wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-11-11 16:40:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

SWAR and vector scans: test for special bytes in fewer operations (#6033)

Browse Source 
* SWAR: test for special bytes in the reduced form

The usual test for a zero byte, (x - ones) & ~x & high, needs `& ~x` only
to keep bytes from 0x80 out. The tests for quotes, backslashes and control
characters in string_scan.hpp and the serializer also flag every byte from
0x80 with `v & high`, so the `& ~x` terms can be dropped. Clang finds this
reduction itself; GCC does not and emits 24 instead of 16 instructions.

The masks are the same for 1.3 billion random words and for every pair of
adjacent byte values. With GCC 15 on x86-64: accept() -2 to -4 %,
sax_parse() -2 %, dump() -3 %. Clang is unchanged.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Vector scans: one compare for the quote and the control characters

The SSE2/NEON tests for the bytes a string run stops at compared with the
quote, with the backslash and with 0x20 separately. Flipping bit 1 maps
0x00-0x1F onto itself and the quote onto 0x20, and every other ASCII byte
to 33 or more, so (c ^ 2) < 33 finds the quote and the control characters
with one compare: signed where the bytes from 0x80 stop the run too,
unsigned (or with a saturating subtraction / minimum on SSE2) where they
do not. This saves one vector operation per 16 bytes in all twelve vector
tests: the lexer's vector_plain_run() and vector_utf8_run(), dump()'s
copy_plain_halves() and copy_plain_vectors(), and json_view's scanner and
serializer. The DEL tests of the ensure_ascii paths stay.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Tests: sweep_allocator::construct() accepts pointers to const

Recent libc++ (emsdk latest) probes construct(const T*, const T&) in an
unevaluated context while checking for trivial copies; the static_cast to
void* in the noexcept specification then fails to compile.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N5NasEsrzHhSNouxSoEwqz
(cherry picked from commit 794bf70823c12a2a1cb2a8a95f34dfb6357746a8)
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Tests: guard sweep_allocator::construct() against const types instead of const_cast

The const_cast added in the previous commit is rejected by
cppcoreguidelines-pro-type-const-cast (clang-tidy). Make construct() not
viable for const U instead, which is what libc++ probes for.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N5NasEsrzHhSNouxSoEwqz
(cherry picked from commit de099fa607001b710862fd1bbecef3609c54cbc4)
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

* Fix CI: astyle and clang-tidy for sweep_allocator::construct()

astyle 3.4.13 reformats the enable_if<!...> default template argument
(Check amalgamation). Delete the const overload instead, which makes the
libc++ probe for const objects fail in the SFINAE context just the same
and needs no <type_traits>.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N5NasEsrzHhSNouxSoEwqz
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

---------

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
Niels LohmannandClaude Sonnet 5.5 authored and GitHub committed 2026-11-10 22:30:28 +01:00
1 parent 8c0b48088c
commit 2a4aec3e69
7 files changed
+156 -120
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

