diff options
author | Matthias Kretz <m.kretz@gsi.de> | 2023-05-23 23:48:49 +0200 |
---|---|---|
committer | Matthias Kretz <m.kretz@gsi.de> | 2023-05-24 13:06:35 +0200 |
commit | b0a483b0a011f9cbc8b25053eae809c77dae2a12 (patch) | |
tree | a785c19e946b41a7f4d844073a245b4b391aa9ba | |
parent | b4df098647b687ca4e43952ec4a198b2816732ba (diff) | |
download | gcc-b0a483b0a011f9cbc8b25053eae809c77dae2a12.zip gcc-b0a483b0a011f9cbc8b25053eae809c77dae2a12.tar.gz gcc-b0a483b0a011f9cbc8b25053eae809c77dae2a12.tar.bz2 |
libstdc++: Add missing constexpr to simd_neon
Signed-off-by: Matthias Kretz <m.kretz@gsi.de>
libstdc++-v3/ChangeLog:
PR libstdc++/109261
* include/experimental/bits/simd_neon.h (_S_reduce): Add
constexpr and make NEON implementation conditional on
not __builtin_is_constant_evaluated.
-rw-r--r-- | libstdc++-v3/include/experimental/bits/simd_neon.h | 76 |
1 files changed, 36 insertions, 40 deletions
diff --git a/libstdc++-v3/include/experimental/bits/simd_neon.h b/libstdc++-v3/include/experimental/bits/simd_neon.h index 637b121..8f732d7 100644 --- a/libstdc++-v3/include/experimental/bits/simd_neon.h +++ b/libstdc++-v3/include/experimental/bits/simd_neon.h @@ -84,50 +84,46 @@ template <typename _Abi, typename> // }}} // _S_reduce {{{ template <typename _Tp, typename _BinaryOperation> - _GLIBCXX_SIMD_INTRINSIC static _Tp + _GLIBCXX_SIMD_INTRINSIC static constexpr _Tp _S_reduce(simd<_Tp, _Abi> __x, _BinaryOperation&& __binary_op) { - constexpr size_t _Np = __x.size(); - if constexpr (sizeof(__x) == 16 && _Np >= 4 - && !_Abi::template _S_is_partial<_Tp>) - { - const auto __halves = split<simd<_Tp, simd_abi::_Neon<8>>>(__x); - const auto __y = __binary_op(__halves[0], __halves[1]); - return _SimdImplNeon<simd_abi::_Neon<8>>::_S_reduce( - __y, static_cast<_BinaryOperation&&>(__binary_op)); - } - else if constexpr (_Np == 8) - { - __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<1, 0, 3, 2, 5, 4, 7, 6>( - __x._M_data))); - __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<3, 2, 1, 0, 7, 6, 5, 4>( - __x._M_data))); - __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<7, 6, 5, 4, 3, 2, 1, 0>( - __x._M_data))); - return __x[0]; - } - else if constexpr (_Np == 4) - { - __x - = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<1, 0, 3, 2>(__x._M_data))); - __x - = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<3, 2, 1, 0>(__x._M_data))); - return __x[0]; - } - else if constexpr (_Np == 2) + if (not __builtin_is_constant_evaluated()) { - __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( - __vector_permute<1, 0>(__x._M_data))); - return __x[0]; + constexpr size_t _Np = __x.size(); + if constexpr (sizeof(__x) == 16 && _Np >= 4 + && !_Abi::template _S_is_partial<_Tp>) + { + const auto __halves = split<simd<_Tp, simd_abi::_Neon<8>>>(__x); + const auto __y = __binary_op(__halves[0], __halves[1]); + return _SimdImplNeon<simd_abi::_Neon<8>>::_S_reduce( + __y, static_cast<_BinaryOperation&&>(__binary_op)); + } + else if constexpr (_Np == 8) + { + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<1, 0, 3, 2, 5, 4, 7, 6>(__x._M_data))); + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<3, 2, 1, 0, 7, 6, 5, 4>(__x._M_data))); + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<7, 6, 5, 4, 3, 2, 1, 0>(__x._M_data))); + return __x[0]; + } + else if constexpr (_Np == 4) + { + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<1, 0, 3, 2>(__x._M_data))); + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<3, 2, 1, 0>(__x._M_data))); + return __x[0]; + } + else if constexpr (_Np == 2) + { + __x = __binary_op(__x, _Base::template _M_make_simd<_Tp, _Np>( + __vector_permute<1, 0>(__x._M_data))); + return __x[0]; + } } - else - return _Base::_S_reduce(__x, - static_cast<_BinaryOperation&&>(__binary_op)); + return _Base::_S_reduce(__x, static_cast<_BinaryOperation&&>(__binary_op)); } // }}} |