[locale] Avoid copy of __atoms when char_type is char

The function num_get<_CharT>::stage2_int_prep makes unnecessary copy of src
into atoms when char_type is char. This can be avoided by creating
a switch on type and just returning __src when char_type is char.

Added the test case to demonstrate performance improvement.
In order to avoid ABI incompatibilities, the changes are guarded
with a macro _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET

Differential Revision: https://reviews.llvm.org/D30268
Reviewed by: EricWF

llvm-svn: 305427

libcxx/benchmarks/stringstream.bench.cpp

@@ -0,0 +1,38 @@
+#include "benchmark/benchmark_api.h"
+
+#include <sstream>
+double __attribute__((noinline)) istream_numbers();
+
+double istream_numbers() {
+  const char *a[] = {
+    "-6  69 -71  2.4882e-02 -100 101 -2.00005 5000000 -50000000",
+    "-25 71   7 -9.3262e+01 -100 101 -2.00005 5000000 -50000000",
+    "-14 53  46 -6.7026e-02 -100 101 -2.00005 5000000 -50000000"
+  };
+
+  int a1, a2, a3, a4, a5, a6, a7;
+  double f1 = 0.0, f2 = 0.0, q = 0.0;
+  for (int i=0; i < 3; i++) {
+    std::istringstream s(a[i]);
+    s >> a1
+      >> a2
+      >> a3
+      >> f1
+      >> a4
+      >> a5
+      >> f2
+      >> a6
+      >> a7;
+    q += (a1 + a2 + a3 + a4 + a5 + a6 + a7 + f1 + f2)/1000000;
+  }
+  return q;
+}
+
+static void BM_Istream_numbers(benchmark::State &state) {
+  double i = 0;
+  while (state.KeepRunning())
+    benchmark::DoNotOptimize(i += istream_numbers());
+}
+
+BENCHMARK(BM_Istream_numbers)->RangeMultiplier(2)->Range(1024, 4096);
+BENCHMARK_MAIN()

libcxx/include/__config

@@ -76,6 +76,9 @@
 // its vtable and typeinfo to libc++ rather than having all other libraries
 // using that class define their own copies.
 #define _LIBCPP_ABI_BAD_FUNCTION_CALL_KEY_FUNCTION
+
+// Enable optimized version of __do_get_(un)signed which avoids redundant copies.
+#define _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
 #elif _LIBCPP_ABI_VERSION == 1
 #if !defined(_LIBCPP_OBJECT_FORMAT_COFF)
 // Enable compiling copies of now inline methods into the dylib to support

libcxx/include/locale

@@ -372,19 +372,57 @@ template <class _CharT>
 struct __num_get
     : protected __num_get_base
 {
-    static string __stage2_int_prep(ios_base& __iob, _CharT* __atoms, _CharT& __thousands_sep);
     static string __stage2_float_prep(ios_base& __iob, _CharT* __atoms, _CharT& __decimal_point,
                                       _CharT& __thousands_sep);
-    static int __stage2_int_loop(_CharT __ct, int __base, char* __a, char*& __a_end,
-                  unsigned& __dc, _CharT __thousands_sep, const string& __grouping,
-                  unsigned* __g, unsigned*& __g_end, _CharT* __atoms);
+
     static int __stage2_float_loop(_CharT __ct, bool& __in_units, char& __exp,
                                    char* __a, char*& __a_end,
                                    _CharT __decimal_point, _CharT __thousands_sep,
                                    const string& __grouping, unsigned* __g,
                                    unsigned*& __g_end, unsigned& __dc, _CharT* __atoms);
+#ifndef _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
+    static string __stage2_int_prep(ios_base& __iob, _CharT* __atoms, _CharT& __thousands_sep);
+    static int __stage2_int_loop(_CharT __ct, int __base, char* __a, char*& __a_end,
+                  unsigned& __dc, _CharT __thousands_sep, const string& __grouping,
+                  unsigned* __g, unsigned*& __g_end, _CharT* __atoms);
+
+#else
+    static string __stage2_int_prep(ios_base& __iob, _CharT& __thousands_sep)
+    {
+        locale __loc = __iob.getloc();
+        const numpunct<_CharT>& __np = use_facet<numpunct<_CharT> >(__loc);
+        __thousands_sep = __np.thousands_sep();
+        return __np.grouping();
+    }
+
+    const _CharT* __do_widen(ios_base& __iob, _CharT* __atoms) const
+    {
+      return __do_widen_p(__iob, __atoms);
+    }
+
+
+    static int __stage2_int_loop(_CharT __ct, int __base, char* __a, char*& __a_end,
+                  unsigned& __dc, _CharT __thousands_sep, const string& __grouping,
+                  unsigned* __g, unsigned*& __g_end, const _CharT* __atoms);
+private:
+    template<typename T>
+    const T* __do_widen_p(ios_base& __iob, T* __atoms) const
+    {
+      locale __loc = __iob.getloc();
+      use_facet<ctype<T> >(__loc).widen(__src, __src + 26, __atoms);
+      return __atoms;
+    }
+
+    const char* __do_widen_p(ios_base& __iob, char* __atoms) const
+    {
+      (void)__iob;
+      (void)__atoms;
+      return __src;
+    }
+#endif
 };
 
