Random Number Generator (llvm)

Provides an abstraction for a random number generator (RNG) that produces a stream of pseudo-random numbers.
The current implementation uses C++11 facilities and is therefore not cryptographically secure.

The RNG is salted with the text of the current command line invocation.
In addition, a user may specify a seed (reproducible builds).

In clang, the seed can be set via

-frandom-seed=X
In the back end, the seed can be set via

-rng-seed=X
This is the llvm part of the patch.
clang part: D3391

URL: http://reviews.llvm.org/D3390
Author: yln

I'm landing this for the second time, it broke Windows bots the first time around.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211705 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/IR/Module.h

@@ -29,6 +29,7 @@ namespace llvm {
 class FunctionType;
 class GVMaterializer;
 class LLVMContext;
+class RandomNumberGenerator;
 class StructType;
 template<typename T> struct DenseMapInfo;
 template<typename KeyT, typename ValueT, typename KeyInfoT> class DenseMap;
@@ -201,6 +202,8 @@ private:
   std::string ModuleID;           ///< Human readable identifier for the module
   std::string TargetTriple;       ///< Platform target triple Module compiled on
   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.
@@ -249,6 +252,11 @@ 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;
+
 /// @}
 /// @name Module Level Mutators
 /// @{

include/llvm/Support/RandomNumberGenerator.h

@@ -0,0 +1,54 @@
+//==- llvm/Support/RandomNumberGenerator.h - RNG for diversity ---*- C++ -*-==//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// 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.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_RANDOMNUMBERGENERATOR_H_
+#define LLVM_SUPPORT_RANDOMNUMBERGENERATOR_H_
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/DataTypes.h" // Needed for uint64_t on Windows.
+#include <random>
+
+namespace llvm {
+
+/// A random number generator.
+/// Instances of this class should not be shared across threads.
+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);
+
+private:
+  // 64-bit Mersenne Twister by Matsumoto and Nishimura, 2000
+  // http://en.cppreference.com/w/cpp/numeric/random/mersenne_twister_engine
+  std::mt19937_64 Generator;
+
+  // Noncopyable.
+  RandomNumberGenerator(const RandomNumberGenerator &other) = delete;
+  RandomNumberGenerator &operator=(const RandomNumberGenerator &other) = delete;
+};
+}
+
+#endif

lib/IR/Module.cpp

@@ -24,6 +24,8 @@
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/LeakDetector.h"
 #include "llvm/Support/Dwarf.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/RandomNumberGenerator.h"
 #include <algorithm>
 #include <cstdarg>
 #include <cstdlib>
@@ -44,7 +46,7 @@ template class llvm::SymbolTableListTraits<GlobalAlias, Module>;
 //
 
 Module::Module(StringRef MID, LLVMContext &C)
-    : Context(C), Materializer(), ModuleID(MID), DL("") {
+    : Context(C), Materializer(), ModuleID(MID), RNG(nullptr), DL("") {
   ValSymTab = new ValueSymbolTable();
   NamedMDSymTab = new StringMap<NamedMDNode *>();
   Context.addModule(this);
@@ -59,6 +61,7 @@ Module::~Module() {
   NamedMDList.clear();
   delete ValSymTab;
   delete static_cast<StringMap<NamedMDNode *> *>(NamedMDSymTab);
+  delete RNG;
 }
 
 /// getNamedValue - Return the first global value in the module with
@@ -355,6 +358,16 @@ 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/CMakeLists.txt

@@ -41,6 +41,7 @@ add_llvm_library(LLVMSupport
   MD5.cpp
   PluginLoader.cpp
   PrettyStackTrace.cpp
+  RandomNumberGenerator.cpp
   Regex.cpp
   ScaledNumber.cpp
   SmallPtrSet.cpp

lib/Support/RandomNumberGenerator.cpp

@@ -0,0 +1,61 @@
+//===-- RandomNumberGenerator.cpp - Implement RNG class -------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements 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"
+
+using namespace llvm;
+
+// Tracking BUG: 19665
+// http://llvm.org/bugs/show_bug.cgi?id=19665
+//
+// Do not change to cl::opt<uint64_t> since this silently breaks argument parsing.
+static cl::opt<unsigned long long>
+Seed("rng-seed", cl::value_desc("seed"),
+     cl::desc("Seed for the random number generator"), cl::init(0));
+
+RandomNumberGenerator::RandomNumberGenerator(StringRef Salt) {
+  DEBUG(
+    if (Seed == 0)
+      errs() << "Warning! Using unseeded random number generator.\n"
+  );
+
+  // Combine seed and salt using std::seed_seq.
+  // Entropy: Seed-low, Seed-high, Salt...
+  std::vector<uint32_t> Data;
+  Data.reserve(2 + Salt.size()/4 + 1);
+  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::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);
+}