@zigc/lib 0.17.0-dev.135 → 0.17.0-dev.215

package/include/xmmintrin.h

@@ -16,7 +16,6 @@
 
 #include <mmintrin.h>
 
-typedef int __v4si __attribute__((__vector_size__(16)));
 typedef float __v4sf __attribute__((__vector_size__(16)));
 typedef float __m128 __attribute__((__vector_size__(16), __aligned__(16)));
 
@@ -24,6 +23,8 @@ typedef float __m128_u __attribute__((__vector_size__(16), __aligned__(1)));
 
 /* Unsigned types */
 typedef unsigned int __v4su __attribute__((__vector_size__(16)));
+typedef unsigned short __v8hu __attribute__((__vector_size__(16)));
+typedef unsigned char __v16qu __attribute__((__vector_size__(16)));
 
 /* This header should only be included in a hosted environment as it depends on
  * a standard library to provide allocation routines. */
@@ -32,21 +33,12 @@ typedef unsigned int __v4su __attribute__((__vector_size__(16)));
 #endif
 
 /* Define the default attributes for the functions in this file. */
-#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
-#define __DEFAULT_FN_ATTRS                                                     \
-  __attribute__((__always_inline__, __nodebug__, __target__("sse,no-evex512"), \
-                 __min_vector_width__(128)))
-#define __DEFAULT_FN_ATTRS_SSE2                                                \
-  __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("sse2,no-evex512"), __min_vector_width__(128)))
-#else
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__, __target__("sse"),            \
                  __min_vector_width__(128)))
 #define __DEFAULT_FN_ATTRS_SSE2                                                \
   __attribute__((__always_inline__, __nodebug__, __target__("sse2"),           \
                  __min_vector_width__(128)))
-#endif
 
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
 #define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
@@ -239,10 +231,9 @@ _mm_div_ps(__m128 __a, __m128 __b) {
 ///    used in the calculation.
 /// \returns A 128-bit vector of [4 x float] containing the square root of the
 ///    value in the low-order bits of the operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_sqrt_ss(__m128 __a)
-{
-  return (__m128)__builtin_ia32_sqrtss((__v4sf)__a);
+static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_sqrt_ss(__m128 __a) {
+  __a[0] = __builtin_elementwise_sqrt(__a[0]);
+  return __a;
 }
 
 /// Calculates the square roots of the values stored in a 128-bit vector
@@ -256,10 +247,8 @@ _mm_sqrt_ss(__m128 __a)
 ///    A 128-bit vector of [4 x float].
 /// \returns A 128-bit vector of [4 x float] containing the square roots of the
 ///    values in the operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_sqrt_ps(__m128 __a)
-{
-  return __builtin_ia32_sqrtps((__v4sf)__a);
+static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_sqrt_ps(__m128 __a) {
+  return __builtin_elementwise_sqrt(__a);
 }
 
 /// Calculates the approximate reciprocal of the value stored in the
@@ -352,9 +341,7 @@ _mm_rsqrt_ps(__m128 __a)
 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
 ///    minimum value between both operands. The upper 96 bits are copied from
 ///    the upper 96 bits of the first source operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_min_ss(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_min_ss(__m128 __a, __m128 __b) {
   return __builtin_ia32_minss((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -373,9 +360,8 @@ _mm_min_ss(__m128 __a, __m128 __b)
 ///    A 128-bit vector of [4 x float] containing one of the operands.
 /// \returns A 128-bit vector of [4 x float] containing the minimum values
 ///    between both operands.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_min_ps(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_min_ps(__m128 __a,
+                                                                 __m128 __b) {
   return __builtin_ia32_minps((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -398,9 +384,7 @@ _mm_min_ps(__m128 __a, __m128 __b)
 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
 ///    maximum value between both operands. The upper 96 bits are copied from
 ///    the upper 96 bits of the first source operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_max_ss(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_max_ss(__m128 __a, __m128 __b) {
   return __builtin_ia32_maxss((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -419,9 +403,8 @@ _mm_max_ss(__m128 __a, __m128 __b)
 ///    A 128-bit vector of [4 x float] containing one of the operands.
 /// \returns A 128-bit vector of [4 x float] containing the maximum values
 ///    between both operands.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_max_ps(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_max_ps(__m128 __a,
+                                                                 __m128 __b) {
   return __builtin_ia32_maxps((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -1688,7 +1671,7 @@ _mm_cvtsi64_ss(__m128 __a, long long __b) {
 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
 ///    converted value of the second operand. The upper 64 bits are copied from
 ///    the upper 64 bits of the first operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpi32_ps(__m128 __a, __m64 __b)
 {
   return (__m128)__builtin_shufflevector(
@@ -1714,7 +1697,7 @@ _mm_cvtpi32_ps(__m128 __a, __m64 __b)
 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
 ///    converted value from the second operand. The upper 64 bits are copied
 ///    from the upper 64 bits of the first operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvt_pi2ps(__m128 __a, __m64 __b)
 {
   return _mm_cvtpi32_ps(__a, __b);
@@ -2353,9 +2336,8 @@ void _mm_sfence(void);
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the comparison results.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_max_pi16(__m64 __a, __m64 __b)
-{
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_max_pi16(__m64 __a, __m64 __b) {
   return (__m64)__builtin_elementwise_max((__v4hi)__a, (__v4hi)__b);
 }
 
