2024-01-02 02:12:26 +08:00
|
|
|
/* Copyright (c) 1997-2024 Free Software Foundation, Inc.
|
2017-11-23 21:08:11 +08:00
|
|
|
This file is part of the GNU C Library.
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
The GNU C Library 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
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
|
|
License along with the GNU C Library; if not, see
|
Prefer https to http for gnu.org and fsf.org URLs
Also, change sources.redhat.com to sourceware.org.
This patch was automatically generated by running the following shell
script, which uses GNU sed, and which avoids modifying files imported
from upstream:
sed -ri '
s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g
s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g
' \
$(find $(git ls-files) -prune -type f \
! -name '*.po' \
! -name 'ChangeLog*' \
! -path COPYING ! -path COPYING.LIB \
! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \
! -path manual/texinfo.tex ! -path scripts/config.guess \
! -path scripts/config.sub ! -path scripts/install-sh \
! -path scripts/mkinstalldirs ! -path scripts/move-if-change \
! -path INSTALL ! -path locale/programs/charmap-kw.h \
! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \
! '(' -name configure \
-execdir test -f configure.ac -o -f configure.in ';' ')' \
! '(' -name preconfigure \
-execdir test -f preconfigure.ac ';' ')' \
-print)
and then by running 'make dist-prepare' to regenerate files built
from the altered files, and then executing the following to cleanup:
chmod a+x sysdeps/unix/sysv/linux/riscv/configure
# Omit irrelevant whitespace and comment-only changes,
# perhaps from a slightly-different Autoconf version.
git checkout -f \
sysdeps/csky/configure \
sysdeps/hppa/configure \
sysdeps/riscv/configure \
sysdeps/unix/sysv/linux/csky/configure
# Omit changes that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines
git checkout -f \
sysdeps/powerpc/powerpc64/ppc-mcount.S \
sysdeps/unix/sysv/linux/s390/s390-64/syscall.S
# Omit change that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline
git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 13:40:42 +08:00
|
|
|
<https://www.gnu.org/licenses/>. */
|
2017-11-23 21:08:11 +08:00
|
|
|
|
|
|
|
#include <nss.h>
|
|
|
|
|
|
|
|
/* This is from libc/db/hash/hash_func.c, hash3 is static there */
|
|
|
|
/*
|
nss: Optimize nss_hash in nss_hash.c
The prior unrolling didn't really do much as it left the dependency
chain between iterations. Unrolled the loop for 4 so 4x multiplies
could be pipelined in out-of-order machines.
Results for __nss_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=25 runs
Geometric of all benchmark New / Old: 0.845
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 4.019, 3.729, 1.078
fixed, 1, 4.95, 5.707, 0.867
fixed, 2, 5.152, 5.657, 0.911
fixed, 3, 4.641, 5.721, 0.811
fixed, 4, 5.551, 5.81, 0.955
fixed, 5, 6.525, 6.552, 0.996
fixed, 6, 6.711, 6.561, 1.023
fixed, 7, 6.715, 6.767, 0.992
fixed, 8, 7.874, 7.915, 0.995
fixed, 9, 8.888, 9.767, 0.91
fixed, 10, 8.959, 9.762, 0.918
fixed, 11, 9.188, 9.987, 0.92
fixed, 12, 9.708, 10.618, 0.914
fixed, 13, 10.393, 11.14, 0.933
fixed, 14, 10.628, 12.097, 0.879
fixed, 15, 10.982, 12.965, 0.847
fixed, 16, 11.851, 14.429, 0.821
fixed, 32, 24.334, 34.414, 0.707
fixed, 64, 55.618, 86.688, 0.642
fixed, 128, 118.261, 224.36, 0.527
fixed, 256, 256.183, 538.629, 0.476
random, 2, 11.194, 11.556, 0.969
random, 4, 17.516, 17.205, 1.018
random, 8, 23.501, 20.985, 1.12
random, 16, 28.131, 29.212, 0.963
random, 32, 35.436, 38.662, 0.917
random, 64, 45.74, 58.868, 0.777
random, 128, 75.394, 121.963, 0.618
random, 256, 139.524, 260.726, 0.535
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
2022-05-20 06:18:02 +08:00
|
|
|
* This is INCREDIBLY ugly, but fast. We break the string up into 4 byte
|
2017-11-23 21:08:11 +08:00
|
|
|
* units. On the first time through the loop we get the "leftover bytes"
|
nss: Optimize nss_hash in nss_hash.c
The prior unrolling didn't really do much as it left the dependency
chain between iterations. Unrolled the loop for 4 so 4x multiplies
could be pipelined in out-of-order machines.
