wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-11-10 16:31:28 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
9bee955345cde47305d1470ece021817fbce2224
json/include/nlohmann/detail/input/simd_scan.hpp
T
Niels Lohmann 9bee955345 perf: check whole UTF-8 strings without waiting for each block's result 
valid_utf8_string() checks long strings 16 bytes at a time in
vector_utf8_valid_blocks(), which left its loop at the first block with
an error. Clang compiles "if (error) break; block += 16;" into a
conditional select on the block pointer, so each block waited for the
complete check of the block before: 28 cycles for 16 bytes on Apple M1.

The errors of all blocks are now collected and tested once at the end.
ASCII blocks are skipped in a loop of their own that needs none of the
lookup tables, and from the first block that is not ASCII, eight blocks
are checked without testing for ASCII in between, which was a
mispredicted branch for text with a few non-ASCII characters. If any
block had an error, the caller finds it one sequence at a time from the
start of the string, as before from the block with the error.

The check is used by the binary writers and readers with an error
handler other than keep, and always by BON8. On Apple M1 (Apple Clang),
it needs 0.27 instead of 1.78 cycles per byte for non-ASCII text, and
to_msgpack() with error_handler_t::strict is 24 to 43 % faster for such
text. With GCC 15 on x86-64, where the loop was not affected, the check
itself is 13 to 35 % faster.

A new test puts well-formed and ill-formed sequences at every offset of
strings that are longer than eight blocks.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-11-10 10:07:56 +01:00

443 lines
21 KiB
C++
Raw Blame History

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-FileCopyrightText: 2018-2025 The simdjson authors <https://github.com/simdjson/simdjson>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <atomic> // atomic
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint64_t
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Vector code for runs of string bytes, used by the lexer for contiguous input
// (see string_bulk_run()). NEON (AArch64) and SSE2 (x86-64) belong to the
// baseline instruction sets and are used by default. The vector UTF-8 check
// needs NEON or SSSE3. SSSE3 is not part of x86-64, and the code must not
// depend on the flags of a translation unit (two translation units with
// different flags would have different definitions of the same inline
// functions): the check is compiled for SSSE3 with a function attribute and
// used where the CPU has SSSE3 (all x86-64 CPUs since about 2011), else the
// portable check. Code compiled for SSSE3 anyway (-mssse3 or more) skips the
// CPU check. JSON_NO_SIMD selects the portable code everywhere.
// NLOHMANN_JSON_NO_TARGET_ATTRIBUTE (for compilers that ignore the target
// attribute and then reject the SSSE3 intrinsics) keeps the check portable
// without disabling the SSE2 code.
//
// The vector UTF-8 check (utf8_lookup4) is adapted from simdjson
// (https://github.com/simdjson/simdjson, Daniel Lemire, Geoff Langdale, John
// Keiser, and contributors, available under the Apache 2.0 and MIT licenses;
// used here under the MIT license): the "lookup4" algorithm and tables of
// J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per
// Byte" (2021).