@@ -2372,9 +2354,8 @@ _mm_max_pi16(__m64 __a, __m64 __b)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the comparison results.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_max_pu8(__m64 __a, __m64 __b)
-{
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_max_pu8(__m64 __a, __m64 __b) {
   return (__m64)__builtin_elementwise_max((__v8qu)__a, (__v8qu)__b);
 }
 
@@ -2391,9 +2372,8 @@ _mm_max_pu8(__m64 __a, __m64 __b)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the comparison results.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_min_pi16(__m64 __a, __m64 __b)
-{
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_min_pi16(__m64 __a, __m64 __b) {
   return (__m64)__builtin_elementwise_min((__v4hi)__a, (__v4hi)__b);
 }
 
@@ -2410,9 +2390,8 @@ _mm_min_pi16(__m64 __a, __m64 __b)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the comparison results.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_min_pu8(__m64 __a, __m64 __b)
-{
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_min_pu8(__m64 __a, __m64 __b) {
   return (__m64)__builtin_elementwise_min((__v8qu)__a, (__v8qu)__b);
 }
 
@@ -2428,9 +2407,8 @@ _mm_min_pu8(__m64 __a, __m64 __b)
 ///    A 64-bit integer vector containing the values with bits to be extracted.
 /// \returns The most significant bit from each 8-bit element in \a __a,
 ///    written to bits [7:0].
-static __inline__ int __DEFAULT_FN_ATTRS_SSE2
-_mm_movemask_pi8(__m64 __a)
-{
+static __inline__ int __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_movemask_pi8(__m64 __a) {
   return __builtin_ia32_pmovmskb128((__v16qi)__zext128(__a));
 }
 
@@ -2447,11 +2425,11 @@ _mm_movemask_pi8(__m64 __a)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the products of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_mulhi_pu16(__m64 __a, __m64 __b)
 {
-  return __trunc64(__builtin_ia32_pmulhuw128((__v8hi)__anyext128(__a),
-                                             (__v8hi)__anyext128(__b)));
+  return __trunc64(__builtin_ia32_pmulhuw128((__v8hu)__zext128(__a),
+                                             (__v8hu)__zext128(__b)));
 }
 
 /// Shuffles the 4 16-bit integers from a 64-bit integer vector to the
@@ -2530,8 +2508,8 @@ _mm_maskmove_si64(__m64 __d, __m64 __n, char *__p)
     // If there's a risk of spurious trap due to a 128-bit write, back up the
     // pointer by 8 bytes and shift values in registers to match.
     __p -= 8;
-    __d128 = __builtin_ia32_pslldqi128_byteshift((__v2di)__d128, 8);
-    __n128 = __builtin_ia32_pslldqi128_byteshift((__v2di)__n128, 8);
+    __d128 = (__m128i)__builtin_ia32_pslldqi128_byteshift((__v16qi)__d128, 8);
+    __n128 = (__m128i)__builtin_ia32_pslldqi128_byteshift((__v16qi)__n128, 8);
   }
 
