mirror of
https://github.com/nlohmann/json.git
synced 2026-10-22 14:08:13 +00:00
Copy the short runs between escapes as a block of 16 bytes
The characters between two escapes (a quote, a backslash, a control character) are copied to the write buffer by memcpy with a length known only at run time. For a run of up to 16 characters that has 16 or more bytes in the string behind its start and in the buffer behind its end, a copy of a fixed block of 16 bytes does the same without the call; the surplus bytes in the buffer are overwritten by what follows. Apple M1, Apple clang, retired instructions per dump(), on top of the previous changes: JSON in JSON 8.32M -> 7.52M (-10 %) paths 8.17M -> 7.49M (-8 %) log lines 7.49M -> 7.14M (-5 %) cjk, emoji text (no escapes): +-1 % Linux x86-64 (callgrind), gcc 13 / clang 18: JSON in JSON -11 % / -10 %, paths -7 % / -6 %, log lines -5 % / -4 %. The branch is marked unlikely: text without escapes (CJK, accented Latin) has few short runs, and without the hint it paid up to 5 % for the check. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
2 files changed
+46
-2
No files matched your search
@@ -1038,7 +1038,7 @@ class serializer
|
||||
put_buffer(string_buffer, bytes);
|
||||
bytes = 0;
|
||||
}
|
||||
put_string(s, i, i + run);
|
||||
put_run(s, i, run);
|
||||
bytes_after_last_accept = 0;
|
||||
undumped_chars = 0;
|
||||
i += run;
|
||||
@@ -1474,6 +1474,28 @@ class serializer
|
||||
write_buffer_pos += length;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief append the characters of @a str in [@a start, @a start + @a length)
|
||||
|
||||
A run of up to 16 characters with 16 or more in the string from @a start on
|
||||
and in the write buffer from its end on is copied as a whole block of 16,
|
||||
which spares the call of memcpy with a length known only at run time; the
|
||||
surplus characters in the buffer are overwritten by what follows.
|
||||
*/
|
||||
template<typename StringType>
|
||||
void put_run(const StringType& str, const std::size_t start, const std::size_t length)
|
||||
{
|
||||
// a short run is the exception in text without escapes (CJK, accented
|
||||
// Latin), for which this keeps the long path the fast one
|
||||
if (JSON_HEDLEY_UNLIKELY(length <= 16 && start + 16 <= str.size() && write_buffer_pos + 16 <= write_buffer.size()))
|
||||
{
|
||||
std::memcpy(write_buffer.data() + write_buffer_pos, str.data() + start, 16);
|
||||
write_buffer_pos += length;
|
||||
return;
|
||||
}
|
||||
put_string(str, start, start + length);
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief append the characters of @a str in [@a start, @a end)
|
||||
|
||||
|
||||
Reference in new issue
Block a user