+#ifndef _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
 template <class _CharT>
 string
 __num_get<_CharT>::__stage2_int_prep(ios_base& __iob, _CharT* __atoms, _CharT& __thousands_sep)
@@ -395,6 +433,7 @@ __num_get<_CharT>::__stage2_int_prep(ios_base& __iob, _CharT* __atoms, _CharT& _
     __thousands_sep = __np.thousands_sep();
     return __np.grouping();
 }
+#endif
 
 template <class _CharT>
 string
@@ -411,9 +450,16 @@ __num_get<_CharT>::__stage2_float_prep(ios_base& __iob, _CharT* __atoms, _CharT&
 
 template <class _CharT>
 int
+#ifndef _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
 __num_get<_CharT>::__stage2_int_loop(_CharT __ct, int __base, char* __a, char*& __a_end,
                   unsigned& __dc, _CharT __thousands_sep, const string& __grouping,
                   unsigned* __g, unsigned*& __g_end, _CharT* __atoms)
+#else
+__num_get<_CharT>::__stage2_int_loop(_CharT __ct, int __base, char* __a, char*& __a_end,
+                  unsigned& __dc, _CharT __thousands_sep, const string& __grouping,
+                  unsigned* __g, unsigned*& __g_end, const _CharT* __atoms)
+
+#endif
 {
     if (__a_end == __a && (__ct == __atoms[24] || __ct == __atoms[25]))
     {
@@ -849,9 +895,16 @@ num_get<_CharT, _InputIterator>::__do_get_signed(iter_type __b, iter_type __e,
     // Stage 1
     int __base = this->__get_base(__iob);
     // Stage 2
-    char_type __atoms[26];
     char_type __thousands_sep;
+    const int __atoms_size = 26;
+#ifdef _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
+    char_type __atoms1[__atoms_size];
+    const char_type *__atoms = this->__do_widen(__iob, __atoms1);
+    string __grouping = this->__stage2_int_prep(__iob, __thousands_sep);
+#else
+    char_type __atoms[__atoms_size];
     string __grouping = this->__stage2_int_prep(__iob, __atoms, __thousands_sep);
+#endif
     string __buf;
     __buf.resize(__buf.capacity());
     char* __a = &__buf[0];
@@ -899,9 +952,16 @@ num_get<_CharT, _InputIterator>::__do_get_unsigned(iter_type __b, iter_type __e,
     // Stage 1
     int __base = this->__get_base(__iob);
     // Stage 2
-    char_type __atoms[26];
     char_type __thousands_sep;
+    const int __atoms_size = 26;
+#ifdef _LIBCPP_ABI_OPTIMIZED_LOCALE_NUM_GET
+    char_type __atoms1[__atoms_size];
+    const char_type *__atoms = this->__do_widen(__iob, __atoms1);
+    string __grouping = this->__stage2_int_prep(__iob, __thousands_sep);
+#else
+    char_type __atoms[__atoms_size];
     string __grouping = this->__stage2_int_prep(__iob, __atoms, __thousands_sep);
+#endif
     string __buf;
     __buf.resize(__buf.capacity());
     char* __a = &__buf[0];