   __builtin_ia32_maskmovdqu((__v16qi)__d128, (__v16qi)__n128, __p);
@@ -2550,11 +2528,10 @@ _mm_maskmove_si64(__m64 __d, __m64 __n, char *__p)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the averages of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_avg_pu8(__m64 __a, __m64 __b)
-{
-  return __trunc64(__builtin_ia32_pavgb128((__v16qi)__anyext128(__a),
-                                           (__v16qi)__anyext128(__b)));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_avg_pu8(__m64 __a, __m64 __b) {
+  return __trunc64(__builtin_ia32_pavgb128((__v16qu)__zext128(__a),
+                                           (__v16qu)__zext128(__b)));
 }
 
 /// Computes the rounded averages of the packed unsigned 16-bit integer
@@ -2570,11 +2547,10 @@ _mm_avg_pu8(__m64 __a, __m64 __b)
 /// \param __b
 ///    A 64-bit integer vector containing one of the source operands.
 /// \returns A 64-bit integer vector containing the averages of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_avg_pu16(__m64 __a, __m64 __b)
-{
-  return __trunc64(__builtin_ia32_pavgw128((__v8hi)__anyext128(__a),
-                                           (__v8hi)__anyext128(__b)));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_avg_pu16(__m64 __a, __m64 __b) {
+  return __trunc64(
+      __builtin_ia32_pavgw128((__v8hu)__zext128(__a), (__v8hu)__zext128(__b)));
 }
 
 /// Subtracts the corresponding 8-bit unsigned integer values of the two
@@ -2873,7 +2849,7 @@ _mm_movelh_ps(__m128 __a, __m128 __b) {
 ///    from the corresponding elements in this operand.
 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
 ///    values from the operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpi16_ps(__m64 __a)
 {
   return __builtin_convertvector((__v4hi)__a, __v4sf);
@@ -2891,7 +2867,7 @@ _mm_cvtpi16_ps(__m64 __a)
 ///    destination are copied from the corresponding elements in this operand.
 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
 ///    values from the operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpu16_ps(__m64 __a)
 {
   return __builtin_convertvector((__v4hu)__a, __v4sf);
@@ -2909,7 +2885,7 @@ _mm_cvtpu16_ps(__m64 __a)
 ///    from the corresponding lower 4 elements in this operand.
 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
 ///    values from the operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpi8_ps(__m64 __a)
 {
   return __builtin_convertvector(
@@ -2930,7 +2906,7 @@ _mm_cvtpi8_ps(__m64 __a)
 ///    operand.
 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
 ///    values from the source operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpu8_ps(__m64 __a)
 {
   return __builtin_convertvector(
@@ -2954,7 +2930,7 @@ _mm_cvtpu8_ps(__m64 __a)
 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
 ///    copied and converted values from the first operand. The upper 64 bits
 ///    contain the copied and converted values from the second operand.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m128 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_cvtpi32x2_ps(__m64 __a, __m64 __b)
 {
   return __builtin_convertvector(
@@ -3029,9 +3005,7 @@ _mm_cvtps_pi8(__m128 __a)
 /// \returns A 32-bit integer value. Bits [3:0] contain the sign bits from each
 ///    single-precision floating-point element of the parameter. Bits [31:4] are
 ///    set to zero.
-static __inline__ int __DEFAULT_FN_ATTRS
-_mm_movemask_ps(__m128 __a)
-{
+static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR _mm_movemask_ps(__m128 __a) {
   return __builtin_ia32_movmskps((__v4sf)__a);
 }
 

package/include/xopintrin.h

@@ -20,6 +20,14 @@
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("xop"), __min_vector_width__(128)))
 #define __DEFAULT_FN_ATTRS256 __attribute__((__always_inline__, __nodebug__, __target__("xop"), __min_vector_width__(256)))
 
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
+#define __DEFAULT_FN_ATTRS256_CONSTEXPR __DEFAULT_FN_ATTRS256 constexpr
+#else
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#define __DEFAULT_FN_ATTRS256_CONSTEXPR __DEFAULT_FN_ATTRS256
+#endif
+
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_maccs_epi16(__m128i __A, __m128i __B, __m128i __C)
 {
@@ -182,13 +190,13 @@ _mm_hsubq_epi32(__m128i __A)
   return (__m128i)__builtin_ia32_vphsubdq((__v4si)__A);
 }
 