#if !defined(JSON_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#include <arm_neon.h>
#define JSON_SCAN_NEON 1
#else
#define JSON_SCAN_NEON 0
#endif
// (x86 only: other targets can define __SSE2__ as well, e.g., WebAssembly with -msse2, but have no <cpuid.h>)
#if !defined(JSON_NO_SIMD) && !JSON_SCAN_NEON && (defined(__x86_64__) || defined(__i386__) || defined(_M_X64) || defined(_M_IX86)) && !defined(_M_ARM64EC) && (defined(__SSE2__) || defined(_M_X64) || (defined(_M_IX86_FP) && _M_IX86_FP >= 2))
#include <emmintrin.h>
#define JSON_SCAN_SSE2 1
#else
#define JSON_SCAN_SSE2 0
#endif
#if JSON_SCAN_SSE2 && defined(__SSSE3__)
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#else
#define JSON_SCAN_SSSE3 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#endif
#if JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && !defined(NLOHMANN_JSON_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)) && !defined(__cpp_modules)))
// (GCC before 4.9 has no SSSE3 intrinsics without -mssse3; GCC with C++20
// modules drops the target attribute from functions it reads from a module
// interface and then rejects the intrinsics: "needs isa option -mssse3")
// <cpuid.h> of GCC before 11 has no include guard, and json.hpp and
// json_view.hpp both include it
#ifndef NLOHMANN_JSON_CPUID_INCLUDED
#define NLOHMANN_JSON_CPUID_INCLUDED
#include <cpuid.h>
#endif
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET __attribute__((target("ssse3")))
#elif JSON_SCAN_SSE2 && !JSON_SCAN_SSSE3 && defined(_MSC_VER)
// (MSVC compiles intrinsics of any instruction set)
#include <intrin.h>
#include <tmmintrin.h>
#define JSON_SCAN_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET
#else
#define JSON_SCAN_SSSE3_DISPATCH 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define JSON_SCAN_SSSE3_TARGET
#endif
#define JSON_SCAN_VECTOR (JSON_SCAN_NEON || JSON_SCAN_SSE2)
#define JSON_SCAN_VECTOR_UTF8 (JSON_SCAN_NEON || JSON_SCAN_SSSE3 || JSON_SCAN_SSSE3_DISPATCH)
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
#if JSON_SCAN_VECTOR
/*!
@brief the first byte of a string run that is a quote, a backslash, a control
character, or not ASCII, 16 bytes per step
Stops at such a byte, or where fewer than 16 bytes are left (the caller tells
the two apart). A signed compare with 0x20 finds control characters and
non-ASCII bytes at once.
*/
JSON_HEDLEY_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
{
while (e - p >= 16)
{
#if JSON_SCAN_NEON
const uint8x16_t in = vld1q_u8(p);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
// one nibble per byte (the usual NEON replacement of x86's movemask, see
// D. Kutenin, "Porting x86 vector bitmask optimizations to Arm NEON", 2022)
const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
if (bits != 0)
{
return p + (count_trailing_zeros(bits) >> 2u);
}
#else
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
if (bits != 0)
{
return p + count_trailing_zeros(bits);
}
#endif
p += 16;
}
return p;
}
#endif
#if JSON_SCAN_VECTOR
/// vector_plain_run() for runs that are already longer than a few words:
/// inline with SSE2, out of line with NEON, where a larger string loop slows
/// down the rest of the lexer
#if JSON_SCAN_NEON
JSON_HEDLEY_NEVER_INLINE inline
#else
JSON_HEDLEY_ALWAYS_INLINE
#endif
const unsigned char* vector_plain_run_long(const unsigned char* p, const unsigned char* e) noexcept
{
return vector_plain_run(p, e);
}
#endif
#if JSON_SCAN_SSSE3_DISPATCH
/// whether the CPU has SSSE3 (CPUID leaf 1, ECX bit 9)
inline bool cpu_ssse3() noexcept
{
#if defined(_MSC_VER) && !defined(__clang__)
std::array<int, 4> regs {{}};
__cpuid(regs.data(), 1);
return (static_cast<unsigned>(regs[2]) & (1u << 9u)) != 0;
#else
unsigned eax = 0;
unsigned ebx = 0;
unsigned ecx = 0;
unsigned edx = 0;
return __get_cpuid(1, &eax, &ebx, &ecx, &edx) != 0 && (ecx & (1u << 9u)) != 0;
#endif
}
/// whether the CPU has SSSE3, asked once: the answer is kept in an atomic
/// that is initialized at compile time, so that neither a guard of a local
/// static nor a global constructor is needed (threads that ask at the same
/// time all store the same answer)
JSON_HEDLEY_ALWAYS_INLINE bool cpu_has_ssse3() noexcept
{
static std::atomic<int> known{0}; // 0: not asked yet, 1: no, 2: yes
int state = known.load(std::memory_order_relaxed);
if (JSON_HEDLEY_UNLIKELY(state == 0))
{
state = cpu_ssse3() ? 2 : 1;
known.store(state, std::memory_order_relaxed);
}
return state == 2;
}
#endif
#if JSON_SCAN_VECTOR_UTF8
/// Tables of the UTF-8 check of J. Keiser and D. Lemire, "Validating UTF-8 In
/// Less Than One Instruction Per Byte" (2021), as in simdjson ("lookup4"): each
/// maps a nibble (high and low nibble of the previous byte, high nibble of the
/// current byte) to the errors it allows; a byte pair is ill-formed if all
/// three have an error bit in common.
