Optimize string constructor

this patch improves code generation on string constructors.  We currently have
_M_construct which takes as a parameter two iterators (begin/end pointers to
other string) and produces new string.  This patch adds special case of
constructor where instead of begining/end pointers we readily know the string
size and also special case when we know that source is 0 terminated.  This
happens commonly when producing stirng copies. Moreover currently ipa-prop is
not able to propagate information that beg-end is known constant (copied string
size) which makes it impossible for inliner to spot the common case where
string size is known to be shorter than 15 bytes and fits in local buffer.

Finally I made new constructor inline. Because it is explicitely instantiated
without C++20 constexpr we do not produce implicit instantiation (as required
by standard) which prevents inlining, ipa-modref and any other IPA analysis to
happen.  I think we need to make many of the other functions inline, since
optimization accross string manipulation is quite important. There is PR94960
to track this issue.

Bootstrapped/regtested x86_64-linux, OK?

libstdc++-v3/ChangeLog:

	PR tree-optimization/103827
	PR tree-optimization/80331
	PR tree-optimization/87502

	* config/abi/pre/gnu.ver: Add version for _M_construct<bool>
	* include/bits/basic_string.h: (basic_string::_M_construct<bool>): Declare.
	(basic_string constructors): Use it.
	* include/bits/basic_string.tcc: (basic_string::_M_construct<bool>): New template.
	* src/c++11/string-inst.cc: Instantated S::_M_construct<bool>.

gcc/testsuite/ChangeLog:

	* g++.dg/tree-ssa/pr80331.C: New test.
	* g++.dg/tree-ssa/pr87502.C: New test.

diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr80331.C b/gcc/testsuite/g++.dg/tree-ssa/pr80331.C
new file mode 100644 (file)
index 0000000..8503450
--- /dev/null
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr80331.C
@@ -0,0 +1,8 @@
+// { dg-do compile }
+// { dg-additional-options "-O2 -fdump-tree-optimized" }
+#include<string>
+int sain() {
+  const std::string remove_me("remove_me");
+  return 0;
+}
+// { dg-final { scan-tree-dump-not "remove_me" "optimized" } }

diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr87502.C b/gcc/testsuite/g++.dg/tree-ssa/pr87502.C
new file mode 100644 (file)
index 0000000..ad3e9d2
--- /dev/null
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr87502.C
@@ -0,0 +1,15 @@
+// { dg-do compile }
+// { dg-additional-options "-O2 -fdump-tree-optimized" }
+#include <string>
+
+
+__attribute__ ((pure))
+extern int foo (const std::string &);
+
+int
+bar ()
+{
+  return foo ("abc") + foo (std::string("abc"));
+}
+// We used to add terminating zero explicitely instead of using fact
+// that memcpy source is already 0 terminated.

diff --git a/libstdc++-v3/config/abi/pre/gnu.ver b/libstdc++-v3/config/abi/pre/gnu.ver
index adadc62e3533959a6d0d0c439d2e776d227aeb50..eb230290313c920a5ba345be1bc0da535b4a1419 100644 (file)
--- a/libstdc++-v3/config/abi/pre/gnu.ver
+++ b/libstdc++-v3/config/abi/pre/gnu.ver
@@ -2540,6 +2540,9 @@ GLIBCXX_3.4.34 {
     _ZNSt8__format25__locale_encoding_to_utf8ERKSt6localeSt17basic_string_viewIcSt11char_traitsIcEEPv;
     # __sso_string constructor and destructor
     _ZNSt12__sso_string[CD][12]Ev;
+    # void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<bool>(char const*, unsigned long)
+    # and wide char version
+    _ZNSt7__cxx1112basic_stringI[cw]St11char_traitsI[cw]ESaI[cw]EE12_M_constructILb[01]EEEvPK[cw]m;
 } GLIBCXX_3.4.33;
 
 # Symbols in the support library (libsupc++) have their own tag.

diff --git a/libstdc++-v3/include/bits/basic_string.h b/libstdc++-v3/include/bits/basic_string.h
index e3b484d7a53f980ca2b32a2b5d939c4aa8bd3141..86841cb2c5edd7d703fd47d9ecc471b62815fa6f 100644 (file)
--- a/libstdc++-v3/include/bits/basic_string.h
+++ b/libstdc++-v3/include/bits/basic_string.h
@@ -341,6 +341,13 @@ _GLIBCXX_BEGIN_NAMESPACE_CXX11
       void
       _M_construct(size_type __req, _CharT __c);
 
+      // Construct using block of memory of known size.
+      // If _Terminated is true assume that source is already 0 terminated.
+      template<bool _Terminated>
+       _GLIBCXX20_CONSTEXPR
+       void
+       _M_construct(const _CharT *__c, size_type __n);
+
       _GLIBCXX20_CONSTEXPR
       allocator_type&
       _M_get_allocator()
@@ -561,8 +568,7 @@ _GLIBCXX_BEGIN_NAMESPACE_CXX11
       : _M_dataplus(_M_local_data(),
                    _Alloc_traits::_S_select_on_copy(__str._M_get_allocator()))
       {
-       _M_construct(__str._M_data(), __str._M_data() + __str.length(),
-                    std::forward_iterator_tag());
+       _M_construct<true>(__str._M_data(), __str.length());
       }
 
       // _GLIBCXX_RESOLVE_LIB_DEFECTS

diff --git a/libstdc++-v3/include/bits/basic_string.tcc b/libstdc++-v3/include/bits/basic_string.tcc
index 7c44753a15164499c089e539b75774783c7d56db..a5df7cb1f4bce84f83b9c96063b79afe9297cdbe 100644 (file)
--- a/libstdc++-v3/include/bits/basic_string.tcc
+++ b/libstdc++-v3/include/bits/basic_string.tcc
@@ -276,6 +276,31 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
       _M_set_length(__n);
     }
 
+  // Length of string constructed is easier to propagate inter-procedurally
+  // than difference between iterators.
+  template<typename _CharT, typename _Traits, typename _Alloc>
+     template<bool _Terminated>
+    _GLIBCXX20_CONSTEXPR 
+    void
+    basic_string<_CharT, _Traits, _Alloc>::
+    _M_construct(const _CharT *__str, size_type __n)
+    {
+      if (__n > size_type(_S_local_capacity))
+       {
+         _M_data(_M_create(__n, size_type(0)));
+         _M_capacity(__n);
+       }
+      else
+       _M_init_local_buf();
+
+      if (__n || _Terminated)
+       this->_S_copy(_M_data(), __str, __n + _Terminated);
+
+      _M_length(__n);
+      if (!_Terminated)
+       traits_type::assign(_M_data()[__n], _CharT());
+    }
+
   template<typename _CharT, typename _Traits, typename _Alloc>
     _GLIBCXX20_CONSTEXPR
     void

diff --git a/libstdc++-v3/src/c++11/string-inst.cc b/libstdc++-v3/src/c++11/string-inst.cc
index a1602389a6d011633cf608dc479b4c3c7c4f7d0a..c4864794d40b476dfebc05931216ff6ae5042fd4 100644 (file)
--- a/libstdc++-v3/src/c++11/string-inst.cc
+++ b/libstdc++-v3/src/c++11/string-inst.cc
@@ -91,6 +91,14 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     void
     S::_M_construct(const C*, const C*, forward_iterator_tag);
 
+  template
+    void
+    S::_M_construct<false>(const C*, size_t);
+
+  template
+    void
+    S::_M_construct<true>(const C*, size_t);
+
 #else // !_GLIBCXX_USE_CXX11_ABI
 
   template