-static __inline__ __m128i __DEFAULT_FN_ATTRS
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_cmov_si128(__m128i __A, __m128i __B, __m128i __C)
 {
   return (__m128i)(((__v2du)__A & (__v2du)__C) | ((__v2du)__B & ~(__v2du)__C));
 }
 
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmov_si256(__m256i __A, __m256i __B, __m256i __C)
 {
   return (__m256i)(((__v4du)__A & (__v4du)__C) | ((__v4du)__B & ~(__v4du)__C));
@@ -200,28 +208,28 @@ _mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
   return (__m128i)__builtin_ia32_vpperm((__v16qi)__A, (__v16qi)__B, (__v16qi)__C);
 }
 
-static __inline__ __m128i __DEFAULT_FN_ATTRS
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_rot_epi8(__m128i __A, __m128i __B)
 {
-  return (__m128i)__builtin_ia32_vprotb((__v16qi)__A, (__v16qi)__B);
+  return (__m128i)__builtin_elementwise_fshl((__v16qu)__A, (__v16qu)__A, (__v16qu)__B);
 }
 
-static __inline__ __m128i __DEFAULT_FN_ATTRS
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_rot_epi16(__m128i __A, __m128i __B)
 {
-  return (__m128i)__builtin_ia32_vprotw((__v8hi)__A, (__v8hi)__B);
+  return (__m128i)__builtin_elementwise_fshl((__v8hu)__A, (__v8hu)__A, (__v8hu)__B);
 }
 
-static __inline__ __m128i __DEFAULT_FN_ATTRS
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_rot_epi32(__m128i __A, __m128i __B)
 {
-  return (__m128i)__builtin_ia32_vprotd((__v4si)__A, (__v4si)__B);
+  return (__m128i)__builtin_elementwise_fshl((__v4su)__A, (__v4su)__A, (__v4su)__B);
 }
 
-static __inline__ __m128i __DEFAULT_FN_ATTRS
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_rot_epi64(__m128i __A, __m128i __B)
 {
-  return (__m128i)__builtin_ia32_vprotq((__v2di)__A, (__v2di)__B);
+  return (__m128i)__builtin_elementwise_fshl((__v2du)__A, (__v2du)__A, (__v2du)__B);
 }
 
 #define _mm_roti_epi8(A, N) \
@@ -766,5 +774,7 @@ _mm256_frcz_pd(__m256d __A)
 
 #undef __DEFAULT_FN_ATTRS
 #undef __DEFAULT_FN_ATTRS256
+#undef __DEFAULT_FN_ATTRS_CONSTEXPR
+#undef __DEFAULT_FN_ATTRS256_CONSTEXPR
 
 #endif /* __XOPINTRIN_H */

package/libcxx/include/__algorithm/all_of.h

@@ -10,24 +10,28 @@
 #ifndef _LIBCPP___ALGORITHM_ALL_OF_H
 #define _LIBCPP___ALGORITHM_ALL_OF_H
 
+#include <__algorithm/any_of.h>
 #include <__config>
 #include <__functional/identity.h>
 #include <__type_traits/invoke.h>
+#include <__utility/forward.h>
+#include <__utility/move.h>
 
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
 #  pragma GCC system_header
 #endif
 
+_LIBCPP_PUSH_MACROS
+#include <__undef_macros>
+
 _LIBCPP_BEGIN_NAMESPACE_STD
 
 template <class _Iter, class _Sent, class _Proj, class _Pred>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 bool
 __all_of(_Iter __first, _Sent __last, _Pred& __pred, _Proj& __proj) {
-  for (; __first != __last; ++__first) {
-    if (!std::__invoke(__pred, std::__invoke(__proj, *__first)))
-      return false;
-  }
-  return true;
+  using _Ref          = decltype(std::__invoke(__proj, *__first));
+  auto __negated_pred = [&__pred](_Ref __arg) -> bool { return !std::__invoke(__pred, std::forward<_Ref>(__arg)); };
+  return !std::__any_of(std::move(__first), std::move(__last), __negated_pred, __proj);
 }
 
 template <class _InputIterator, class _Predicate>
@@ -39,4 +43,6 @@ all_of(_InputIterator __first, _InputIterator __last, _Predicate __pred) {
 
