libstdc++: Improve std::rot[lr] [PR99396]

As can be seen on:

unsigned char f1 (unsigned char x, int y) { return std::rotl (x, y); }
unsigned char f2 (unsigned char x, int y) { return std::rotr (x, y); }
unsigned short f3 (unsigned short x, int y) { return std::rotl (x, y); }
unsigned short f4 (unsigned short x, int y) { return std::rotr (x, y); }
unsigned int f5 (unsigned int x, int y) { return std::rotl (x, y); }
unsigned int f6 (unsigned int x, int y) { return std::rotr (x, y); }
unsigned long int f7 (unsigned long int x, int y) { return std::rotl (x, y); }
unsigned long int f8 (unsigned long int x, int y) { return std::rotr (x, y); }
unsigned long long int f9 (unsigned long long int x, int y) { return std::rotl (x, y); }
unsigned long long int f10 (unsigned long long int x, int y) { return std::rotr (x, y); }
//unsigned __int128 f11 (unsigned __int128 x, int y) { return std::rotl (x, y); }
//unsigned __int128 f12 (unsigned __int128 x, int y) { return std::rotr (x, y); }

constexpr auto a = std::rotl (1234U, 0);
constexpr auto b = std::rotl (1234U, 5);
constexpr auto c = std::rotl (1234U, -5);
constexpr auto d = std::rotl (1234U, -__INT_MAX__ - 1);
the current <bit> definitions of std::__rot[lr] aren't pattern recognized
as rotates, they are too long/complex for that, starting with signed modulo,
special case for 0 and different cases for positive and negative.

For types with power of two bits the following patch adds definitions that
the compiler can pattern recognize and turn e.g. on x86_64 into ro[lr][bwlq]
instructions.  For weirdo types like unsigned __int20 etc. it keeps the
current definitions.

2021-03-06  Jakub Jelinek  <jakub@redhat.com>

	PR libstdc++/99396
	* include/std/bit (__rotl, __rotr): Add optimized variants for power of
	two _Nd which the compiler can pattern match the rotates.

diff --git a/libstdc++-v3/include/std/bit b/libstdc++-v3/include/std/bit
index 1a6f240e69289ffa93b959fec6e37ce5b88ea6b2..8638a02c8a68cb931d73897f02f4157cfea029c3 100644 (file)
--- a/libstdc++-v3/include/std/bit
+++ b/libstdc++-v3/include/std/bit
@@ -68,6 +68,14 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     __rotl(_Tp __x, int __s) noexcept
     {
       constexpr auto _Nd = __gnu_cxx::__int_traits<_Tp>::__digits;
+      if _GLIBCXX17_CONSTEXPR ((_Nd & (_Nd - 1)) == 0)
+       {
+         // Variant for power of two _Nd which the compiler can
+         // easily pattern match.
+         constexpr unsigned __uNd = _Nd;
+         const unsigned __r = __s;
+         return (__x << (__r % __uNd)) | (__x >> ((-__r) % __uNd));
+       }
       const int __r = __s % _Nd;
       if (__r == 0)
        return __x;
@@ -82,6 +90,14 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     __rotr(_Tp __x, int __s) noexcept
     {
       constexpr auto _Nd = __gnu_cxx::__int_traits<_Tp>::__digits;
+      if _GLIBCXX17_CONSTEXPR ((_Nd & (_Nd - 1)) == 0)
+       {
+         // Variant for power of two _Nd which the compiler can
+         // easily pattern match.
+         constexpr unsigned __uNd = _Nd;
+         const unsigned __r = __s;
+         return (__x >> (__r % __uNd)) | (__x << ((-__r) % __uNd));
+       }
       const int __r = __s % _Nd;
       if (__r == 0)
        return __x;