single_include/nlohmann/json_view.hpp
Generated
+34 -23
View File
@@ -759,8 +759,10 @@ namespace view
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.
the two apart). One signed compare finds the quote, the control characters and
the non-ASCII bytes at once: these are exactly the bytes with
(int8_t)(c ^ 2) < 33 (see detail::vector_plain_run()). The backslash needs its
own compare.
*/
NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
{
@@ -768,8 +770,8 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned
{
#if NLOHMANN_VIEW_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)));
const uint8x16_t special = vorrq_u8(vceqq_u8(in, vdupq_n_u8('\\')),
vcltq_s8(vreinterpretq_s8_u8(veorq_u8(in, vdupq_n_u8(2))), vdupq_n_s8(33)));
// 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);
@@ -779,8 +781,8 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned
}
#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 __m128i special = _mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('\\')),
_mm_cmplt_epi8(_mm_xor_si128(in, _mm_set1_epi8(2)), _mm_set1_epi8(33)));
const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
if (bits != 0)
{
@@ -806,15 +808,17 @@ NLOHMANN_VIEW_ALWAYS_INLINE unsigned copy_plain_run16(const unsigned char* p, ch
#if NLOHMANN_VIEW_NEON
const uint8x16_t in = vld1q_u8(p);
vst1q_u8(reinterpret_cast<std::uint8_t*>(w), in); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
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)));
// (int8_t)(c ^ 2) < 33: the quote, the control characters and the
// non-ASCII bytes (see vector_plain_run())
const uint8x16_t special = vorrq_u8(vceqq_u8(in, vdupq_n_u8('\\')),
vcltq_s8(vreinterpretq_s8_u8(veorq_u8(in, vdupq_n_u8(2))), vdupq_n_s8(33)));
const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits) >> 2u) : 16u;
#else
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
_mm_storeu_si128(static_cast<__m128i*>(static_cast<void*>(w)), in); // 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 __m128i special = _mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('\\')),
_mm_cmplt_epi8(_mm_xor_si128(in, _mm_set1_epi8(2)), _mm_set1_epi8(33)));
const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
return bits != 0 ? static_cast<unsigned>(count_trailing_zeros(bits)) : 16u;
#endif
@@ -974,7 +978,8 @@ NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE NLOHMANN_VIEW_NOCLONE inline c
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)));
// the quote and the control characters: (c ^ 2) < 33 (see vector_plain_run())
const uint8x16_t special = vorrq_u8(vceqq_u8(in, vdupq_n_u8('\\')), vcltq_u8(veorq_u8(in, vdupq_n_u8(2)), vdupq_n_u8(33)));
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)));
@@ -1013,8 +1018,10 @@ NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE NLOHMANN_VIEW_NOCLONE inline c
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
// the quote and the control characters: (c ^ 2) < 33, that is,
// (c ^ 2) - 32 saturates to 0 (see vector_plain_run())
const __m128i special = _mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('\\')),
_mm_cmpeq_epi8(_mm_subs_epu8(_mm_xor_si128(in, _mm_set1_epi8(2)), _mm_set1_epi8(32)), zero));
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))),
@@ -8600,9 +8607,12 @@ inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexc
for (; i + 16 <= n; i += 16)
{
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(s + i))); // NOLINT(bugprone-casting-through-void)
// (a byte is below 0x20 if it is its own minimum with 0x1F)
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_min_epu8(in, _mm_set1_epi8(0x1F)), in));
// the quote and the control characters are the bytes with
// (c ^ 2) <= 32, that is, those that are their own minimum with 32
// (see vector_plain_run())
const __m128i flipped = _mm_xor_si128(in, _mm_set1_epi8(2));
const __m128i special = _mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('\\')),
_mm_cmpeq_epi8(_mm_min_epu8(flipped, _mm_set1_epi8(32)), flipped));
const auto mask = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
if (mask != 0)
{
@@ -8665,20 +8675,21 @@ inline bool is_ascii_without_delete(const char* s, std::size_t n) noexcept
#if NLOHMANN_VIEW_VECTOR
/// the bytes of the 16 at p that ensure_ascii cannot copy (a quote, a
/// backslash, a control character, DEL, or not ASCII; a signed compare with
/// 0x20 finds control characters and non-ASCII bytes at once), one bit per
/// byte (x86) or one nibble per byte (NEON)
/// backslash, a control character, DEL, or not ASCII; the signed compare
/// (int8_t)(c ^ 2) < 33 finds the quote, the control characters and the
/// non-ASCII bytes at once, see vector_plain_run()), one bit per byte (x86) or
/// one nibble per byte (NEON)
NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t ascii_stop_mask(const unsigned char* p) noexcept
{
#if NLOHMANN_VIEW_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('\\'))),
vorrq_u8(vceqq_u8(in, vdupq_n_u8(0x7F)), vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20))));
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('\\')), vceqq_u8(in, vdupq_n_u8(0x7F))),
vcltq_s8(vreinterpretq_s8_u8(veorq_u8(in, vdupq_n_u8(2))), vdupq_n_s8(33)));
return vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
#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_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F)), _mm_cmplt_epi8(in, _mm_set1_epi8(0x20))));
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('\\')), _mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F))),
_mm_cmplt_epi8(_mm_xor_si128(in, _mm_set1_epi8(2)), _mm_set1_epi8(33)));
return static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
#endif
}