValues in the Module.
 //

lib/Support/RandomNumberGenerator.cpp

@@ -7,16 +7,16 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements random number generation (RNG).
+// This file implements deterministic random number generation (RNG).
 // The current implementation is NOT cryptographically secure as it uses
 // the C++11 <random> facilities.
 //
 //===----------------------------------------------------------------------===//
 
 #define DEBUG_TYPE "rng"
-#include "llvm/Support/RandomNumberGenerator.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/RandomNumberGenerator.h"
 
 using namespace llvm;
 
@@ -31,31 +31,25 @@ Seed("rng-seed", cl::value_desc("seed"),
 RandomNumberGenerator::RandomNumberGenerator(StringRef Salt) {
   DEBUG(
     if (Seed == 0)
-      errs() << "Warning! Using unseeded random number generator.\n"
+      dbgs() << "Warning! Using unseeded random number generator.\n"
   );
 
-  // Combine seed and salt using std::seed_seq.
-  // Entropy: Seed-low, Seed-high, Salt...
+  // Combine seed and salts using std::seed_seq.
+  // Data: Seed-low, Seed-high, Salt
+  // Note: std::seed_seq can only store 32-bit values, even though we
+  // are using a 64-bit RNG. This isn't a problem since the Mersenne
+  // twister constructor copies these correctly into its initial state.
   std::vector<uint32_t> Data;
-  Data.reserve(2 + Salt.size()/4 + 1);
+  Data.reserve(2 + Salt.size());
   Data.push_back(Seed);
   Data.push_back(Seed >> 32);
 
-  uint32_t Pack = 0;
-  for (size_t I = 0; I < Salt.size(); ++I) {
-    Pack <<= 8;
-    Pack += Salt[I];
-
-    if (I%4 == 3)
-      Data.push_back(Pack);
-  }
-  Data.push_back(Pack);
+  std::copy(Salt.begin(), Salt.end(), Data.end());
 
   std::seed_seq SeedSeq(Data.begin(), Data.end());
   Generator.seed(SeedSeq);
 }
 
-uint64_t RandomNumberGenerator::next(uint64_t Max) {
-  std::uniform_int_distribution<uint64_t> distribution(0, Max - 1);
-  return distribution(Generator);
+uint_fast64_t RandomNumberGenerator::operator()() {
+  return Generator();
 }