template<typename Dummy = void>
struct utf8_lookup4
{
static constexpr std::uint8_t too_short = 1u << 0u, too_long = 1u << 1u, overlong_3 = 1u << 2u, too_large = 1u << 3u;
static constexpr std::uint8_t surrogate = 1u << 4u, overlong_2 = 1u << 5u, too_large_1000 = 1u << 6u, overlong_4 = 1u << 6u;
static constexpr std::uint8_t two_conts = 1u << 7u, carry = too_short | too_long | two_conts;
static const std::array<std::uint8_t, 16> byte_1_high;
static const std::array<std::uint8_t, 16> byte_1_low;
static const std::array<std::uint8_t, 16> byte_2_high;
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_high =
{
{
too_long, too_long, too_long, too_long, too_long, too_long, too_long, too_long,
two_conts, two_conts, two_conts, two_conts,
too_short | overlong_2, too_short, too_short | overlong_3 | surrogate, too_short | too_large | too_large_1000 | overlong_4
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_low =
{
{
carry | overlong_3 | overlong_2 | overlong_4, carry | overlong_2, carry, carry,
carry | too_large, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000 | surrogate, carry | too_large | too_large_1000, carry | too_large | too_large_1000
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_2_high =
{
{
too_short, too_short, too_short, too_short, too_short, too_short, too_short, too_short,
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large_1000 | overlong_4),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
too_short, too_short, too_short, too_short
}
};
/*!
@brief the run of plain string bytes and well-formed UTF-8 at p (a character
boundary), 16 bytes per step
The first quote, backslash, or control character is found with vector
compares, and the UTF-8 check of J. Keiser and D. Lemire covers the bytes up
to it. Returns true with @a block at that byte; returns false with @a block at
the start of the 16 bytes where the check found ill-formed UTF-8 or where
fewer than 16 bytes are left, for the caller to finish one sequence at a time.
Out of line, so that no constants of the check occupy registers in the
caller's loop. On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
*/
JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline bool vector_utf8_run(const unsigned char* p, const unsigned char* e, const unsigned char*& block_out) noexcept
{
using lookup = utf8_lookup4<>;
const unsigned char* block = p;
#if JSON_SCAN_NEON
const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
uint8x16_t prev = vdupq_n_u8(0);
while (e - block >= 16)
{
const uint8x16_t in = vld1q_u8(block);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))), vcltq_u8(in, vdupq_n_u8(0x20)));
const uint8x16_t prev1 = vextq_u8(prev, in, 15);
const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
const std::uint64_t special_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
const std::uint64_t err_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(err, err)), 4)), 0);
if (special_bits != 0)
{
// errors up to the special byte count (an incomplete sequence
// before a quote shows at the quote); the bytes after it do not
const unsigned k = static_cast<unsigned>(count_trailing_zeros(special_bits)) >> 2u;
const std::uint64_t upto = k == 15 ? ~std::uint64_t{0} :
(std::uint64_t{1} << (4u * (k + 1u))) - 1u;
if ((err_bits & upto) == 0)
{
block_out = block + k;
return true;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#else
// the same with SSSE3 (pshufb for the table lookups; nibbles from 16-bit
// shifts, as there are no byte shifts)
const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i nibble = _mm_set1_epi8(0x0F);
const __m128i zero = _mm_setzero_si128();
__m128i prev = zero;
while (e - block >= 16)
{
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmpeq_epi8(_mm_subs_epu8(in, _mm_set1_epi8(0x1F)), zero)); // in < 0x20
const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
_mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
_mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
_mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
const auto special_bits = static_cast<unsigned>(_mm_movemask_epi8(special));
const auto err_bits = ~static_cast<unsigned>(_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero))) & 0xFFFFu;
if (special_bits != 0)
{
const auto k = static_cast<unsigned>(count_trailing_zeros(static_cast<std::uint64_t>(special_bits)));
if ((err_bits & ((2u << k) - 1u)) == 0)
{
block_out = block + k;
return true;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#endif
block_out = block;
return false;
}
/*!
