thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-22 07:31:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Further improvement

Browse Source
This commit is contained in:
Alexey Milovidov 2020-05-31 22:47:39 +03:00
parent 463d2cf836
commit ad14025b5e
1 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/Common/UTF8Helpers.cpp
View File

@ -97,6 +97,35 @@ size_t computeWidth(const UInt8 * data, size_t size, size_t prefix) noexcept
for (size_t i = 0; i < size; ++i)
{
/// Quickly skip regular ASCII
#if defined(__SSE2__)
const auto lower_bound = _mm_set1_epi8(32);
const auto upper_bound = _mm_set1_epi8(126);
while (i + 15 < size)
{
__m128i bytes = _mm_loadu_si128(reinterpret_cast<const __m128i *>(&data[i]));
const uint16_t non_regular_width_mask = _mm_movemask_epi8(
_mm_or_si128(
_mm_cmplt_epi8(bytes, lower_bound),
_mm_cmpgt_epi8(bytes, upper_bound)));
if (non_regular_width_mask)
{
auto num_regular_chars = __builtin_ctz(non_regular_width_mask);
width += num_regular_chars;
i += num_regular_chars;
break;
}
else
{
i += 16;
width += 16;
}
}
#endif
while (i < size && isPrintableASCII(data[i]))
{
++width;