mirror of
https://github.com/scylladb/scylladb.git
synced 2026-04-21 17:10:35 +00:00
422987ab04
Validate ascii string by ORing all bytes and check if 7-th bit is 0. Compared with original std::any_of(), which checks ascii string byte by byte, this new approach validates input in 8 bytes and two independent streams. Performance is much higher for normal cases, though slightly slower when string is very short. See table below. Speed(MB/s) of ascii string validation +---------------+-------------+---------+ | String length | std::any_of | u64 x 2 | +---------------+-------------+---------+ | 9 bytes | 1691 | 1635 | +---------------+-------------+---------+ | 31 bytes | 2923 | 3181 | +---------------+-------------+---------+ | 129 bytes | 3377 | 15110 | +---------------+-------------+---------+ | 1039 bytes | 3357 | 31815 | +---------------+-------------+---------+ | 16385 bytes | 3448 | 47983 | +---------------+-------------+---------+ | 1048576 bytes | 3394 | 31391 | +---------------+-------------+---------+ Signed-off-by: Yibo Cai <yibo.cai@arm.com> Message-Id: <1544669646-31881-1-git-send-email-yibo.cai@arm.com>
65 lines
1.7 KiB
C++
65 lines
1.7 KiB
C++
/*
|
|
* Fast ASCII string validataion.
|
|
*
|
|
* Copyright (c) 2018, Arm Limited.
|
|
*/
|
|
|
|
/*
|
|
* This file is part of Scylla.
|
|
*
|
|
* Scylla is free software: you can redistribute it and/or modify
|
|
* it under the terms of the GNU Affero General Public License as published by
|
|
* the Free Software Foundation, either version 3 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* Scylla is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#include "ascii.hh"
|
|
#include <seastar/core/byteorder.hh>
|
|
|
|
namespace utils {
|
|
|
|
namespace ascii {
|
|
|
|
bool validate(const uint8_t *data, size_t len) {
|
|
// OR all bytes
|
|
uint8_t orall = 0;
|
|
|
|
// Fast OR by 8-bytes and two independent streams
|
|
if (len >= 16) {
|
|
uint64_t or1 = 0, or2 = 0;
|
|
|
|
do {
|
|
or1 |= seastar::read_le<uint64_t>((const char *)data);
|
|
or2 |= seastar::read_le<uint64_t>((const char *)data+8);
|
|
|
|
data += 16;
|
|
len -= 16;
|
|
} while (len >= 16);
|
|
|
|
// Idea from Benny Halevy <bhalevy@scylladb.com>
|
|
// - 7-th bit set ==> orall = !(non-zero) - 1 = 0 - 1 = 0xFF
|
|
// - 7-th bit clear ==> orall = !0 - 1 = 1 - 1 = 0x00
|
|
orall = !((or1 | or2) & 0x8080808080808080ULL) - 1;
|
|
}
|
|
|
|
// OR remaining bytes
|
|
while (len--) {
|
|
orall |= *data++;
|
|
}
|
|
|
|
// 7-th bit should be 0
|
|
return orall < 0x80;
|
|
}
|
|
|
|
} // namespace ascii
|
|
|
|
} // namespace utils
|