Add C++11 Ranged For loop alternative to KeepRunning (#454)

README.md

@@ -194,6 +194,58 @@ Three macros are provided for adding benchmark templates.
 #define BENCHMARK_TEMPLATE2(func, arg1, arg2)
 ```
 
+### A Faster KeepRunning loop
+
+In C++11 mode, a ranged-based for loop should be used in preference to
+the `KeepRunning` loop for running the benchmarks. For example:
+
+```c++
+static void BM_Faste(benchmark::State &st) {
+  for (auto _ : state) {
+    FastOperation();
+  }
+}
+```
+
+The reason the ranged-based for loop is faster than using `KeepRunning`, is
+because `KeepRunning` requires a memory load and store of the iteration count
+ever iteration, whereas the ranged-for variant is able to keep the iteration count
+in a register.
+
+For example, an empty inner loop of using the ranged-based for method looks like:
+
+```asm
+# Loop Init
+  mov rbx, qword ptr [r14 + 104]
+  call benchmark::State::StartKeepRunning()
+  test rbx, rbx
+  je .LoopEnd
+.LoopHeader: # =>This Inner Loop Header: Depth=1
+  add rbx, -1
+  jne .LoopHeader
+.LoopEnd:
+```
+
+Compared to an empty `KeepRunning` loop, which looks like:
+
+```asm
+.LoopHeader: # in Loop: Header=BB0_3 Depth=1
+  cmp byte ptr [rbx], 1
+  jne .LoopInit
+.LoopBody: # =>This Inner Loop Header: Depth=1
+  mov rax, qword ptr [rbx + 8]
+  lea rcx, [rax + 1]
+  mov qword ptr [rbx + 8], rcx
+  cmp rax, qword ptr [rbx + 104]
+  jb .LoopHeader
+  jmp .LoopEnd
+.LoopInit:
+  mov rdi, rbx
+  call benchmark::State::StartKeepRunning()
+  jmp .LoopBody
+.LoopEnd:
+```
+
 ## Passing arbitrary arguments to a benchmark
 In C++11 it is possible to define a benchmark that takes an arbitrary number
 of extra arguments. The `BENCHMARK_CAPTURE(func, test_case_name, ...args)`

include/benchmark/benchmark.h

@@ -238,7 +238,6 @@ BENCHMARK(BM_test)->Unit(benchmark::kMillisecond);
 #define BENCHMARK_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
 #endif
 
-
 namespace benchmark {
 class BenchmarkReporter;
 
@@ -413,6 +412,19 @@ enum ReportMode
 // benchmark to use.
 class State {
  public:
+  struct StateIterator;
+  friend struct StateIterator;
+
+  // Returns iterators used to run each iteration of a benchmark using a
+  // C++11 ranged-based for loop. These functions should not be called directly.
+  //
+  // REQUIRES: The benchmark has not started running yet. Neither begin nor end
+  // have been called previously.
+  //
+  // NOTE: KeepRunning may not be used after calling either of these functions.
+  BENCHMARK_ALWAYS_INLINE StateIterator begin();
+  BENCHMARK_ALWAYS_INLINE StateIterator end();
+
   // Returns true if the benchmark should continue through another iteration.
   // NOTE: A benchmark may not return from the test until KeepRunning() has
   // returned false.
@@ -585,6 +597,53 @@ class State {
   BENCHMARK_DISALLOW_COPY_AND_ASSIGN(State);
 };
 
+struct State::StateIterator {
+  struct BENCHMARK_UNUSED Value {};
+  typedef std::forward_iterator_tag iterator_category;
+  typedef Value value_type;
+  typedef Value reference;
+  typedef Value pointer;
+
+ private:
+  friend class State;
+  BENCHMARK_ALWAYS_INLINE
+  StateIterator() : cached_(0), parent_() {}
+
+  BENCHMARK_ALWAYS_INLINE
+  explicit StateIterator(State* st)
+      : cached_(st->max_iterations), parent_(st) {}
+
+ public:
+  BENCHMARK_ALWAYS_INLINE
+  Value operator*() const { return Value(); }
+
+  BENCHMARK_ALWAYS_INLINE
+  StateIterator& operator++() {
+    assert(cached_ > 0);
+    --cached_;
+    return *this;
+  }
+
+  BENCHMARK_ALWAYS_INLINE
+  bool operator!=(StateIterator const&) const {
+    if (BENCHMARK_BUILTIN_EXPECT(cached_ != 0, true)) return true;
+    parent_->FinishKeepRunning();
+    return false;
+  }
+
+ private:
+  size_t cached_;
+  State* const parent_;
+};
+
+BENCHMARK_ALWAYS_INLINE inline State::StateIterator State::begin() {
+  return StateIterator(this);
+}
+BENCHMARK_ALWAYS_INLINE inline State::StateIterator State::end() {
+  StartKeepRunning();
+  return StateIterator();
+}
+
 namespace internal {
 
 typedef void(Function)(State&);

test/basic_test.cc

@@ -96,4 +96,23 @@ void BM_empty_stop_start(benchmark::State& state) {
 BENCHMARK(BM_empty_stop_start);
 BENCHMARK(BM_empty_stop_start)->ThreadPerCpu();
 
+
+void BM_KeepRunning(benchmark::State& state) {
+  size_t iter_count = 0;
+  while (state.KeepRunning()) {
+    ++iter_count;
+  }
+  assert(iter_count == state.max_iterations);
+}
+BENCHMARK(BM_KeepRunning);
+
+void BM_RangedFor(benchmark::State& state) {
+  size_t iter_count = 0;
+  for (auto _ : state) {
+    ++iter_count;
+  }
+  assert(iter_count == state.max_iterations);
+}
+BENCHMARK(BM_RangedFor);
+
 BENCHMARK_MAIN()