 _LIBCPP_END_NAMESPACE_STD
 
+_LIBCPP_POP_MACROS
+
 #endif // _LIBCPP___ALGORITHM_ALL_OF_H

package/libcxx/include/__algorithm/comp.h

@@ -11,6 +11,7 @@
 
 #include <__config>
 #include <__type_traits/desugars_to.h>
+#include <__type_traits/is_generic_transparent_comparator.h>
 #include <__type_traits/is_integral.h>
 
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
@@ -48,6 +49,9 @@ inline const bool __desugars_to_v<__less_tag, __less<>, _Tp, _Tp> = true;
 template <class _Tp>
 inline const bool __desugars_to_v<__totally_ordered_less_tag, __less<>, _Tp, _Tp> = is_integral<_Tp>::value;
 
+template <>
+inline const bool __is_generic_transparent_comparator_v<__less<> > = true;
+
 _LIBCPP_END_NAMESPACE_STD
 
 #endif // _LIBCPP___ALGORITHM_COMP_H

package/libcxx/include/__algorithm/copy.h

@@ -12,11 +12,10 @@
 #include <__algorithm/copy_move_common.h>
 #include <__algorithm/for_each_segment.h>
 #include <__algorithm/min.h>
+#include <__algorithm/specialized_algorithms.h>
 #include <__config>
-#include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
 #include <__iterator/segmented_iterator.h>
-#include <__memory/pointer_traits.h>
 #include <__type_traits/common_type.h>
 #include <__type_traits/enable_if.h>
 #include <__utility/move.h>
@@ -38,124 +37,14 @@ copy(_InputIterator __first, _InputIterator __last, _OutputIterator __result);
 template <class _InIter, class _Sent, class _OutIter>
 inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter> __copy(_InIter, _Sent, _OutIter);
 
