Files
clang-p2996/libcxx/include/__bit/countr.h
Nikolas Klauser b68e2eba0b [libc++] Vectorize mismatch (#73255)
```
---------------------------------------------------
Benchmark                           old         new
---------------------------------------------------
bm_mismatch<char>/1           0.835 ns      2.37 ns
bm_mismatch<char>/2            1.44 ns      2.60 ns
bm_mismatch<char>/3            2.06 ns      2.83 ns
bm_mismatch<char>/4            2.60 ns      3.29 ns
bm_mismatch<char>/5            3.15 ns      3.77 ns
bm_mismatch<char>/6            3.82 ns      4.17 ns
bm_mismatch<char>/7            4.29 ns      4.52 ns
bm_mismatch<char>/8            4.78 ns      4.86 ns
bm_mismatch<char>/16           9.06 ns      7.54 ns
bm_mismatch<char>/64           31.7 ns      19.1 ns
bm_mismatch<char>/512           249 ns      8.16 ns
bm_mismatch<char>/4096         1956 ns      44.2 ns
bm_mismatch<char>/32768       15498 ns       501 ns
bm_mismatch<char>/262144     123965 ns      4479 ns
bm_mismatch<char>/1048576    495668 ns     21306 ns
bm_mismatch<short>/1          0.710 ns      2.12 ns
bm_mismatch<short>/2           1.03 ns      2.66 ns
bm_mismatch<short>/3           1.29 ns      3.56 ns
bm_mismatch<short>/4           1.68 ns      4.29 ns
bm_mismatch<short>/5           1.96 ns      5.18 ns
bm_mismatch<short>/6           2.59 ns      5.91 ns
bm_mismatch<short>/7           2.86 ns      6.63 ns
bm_mismatch<short>/8           3.19 ns      7.33 ns
bm_mismatch<short>/16          5.48 ns      13.0 ns
bm_mismatch<short>/64          16.6 ns      4.06 ns
bm_mismatch<short>/512          130 ns      13.8 ns
bm_mismatch<short>/4096         985 ns      93.8 ns
bm_mismatch<short>/32768       7846 ns      1002 ns
bm_mismatch<short>/262144     63217 ns     10637 ns
bm_mismatch<short>/1048576   251782 ns     42471 ns
bm_mismatch<int>/1            0.716 ns      1.91 ns
bm_mismatch<int>/2             1.21 ns      2.49 ns
bm_mismatch<int>/3             1.38 ns      3.46 ns
bm_mismatch<int>/4             1.71 ns      4.04 ns
bm_mismatch<int>/5             2.00 ns      4.98 ns
bm_mismatch<int>/6             2.43 ns      5.67 ns
bm_mismatch<int>/7             3.05 ns      6.38 ns
bm_mismatch<int>/8             3.22 ns      7.09 ns
bm_mismatch<int>/16            5.18 ns      12.8 ns
bm_mismatch<int>/64            16.6 ns      5.28 ns
bm_mismatch<int>/512            129 ns      25.2 ns
bm_mismatch<int>/4096          1009 ns       201 ns
bm_mismatch<int>/32768         7776 ns      2144 ns
bm_mismatch<int>/262144       62371 ns     20551 ns
bm_mismatch<int>/1048576     254750 ns     90097 ns
```
2024-03-23 15:28:22 +01:00

79 lines
2.5 KiB
C++

//===----------------------------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef _LIBCPP___BIT_COUNTR_H
#define _LIBCPP___BIT_COUNTR_H
#include <__bit/rotate.h>
#include <__concepts/arithmetic.h>
#include <__config>
#include <limits>
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
# pragma GCC system_header
#endif
_LIBCPP_PUSH_MACROS
#include <__undef_macros>
_LIBCPP_BEGIN_NAMESPACE_STD
_LIBCPP_NODISCARD inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR int __libcpp_ctz(unsigned __x) _NOEXCEPT {
return __builtin_ctz(__x);
}
_LIBCPP_NODISCARD inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR int __libcpp_ctz(unsigned long __x) _NOEXCEPT {
return __builtin_ctzl(__x);
}
_LIBCPP_NODISCARD inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR int __libcpp_ctz(unsigned long long __x) _NOEXCEPT {
return __builtin_ctzll(__x);
}
template <class _Tp>
_LIBCPP_NODISCARD _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 int __countr_zero(_Tp __t) _NOEXCEPT {
if (__t == 0)
return numeric_limits<_Tp>::digits;
if (sizeof(_Tp) <= sizeof(unsigned int))
return std::__libcpp_ctz(static_cast<unsigned int>(__t));
else if (sizeof(_Tp) <= sizeof(unsigned long))
return std::__libcpp_ctz(static_cast<unsigned long>(__t));
else if (sizeof(_Tp) <= sizeof(unsigned long long))
return std::__libcpp_ctz(static_cast<unsigned long long>(__t));
else {
int __ret = 0;
const unsigned int __ulldigits = numeric_limits<unsigned long long>::digits;
while (static_cast<unsigned long long>(__t) == 0uLL) {
__ret += __ulldigits;
__t >>= __ulldigits;
}
return __ret + std::__libcpp_ctz(static_cast<unsigned long long>(__t));
}
}
#if _LIBCPP_STD_VER >= 20
template <__libcpp_unsigned_integer _Tp>
_LIBCPP_NODISCARD_EXT _LIBCPP_HIDE_FROM_ABI constexpr int countr_zero(_Tp __t) noexcept {
return std::__countr_zero(__t);
}
template <__libcpp_unsigned_integer _Tp>
_LIBCPP_NODISCARD_EXT _LIBCPP_HIDE_FROM_ABI constexpr int countr_one(_Tp __t) noexcept {
return __t != numeric_limits<_Tp>::max() ? std::countr_zero(static_cast<_Tp>(~__t)) : numeric_limits<_Tp>::digits;
}
#endif // _LIBCPP_STD_VER >= 20
_LIBCPP_END_NAMESPACE_STD
_LIBCPP_POP_MACROS
#endif // _LIBCPP___BIT_COUNTR_H