amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-11-10 06:17:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
Niels Lohmann authored and GitHub committed 2026-11-10 07:08:48 +01:00
1 parent 3836e2e5c6
commit fa272dc6c7
6 files changed
+140 -92
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/output/serializer.hpp
+20 -14
View File
@@ -834,8 +834,10 @@ class serializer
const uint8x8_t lo = vld1_u8(reinterpret_cast<const std::uint8_t*>(p));
const uint8x8_t hi = vld1_u8(reinterpret_cast<const std::uint8_t*>(p + n - 8));
const uint8x16_t in = vcombine_u8(lo, hi);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)), vceqq_u8(in, vdupq_n_u8(0x7F))));
// (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(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)));
if (vmaxvq_u8(special) != 0)
{
return false;
@@ -846,8 +848,8 @@ class serializer
const __m128i lo = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
const __m128i hi = _mm_loadl_epi64(static_cast<const __m128i*>(static_cast<const void*>(p + n - 8))); // NOLINT(bugprone-casting-through-void)
const __m128i in = _mm_unpacklo_epi64(lo, hi);
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_cmplt_epi8(in, _mm_set1_epi8(0x20)), _mm_cmpeq_epi8(in, _mm_set1_epi8(0x7F))));
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)));
if (_mm_movemask_epi8(special) != 0)
{
return false;
@@ -866,10 +868,13 @@ class serializer
#if JSON_SCAN_NEON
const uint8x16_t a = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p));
const uint8x16_t b = vld1q_u8(reinterpret_cast<const std::uint8_t*>(p + n - 16));
const uint8x16_t special = vorrq_u8(vorrq_u8(vorrq_u8(vceqq_u8(a, vdupq_n_u8('"')), vceqq_u8(a, vdupq_n_u8('\\'))),
vorrq_u8(vceqq_u8(b, vdupq_n_u8('"')), vceqq_u8(b, vdupq_n_u8('\\')))),
vorrq_u8(vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(a), vdupq_n_s8(0x20)), vcltq_s8(vreinterpretq_s8_u8(b), vdupq_n_s8(0x20))),
vorrq_u8(vceqq_u8(a, vdupq_n_u8(0x7F)), vceqq_u8(b, vdupq_n_u8(0x7F)))));
// (int8_t)(c ^ 2) < 33: the quote, the control characters and the
// non-ASCII bytes (see vector_plain_run())
const uint8x16_t flip = vdupq_n_u8(2);
const int8x16_t limit = vdupq_n_s8(33);
const uint8x16_t special = vorrq_u8(vorrq_u8(vorrq_u8(vceqq_u8(a, vdupq_n_u8('\\')), vceqq_u8(b, vdupq_n_u8('\\'))),
vorrq_u8(vceqq_u8(a, vdupq_n_u8(0x7F)), vceqq_u8(b, vdupq_n_u8(0x7F)))),
vorrq_u8(vcltq_s8(vreinterpretq_s8_u8(veorq_u8(a, flip)), limit), vcltq_s8(vreinterpretq_s8_u8(veorq_u8(b, flip)), limit)));
if (vmaxvq_u8(special) != 0)
{
return false;
@@ -879,14 +884,15 @@ class serializer
#else
const __m128i a = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
const __m128i b = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p + n - 16))); // NOLINT(bugprone-casting-through-void)
const __m128i quote = _mm_set1_epi8('"');
// (int8_t)(c ^ 2) < 33: the quote, the control characters and the
// non-ASCII bytes (see vector_plain_run())
const __m128i backslash = _mm_set1_epi8('\\');
const __m128i space = _mm_set1_epi8(0x20);
const __m128i del = _mm_set1_epi8(0x7F);
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(a, quote), _mm_cmpeq_epi8(a, backslash)),
_mm_or_si128(_mm_cmpeq_epi8(b, quote), _mm_cmpeq_epi8(b, backslash))),
_mm_or_si128(_mm_or_si128(_mm_cmplt_epi8(a, space), _mm_cmplt_epi8(b, space)),
_mm_or_si128(_mm_cmpeq_epi8(a, del), _mm_cmpeq_epi8(b, del))));
const __m128i flip = _mm_set1_epi8(2);
const __m128i limit = _mm_set1_epi8(33);
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(a, backslash), _mm_cmpeq_epi8(b, backslash)),
_mm_or_si128(_mm_cmpeq_epi8(a, del), _mm_cmpeq_epi8(b, del))),
_mm_or_si128(_mm_cmplt_epi8(_mm_xor_si128(a, flip), limit), _mm_cmplt_epi8(_mm_xor_si128(b, flip), limit)));
if (_mm_movemask_epi8(special) != 0)
{
return false;