Results for __nss_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=25 runs
Geometric of all benchmark New / Old: 0.845
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 4.019, 3.729, 1.078
fixed, 1, 4.95, 5.707, 0.867
fixed, 2, 5.152, 5.657, 0.911
fixed, 3, 4.641, 5.721, 0.811
fixed, 4, 5.551, 5.81, 0.955
fixed, 5, 6.525, 6.552, 0.996
fixed, 6, 6.711, 6.561, 1.023
fixed, 7, 6.715, 6.767, 0.992
fixed, 8, 7.874, 7.915, 0.995
fixed, 9, 8.888, 9.767, 0.91
fixed, 10, 8.959, 9.762, 0.918
fixed, 11, 9.188, 9.987, 0.92
fixed, 12, 9.708, 10.618, 0.914
fixed, 13, 10.393, 11.14, 0.933
fixed, 14, 10.628, 12.097, 0.879
fixed, 15, 10.982, 12.965, 0.847
fixed, 16, 11.851, 14.429, 0.821
fixed, 32, 24.334, 34.414, 0.707
fixed, 64, 55.618, 86.688, 0.642
fixed, 128, 118.261, 224.36, 0.527
fixed, 256, 256.183, 538.629, 0.476
random, 2, 11.194, 11.556, 0.969
random, 4, 17.516, 17.205, 1.018
random, 8, 23.501, 20.985, 1.12
random, 16, 28.131, 29.212, 0.963
random, 32, 35.436, 38.662, 0.917
random, 64, 45.74, 58.868, 0.777
random, 128, 75.394, 121.963, 0.618
random, 256, 139.524, 260.726, 0.535
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
2022-05-20 06:18:02 +08:00
|
|
|
* (len % 4). On every other iteration, we perform a 4x unrolled version
|
|
|
|
* HASHC. Further unrolling does not appear to help.
|
2017-11-23 21:08:11 +08:00
|
|
|
*
|
|
|
|
* OZ's original sdbm hash
|
|
|
|
*/
|
|
|
|
uint32_t
|
|
|
|
__nss_hash (const void *keyarg, size_t len)
|
|
|
|
{
|
nss: Optimize nss_hash in nss_hash.c
The prior unrolling didn't really do much as it left the dependency
chain between iterations. Unrolled the loop for 4 so 4x multiplies
could be pipelined in out-of-order machines.
Results for __nss_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=25 runs
Geometric of all benchmark New / Old: 0.845
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 4.019, 3.729, 1.078
fixed, 1, 4.95, 5.707, 0.867
fixed, 2, 5.152, 5.657, 0.911
fixed, 3, 4.641, 5.721, 0.811
fixed, 4, 5.551, 5.81, 0.955
fixed, 5, 6.525, 6.552, 0.996
fixed, 6, 6.711, 6.561, 1.023
fixed, 7, 6.715, 6.767, 0.992
fixed, 8, 7.874, 7.915, 0.995
fixed, 9, 8.888, 9.767, 0.91
fixed, 10, 8.959, 9.762, 0.918
fixed, 11, 9.188, 9.987, 0.92
fixed, 12, 9.708, 10.618, 0.914
fixed, 13, 10.393, 11.14, 0.933
fixed, 14, 10.628, 12.097, 0.879
fixed, 15, 10.982, 12.965, 0.847
fixed, 16, 11.851, 14.429, 0.821
fixed, 32, 24.334, 34.414, 0.707
fixed, 64, 55.618, 86.688, 0.642
fixed, 128, 118.261, 224.36, 0.527
fixed, 256, 256.183, 538.629, 0.476
random, 2, 11.194, 11.556, 0.969
random, 4, 17.516, 17.205, 1.018
random, 8, 23.501, 20.985, 1.12
random, 16, 28.131, 29.212, 0.963
random, 32, 35.436, 38.662, 0.917
random, 64, 45.74, 58.868, 0.777
random, 128, 75.394, 121.963, 0.618
random, 256, 139.524, 260.726, 0.535
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
2022-05-20 06:18:02 +08:00
|
|
|
enum
|
|
|
|
{
|
|
|
|
HASH_CONST_P0 = 1, /* (uint32_t)(65599 ^ 0). */
|
|
|
|
HASH_CONST_P1 = 65599, /* (uint32_t)(65599 ^ 1). */
|
|
|
|
HASH_CONST_P2 = 8261505, /* (uint32_t)(65599 ^ 2). */
|
|
|
|
HASH_CONST_P3 = 780587199, /* (uint32_t)(65599 ^ 3). */
|
|
|
|
HASH_CONST_P4 = 1139564289 /* (uint32_t)(65599 ^ 4). */
|
|
|
|
};
|
|
|
|
|
2017-11-23 21:08:11 +08:00
|
|
|
const unsigned char *key;
|
|
|
|
uint32_t h;
|
|
|
|
|
nss: Optimize nss_hash in nss_hash.c
The prior unrolling didn't really do much as it left the dependency
chain between iterations. Unrolled the loop for 4 so 4x multiplies
could be pipelined in out-of-order machines.