-template <class _Cp, bool _IsConst>
-_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_aligned(
-    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
-  using _In             = __bit_iterator<_Cp, _IsConst>;
-  using difference_type = typename _In::difference_type;
-  using __storage_type  = typename _In::__storage_type;
-
-  const int __bits_per_word = _In::__bits_per_word;
-  difference_type __n       = __last - __first;
-  if (__n > 0) {
-    // do first word
-    if (__first.__ctz_ != 0) {
-      unsigned __clz       = __bits_per_word - __first.__ctz_;
-      difference_type __dn = std::min(static_cast<difference_type>(__clz), __n);
-      __n -= __dn;
-      __storage_type __m = std::__middle_mask<__storage_type>(__clz - __dn, __first.__ctz_);
-      __storage_type __b = *__first.__seg_ & __m;
-      *__result.__seg_ &= ~__m;
-      *__result.__seg_ |= __b;
-      __result.__seg_ += (__dn + __result.__ctz_) / __bits_per_word;
-      __result.__ctz_ = static_cast<unsigned>((__dn + __result.__ctz_) % __bits_per_word);
-      ++__first.__seg_;
-      // __first.__ctz_ = 0;
-    }
-    // __first.__ctz_ == 0;
-    // do middle words
-    __storage_type __nw = __n / __bits_per_word;
-    std::copy(std::__to_address(__first.__seg_),
-              std::__to_address(__first.__seg_ + __nw),
-              std::__to_address(__result.__seg_));
-    __n -= __nw * __bits_per_word;
-    __result.__seg_ += __nw;
-    // do last word
-    if (__n > 0) {
-      __first.__seg_ += __nw;
-      __storage_type __m = std::__trailing_mask<__storage_type>(__bits_per_word - __n);
-      __storage_type __b = *__first.__seg_ & __m;
-      *__result.__seg_ &= ~__m;
-      *__result.__seg_ |= __b;
-      __result.__ctz_ = static_cast<unsigned>(__n);
-    }
-  }
-  return __result;
-}
-
-template <class _Cp, bool _IsConst>
-_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_unaligned(
-    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
-  using _In             = __bit_iterator<_Cp, _IsConst>;
-  using difference_type = typename _In::difference_type;
-  using __storage_type  = typename _In::__storage_type;
-
-  const int __bits_per_word = _In::__bits_per_word;
-  difference_type __n       = __last - __first;
-  if (__n > 0) {
-    // do first word
-    if (__first.__ctz_ != 0) {
-      unsigned __clz_f     = __bits_per_word - __first.__ctz_;
-      difference_type __dn = std::min(static_cast<difference_type>(__clz_f), __n);
-      __n -= __dn;
-      __storage_type __m   = std::__middle_mask<__storage_type>(__clz_f - __dn, __first.__ctz_);
-      __storage_type __b   = *__first.__seg_ & __m;
-      unsigned __clz_r     = __bits_per_word - __result.__ctz_;
-      __storage_type __ddn = std::min<__storage_type>(__dn, __clz_r);
-      __m                  = std::__middle_mask<__storage_type>(__clz_r - __ddn, __result.__ctz_);
-      *__result.__seg_ &= ~__m;
-      if (__result.__ctz_ > __first.__ctz_)
-        *__result.__seg_ |= __b << (__result.__ctz_ - __first.__ctz_);
-      else
-        *__result.__seg_ |= __b >> (__first.__ctz_ - __result.__ctz_);
-      __result.__seg_ += (__ddn + __result.__ctz_) / __bits_per_word;
-      __result.__ctz_ = static_cast<unsigned>((__ddn + __result.__ctz_) % __bits_per_word);
-      __dn -= __ddn;
-      if (__dn > 0) {
-        __m = std::__trailing_mask<__storage_type>(__bits_per_word - __dn);
-        *__result.__seg_ &= ~__m;
-        *__result.__seg_ |= __b >> (__first.__ctz_ + __ddn);
-        __result.__ctz_ = static_cast<unsigned>(__dn);
-      }
-      ++__first.__seg_;
-      // __first.__ctz_ = 0;
-    }
-    // __first.__ctz_ == 0;
-    // do middle words
-    unsigned __clz_r   = __bits_per_word - __result.__ctz_;
-    __storage_type __m = std::__leading_mask<__storage_type>(__result.__ctz_);
-    for (; __n >= __bits_per_word; __n -= __bits_per_word, ++__first.__seg_) {
-      __storage_type __b = *__first.__seg_;
-      *__result.__seg_ &= ~__m;
-      *__result.__seg_ |= __b << __result.__ctz_;
-      ++__result.__seg_;
-      *__result.__seg_ &= __m;
-      *__result.__seg_ |= __b >> __clz_r;
-    }
-    // do last word
-    if (__n > 0) {
-      __m                 = std::__trailing_mask<__storage_type>(__bits_per_word - __n);
-      __storage_type __b  = *__first.__seg_ & __m;
-      __storage_type __dn = std::min(__n, static_cast<difference_type>(__clz_r));
-      __m                 = std::__middle_mask<__storage_type>(__clz_r - __dn, __result.__ctz_);
-      *__result.__seg_ &= ~__m;
-      *__result.__seg_ |= __b << __result.__ctz_;
-      __result.__seg_ += (__dn + __result.__ctz_) / __bits_per_word;
-      __result.__ctz_ = static_cast<unsigned>((__dn + __result.__ctz_) % __bits_per_word);
-      __n -= __dn;
-      if (__n > 0) {
-        __m = std::__trailing_mask<__storage_type>(__bits_per_word - __n);
-        *__result.__seg_ &= ~__m;
-        *__result.__seg_ |= __b >> __dn;
-        __result.__ctz_ = static_cast<unsigned>(__n);
-      }
-    }
-  }
-  return __result;
-}
-
 struct __copy_impl {
-  template <class _InIter, class _Sent, class _OutIter>
+  template <class _InIter,
+            class _Sent,
+            class _OutIter,
+            __enable_if_t<!__specialized_algorithm<_Algorithm::__copy,
+                                                   __iterator_pair<_InIter, _Sent>,
+                                                   __single_iterator<_OutIter> >::__has_algorithm,
+                          int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter>
   operator()(_InIter __first, _Sent __last, _OutIter __result) const {
     while (__first != __last) {
@@ -167,37 +56,39 @@ struct __copy_impl {
     return std::make_pair(std::move(__first), std::move(__result));
   }
 
