mirror of
https://github.com/scylladb/scylladb.git
synced 2026-06-02 21:17:01 +00:00
9d8507de09
"
zlib's crc32_combine() is not very efficient. It is faster to re-combine
the buffer using crc32(). It's still substantial amount of work which
could be avoided.
This patch introduces a fast implementation of crc32_combine() which
uses a different algorithm than zlib. It also utilizes intrinsics for
carry-less multiplication instruction to perform the computation faster.
The details of the algorithm can be found in code comments.
Performance results using perf_checksum and second buffer of length 64 KiB:
zlib CRC32 combine: 38'851 ns
libdeflate CRC32: 4'797 ns
fast_crc32_combine(): 11 ns
So the new implementation is 3500x faster than zlib's, and 417x faster than
re-checksumming the buffer using libdeflate.
Tested on i7-5960X CPU @ 3.00GHz
Performance was also evaluated using sstable writer benchmark:
perf_fast_forward --populate --sstable-format=mc --data-directory /tmp/perf-mc \
--value-size=10000 --rows 1000000 --datasets small-part
It yielded 9% improvement in median frag/s (129'055 vs 117'977).
Refs #3874
"
* tag 'fast-crc32-combine-v2' of github.com:tgrabiec/scylla:
tests: perf_checksum: Test fast_crc32_combine()
tests: Rename libdeflate_test to checksum_utils_test
tests: libdeflate: Add more tests for checksum_combine()
tests: libdeflate: Check both libdeflate and default checksummers
sstables: Use fast_crc_combine() in the default checksummer
utils/gz: Add fast implementation of crc32_combine()
utils/gz: Add pre-computed polynomials
utils/gz: Import Barett reduction implementation from libdeflate
utils: Extract clmul() from crc.hh
(cherry picked from commit b098b5b987)
61 lines
1.4 KiB
C++
61 lines
1.4 KiB
C++
/*
|
|
* Copyright (C) 2018 ScyllaDB
|
|
*/
|
|
|
|
/*
|
|
* 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/>.
|
|
*
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <cstdint>
|
|
|
|
#if defined(__x86_64__) || defined(__i386__)
|
|
|
|
#include <wmmintrin.h>
|
|
#include <smmintrin.h>
|
|
|
|
// Performs a carry-less multiplication of two integers.
|
|
inline
|
|
uint64_t clmul_u32(uint32_t p1, uint32_t p2) {
|
|
__m128i p = _mm_set_epi64x(p1, p2);
|
|
p = _mm_clmulepi64_si128(p, p, 0x01);
|
|
return _mm_extract_epi64(p, 0);
|
|
}
|
|
|
|
inline
|
|
uint64_t clmul(uint32_t p1, uint32_t p2) {
|
|
return clmul_u32(p1, p2);
|
|
}
|
|
|
|
#elif defined(__aarch64__)
|
|
|
|
#include <arm_neon.h>
|
|
|
|
// Performs a carry-less multiplication of two integers.
|
|
inline
|
|
uint64_t clmul_u32(uint32_t p1, uint32_t p2) {
|
|
return vmull_p64(p1, p2);
|
|
}
|
|
|
|
inline
|
|
uint64_t clmul(uint32_t p1, uint32_t p2) {
|
|
return clmul_u32(p1, p2);
|
|
}
|
|
|
|
#endif
|