@brief vector_utf8_valid_blocks() from the first block that is not ASCII
@a block is that block, and @a first is where the check began (only ASCII up
to @a block). Returns where fewer than 16 bytes are left, or @a first if the
check found an error in any block.
From a block that is not ASCII on, eight blocks are checked without testing
for ASCII again: in text with a few non-ASCII characters (accented letters),
every other block has one, and the test would be a mispredicted branch for
most blocks. After them, ASCII blocks are skipped with one test again.
The errors of all blocks are collected and tested once at the end. A test
after each block lets the compiler advance the position with a conditional
select on its result (Apple Clang 17 does), and each block then waits for the
check of the block before: 28 cycles for 16 bytes instead of 4 on Apple M1.
*/
JSON_SCAN_SSSE3_TARGET JSON_HEDLEY_NEVER_INLINE inline const unsigned char* vector_utf8_check_blocks(const unsigned char* first, const unsigned char* block, const unsigned char* e) noexcept
{
using lookup = utf8_lookup4<>;
#if JSON_SCAN_NEON
const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
uint8x16_t prev = vdupq_n_u8(0);
uint8x16_t error = vdupq_n_u8(0);
while (e - block >= 16)
{
const uint8x16_t ahead = vld1q_u8(block);
if (vmaxvq_u8(vorrq_u8(ahead, prev)) < 0x80)
{
// ASCII here, and no sequence from the block before to finish
prev = ahead;
block += 16;
continue;
}
for (int blocks = 8; blocks != 0 && e - block >= 16; --blocks)
{
const uint8x16_t in = vld1q_u8(block);
const uint8x16_t prev1 = vextq_u8(prev, in, 15);
const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
error = vorrq_u8(error, veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc));
prev = in;
block += 16;
}
}
return vmaxvq_u8(error) != 0 ? first : block;
#else
const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i nibble = _mm_set1_epi8(0x0F);
const __m128i zero = _mm_setzero_si128();
__m128i prev = zero;
__m128i error = zero;
while (e - block >= 16)
{
const __m128i ahead = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
if (_mm_movemask_epi8(_mm_or_si128(ahead, prev)) == 0)
{
prev = ahead;
block += 16;
continue;
}
for (int blocks = 8; blocks != 0 && e - block >= 16; --blocks)
{
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
_mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
_mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
_mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
error = _mm_or_si128(error, _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc));
prev = in;
block += 16;
}
}
return _mm_movemask_epi8(_mm_cmpeq_epi8(error, zero)) != 0xFFFF ? first : block;
#endif
}
/*!
@brief skip 16-byte blocks of well-formed UTF-8 at p (a character boundary)
Like vector_utf8_run, but quotes, backslashes, and control characters are
ordinary characters. Returns where fewer than 16 bytes are left; a sequence may
be cut at that point, so the caller resumes at its start, one sequence at a
time. If the check found an error in any block, @a block itself is returned,
for the caller to find the error one sequence at a time.
ASCII blocks need one test each and none of the tables of the UTF-8 check,
which starts at the first block that is not ASCII (see
vector_utf8_check_blocks()). Out of line, like the check.
*/
JSON_HEDLEY_NEVER_INLINE inline const unsigned char* vector_utf8_valid_blocks(const unsigned char* block, const unsigned char* e) noexcept
{
const unsigned char* const first = block;
while (e - block >= 16)
{
#if JSON_SCAN_NEON
if (JSON_HEDLEY_UNLIKELY(vmaxvq_u8(vld1q_u8(block)) >= 0x80))
#else
if (JSON_HEDLEY_UNLIKELY(_mm_movemask_epi8(_mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block)))) != 0)) // NOLINT(bugprone-casting-through-void)
#endif
{
return vector_utf8_check_blocks(first, block, e);
}
block += 16;
}
return block;
}
#endif
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
Reference in new issue View Git Blame Copy Permalink