Results for __nss_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=25 runs
Geometric of all benchmark New / Old: 0.845
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 4.019, 3.729, 1.078
fixed, 1, 4.95, 5.707, 0.867
fixed, 2, 5.152, 5.657, 0.911
fixed, 3, 4.641, 5.721, 0.811
fixed, 4, 5.551, 5.81, 0.955
fixed, 5, 6.525, 6.552, 0.996
fixed, 6, 6.711, 6.561, 1.023
fixed, 7, 6.715, 6.767, 0.992
fixed, 8, 7.874, 7.915, 0.995
fixed, 9, 8.888, 9.767, 0.91
fixed, 10, 8.959, 9.762, 0.918
fixed, 11, 9.188, 9.987, 0.92
fixed, 12, 9.708, 10.618, 0.914
fixed, 13, 10.393, 11.14, 0.933
fixed, 14, 10.628, 12.097, 0.879
fixed, 15, 10.982, 12.965, 0.847
fixed, 16, 11.851, 14.429, 0.821
fixed, 32, 24.334, 34.414, 0.707
fixed, 64, 55.618, 86.688, 0.642
fixed, 128, 118.261, 224.36, 0.527
fixed, 256, 256.183, 538.629, 0.476
random, 2, 11.194, 11.556, 0.969
random, 4, 17.516, 17.205, 1.018
random, 8, 23.501, 20.985, 1.12
random, 16, 28.131, 29.212, 0.963
random, 32, 35.436, 38.662, 0.917
random, 64, 45.74, 58.868, 0.777
random, 128, 75.394, 121.963, 0.618
random, 256, 139.524, 260.726, 0.535
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
2022-05-20 06:18:02 +08:00
|
|
|
#define HASHC h = *key++ + HASH_CONST_P1 * h
|
2017-11-23 21:08:11 +08:00
|
|
|
|
|
|
|
h = 0;
|
|
|
|
key = keyarg;
|
|
|
|
if (len > 0)
|
|
|
|
{
|
nss: Optimize nss_hash in nss_hash.c
The prior unrolling didn't really do much as it left the dependency
chain between iterations. Unrolled the loop for 4 so 4x multiplies
could be pipelined in out-of-order machines.
Results for __nss_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=25 runs
Geometric of all benchmark New / Old: 0.845
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 4.019, 3.729, 1.078
fixed, 1, 4.95, 5.707, 0.867
fixed, 2, 5.152, 5.657, 0.911
fixed, 3, 4.641, 5.721, 0.811
fixed, 4, 5.551, 5.81, 0.955
fixed, 5, 6.525, 6.552, 0.996
fixed, 6, 6.711, 6.561, 1.023
fixed, 7, 6.715, 6.767, 0.992
fixed, 8, 7.874, 7.915, 0.995
fixed, 9, 8.888, 9.767, 0.91
fixed, 10, 8.959, 9.762, 0.918
fixed, 11, 9.188, 9.987, 0.92
fixed, 12, 9.708, 10.618, 0.914
fixed, 13, 10.393, 11.14, 0.933
fixed, 14, 10.628, 12.097, 0.879
fixed, 15, 10.982, 12.965, 0.847
fixed, 16, 11.851, 14.429, 0.821
fixed, 32, 24.334, 34.414, 0.707
fixed, 64, 55.618, 86.688, 0.642
fixed, 128, 118.261, 224.36, 0.527
fixed, 256, 256.183, 538.629, 0.476
random, 2, 11.194, 11.556, 0.969
random, 4, 17.516, 17.205, 1.018
random, 8, 23.501, 20.985, 1.12
random, 16, 28.131, 29.212, 0.963
random, 32, 35.436, 38.662, 0.917
random, 64, 45.74, 58.868, 0.777
random, 128, 75.394, 121.963, 0.618
random, 256, 139.524, 260.726, 0.535
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
2022-05-20 06:18:02 +08:00
|
|
|
switch ((len & (4 - 1)))
|
|
|
|
{
|
|
|
|
case 0:
|
|
|
|
/* h starts out as zero so no need to include the multiply. */
|
|
|
|
h = *key++;
|
|
|
|
/* FALLTHROUGH */
|
|
|
|
case 3:
|
|
|
|
HASHC;
|
|
|
|
/* FALLTHROUGH */
|
|
|
|
case 2:
|
|
|
|
HASHC;
|
|
|
|
/* FALLTHROUGH */
|
|
|
|
case 1:
|
|
|
|
HASHC;
|
|
|
|
/* FALLTHROUGH */
|
|
|
|
}
|
|
|
|
|
|
|
|
uint32_t c0, c1, c2, c3;
|
|
|
|
for (--len; len >= 4; len -= 4)
|
|
|
|
{
|
|
|
|
c0 = (unsigned char) *(key + 0);
|
|
|
|
c1 = (unsigned char) *(key + 1);
|
|
|
|
c2 = (unsigned char) *(key + 2);
|
|
|
|
c3 = (unsigned char) *(key + 3);
|
|
|
|
h = HASH_CONST_P4 * h + HASH_CONST_P3 * c0 + HASH_CONST_P2 * c1
|
|
|
|
+ HASH_CONST_P1 * c2 + HASH_CONST_P0 * c3;
|
|
|
|
|
|
|
|
key += 4;
|
|
|
|
}
|
2017-11-23 21:08:11 +08:00
|
|
|
}
|
|
|
|
return h;
|
|
|
|
}
|
|
|
|
|
2022-05-20 06:18:00 +08:00
|
|
|
|
2017-11-23 21:08:11 +08:00
|
|
|
libc_hidden_def (__nss_hash)
|