mirror of
https://github.com/nlohmann/json.git
synced 2026-10-06 14:40:32 +00:00
Niels Lohmann
17842694f6
Write doubles with the conversion of Zmij by Victor Zverovich (MIT), ported to C++11 (detail/conversions/zmij.hpp). It finds the shortest decimal that reads back as the same double, and the closest one if there are several. Grisu2, used until now, is fast but not always shortest: it sometimes writes a 17th digit where 16 suffice, or a last digit that is not the closest. The layout is unchanged (1.5, 100.0, 1e+100, -0.0); float keeps Grisu2. Digits are converted eight at a time with the BCD conversion of Xiang JunBo, as in Zmij, and written with one byte swap per eight digits and fixed-size moves instead of per-digit loops. Leading and trailing zeros are counted from those bytes. to_chars() uses a local buffer when the caller's is shorter than the 41 bytes this may write. The powers of ten come from the number-parsing table, adjusted where it holds values rounded up, and extended with Zmij's compressed tables beyond 10^308. write_shortest() converts its 16 digits in one vector register (SSE2 on x86-64, NEON on 64-bit Arm, both baseline) and inserts the decimal point inside the register, avoiding a store-forwarding stall that cost about 25% of the time to write a double. dump() writes floats and integers straight into the serializer's write buffer instead of copying them from a member buffer, and small integers eight digits at a time. read_eight_bytes() and parse_eight_digits() are marked always-inline, which GCC had been calling out of line in the number-parsing loops. Of one million random doubles, about 0.14% are now written with different digits, always to a value that still reads back as the same double. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
107 lines
3.3 KiB
C++
107 lines
3.3 KiB
C++
// __ _____ _____ _____
|
|
// __| | __| | | | JSON for Modern C++
|
|
// | | |__ | | | | | | version 3.12.0
|
|
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
|
|
//
|
|
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#pragma once
|
|
|
|
#include <cstdint> // uint64_t
|
|
|
|
#include <nlohmann/detail/abi_macros.hpp>
|
|
|
|
// Portable bit-level helpers for the number and string scanners. They use
|
|
// compiler builtins where available and plain C++ otherwise, so they need no
|
|
// platform headers and work regardless of byte order.
|
|
|
|
NLOHMANN_JSON_NAMESPACE_BEGIN
|
|
namespace detail
|
|
{
|
|
|
|
/// number of leading zero bits of x (x != 0)
|
|
inline int count_leading_zeros(std::uint64_t x) noexcept
|
|
{
|
|
#if defined(__GNUC__) || defined(__clang__)
|
|
return __builtin_clzll(x);
|
|
#else
|
|
int n = 0;
|
|
for (int shift = 32; shift != 0; shift >>= 1)
|
|
{
|
|
if ((x >> (64 - shift)) == 0)
|
|
{
|
|
n += shift;
|
|
x <<= shift;
|
|
}
|
|
}
|
|
return n;
|
|
#endif
|
|
}
|
|
|
|
/// number of trailing zero bits of x (x != 0)
|
|
inline int count_trailing_zeros(std::uint64_t x) noexcept
|
|
{
|
|
#if defined(__GNUC__) || defined(__clang__)
|
|
return __builtin_ctzll(x);
|
|
#else
|
|
int n = 0;
|
|
for (int shift = 32; shift != 0; shift >>= 1)
|
|
{
|
|
if ((x << (64 - shift)) == 0)
|
|
{
|
|
n += shift;
|
|
x >>= shift;
|
|
}
|
|
}
|
|
return n;
|
|
#endif
|
|
}
|
|
|
|
/// the 128-bit product of two 64-bit numbers
|
|
struct uint128_parts
|
|
{
|
|
std::uint64_t low;
|
|
std::uint64_t high;
|
|
};
|
|
|
|
inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexcept
|
|
{
|
|
#if defined(__SIZEOF_INT128__)
|
|
__extension__ using uint128 = unsigned __int128;
|
|
const uint128 r = static_cast<uint128>(a) * b;
|
|
return {static_cast<std::uint64_t>(r), static_cast<std::uint64_t>(r >> 64u)};
|
|
#else
|
|
const std::uint64_t a_lo = a & 0xFFFFFFFFu;
|
|
const std::uint64_t a_hi = a >> 32u;
|
|
const std::uint64_t b_lo = b & 0xFFFFFFFFu;
|
|
const std::uint64_t b_hi = b >> 32u;
|
|
const std::uint64_t lo_lo = a_lo * b_lo;
|
|
const std::uint64_t hi_lo = a_hi * b_lo;
|
|
const std::uint64_t lo_hi = a_lo * b_hi;
|
|
const std::uint64_t hi_hi = a_hi * b_hi;
|
|
const std::uint64_t cross = (lo_lo >> 32u) + (hi_lo & 0xFFFFFFFFu) + lo_hi;
|
|
return {(cross << 32u) | (lo_lo & 0xFFFFFFFFu), (hi_lo >> 32u) + (cross >> 32u) + hi_hi};
|
|
#endif
|
|
}
|
|
|
|
/// eight bytes as a little-endian word (compilers fold this into one load on
|
|
/// little-endian targets; always inlined, as GCC otherwise calls it in the
|
|
/// number loops)
|
|
JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
|
|
{
|
|
return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
|
|
| (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
|
|
| (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
|
|
| (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
|
|
}
|
|
|
|
/// eight bytes as a little-endian word
|
|
JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const char* p) noexcept
|
|
{
|
|
return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
|
|
}
|
|
|
|
} // namespace detail
|
|
NLOHMANN_JSON_NAMESPACE_END
|