-  template <class _InIter, class _OutIter>
-  struct _CopySegment {
-    using _Traits _LIBCPP_NODEBUG = __segmented_iterator_traits<_InIter>;
-
-    _OutIter& __result_;
-
-    _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 explicit _CopySegment(_OutIter& __result)
-        : __result_(__result) {}
-
-    _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 void
-    operator()(typename _Traits::__local_iterator __lfirst, typename _Traits::__local_iterator __llast) {
-      __result_ = std::__copy(__lfirst, __llast, std::move(__result_)).second;
-    }
-  };
+  template <class _InIter,
+            class _Sent,
+            class _OutIter,
+            __enable_if_t<__specialized_algorithm<_Algorithm::__copy,
+                                                  __iterator_pair<_InIter, _Sent>,
+                                                  __single_iterator<_OutIter> >::__has_algorithm,
+                          int> = 0>
+  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 static pair<_InIter, _OutIter>
+  operator()(_InIter __first, _Sent __last, _OutIter __result) {
+    return __specialized_algorithm<_Algorithm::__copy, __iterator_pair<_InIter, _Sent>, __single_iterator<_OutIter> >()(
+        std::move(__first), std::move(__last), std::move(__result));
+  }
 
-  template <class _InIter, class _OutIter, __enable_if_t<__is_segmented_iterator<_InIter>::value, int> = 0>
+  template <class _InIter, class _OutIter, __enable_if_t<__is_segmented_iterator_v<_InIter>, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter>
   operator()(_InIter __first, _InIter __last, _OutIter __result) const {
-    std::__for_each_segment(__first, __last, _CopySegment<_InIter, _OutIter>(__result));
+    using __local_iterator = typename __segmented_iterator_traits<_InIter>::__local_iterator;
+    std::__for_each_segment(__first, __last, [&__result](__local_iterator __lfirst, __local_iterator __llast) {
+      __result = std::__copy(std::move(__lfirst), std::move(__llast), std::move(__result)).second;
+    });
     return std::make_pair(__last, std::move(__result));
   }
 
   template <class _InIter,
             class _OutIter,
             __enable_if_t<__has_random_access_iterator_category<_InIter>::value &&
-                              !__is_segmented_iterator<_InIter>::value && __is_segmented_iterator<_OutIter>::value,
+                              !__is_segmented_iterator_v<_InIter> && __is_segmented_iterator_v<_OutIter>,
                           int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter>
   operator()(_InIter __first, _InIter __last, _OutIter __result) const {
     using _Traits = __segmented_iterator_traits<_OutIter>;
-    using _DiffT  = typename common_type<__iter_diff_t<_InIter>, __iter_diff_t<_OutIter> >::type;
+    using _DiffT =
+        typename common_type<__iterator_difference_type<_InIter>, __iterator_difference_type<_OutIter> >::type;
 
     if (__first == __last)
       return std::make_pair(std::move(__first), std::move(__result));
@@ -217,16 +108,6 @@ struct __copy_impl {
     }
   }
 
-  template <class _Cp, bool _IsConst>
-  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<__bit_iterator<_Cp, _IsConst>, __bit_iterator<_Cp, false> >
-  operator()(__bit_iterator<_Cp, _IsConst> __first,
-             __bit_iterator<_Cp, _IsConst> __last,
-             __bit_iterator<_Cp, false> __result) const {
-    if (__first.__ctz_ == __result.__ctz_)
-      return std::make_pair(__last, std::__copy_aligned(__first, __last, __result));
-    return std::make_pair(__last, std::__copy_unaligned(__first, __last, __result));
-  }
-
   // At this point, the iterators have been unwrapped so any `contiguous_iterator` has been unwrapped to a pointer.
   template <class _In, class _Out, __enable_if_t<__can_lower_copy_assignment_to_memmove<_In, _Out>::value, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_In*, _Out*>