diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-05-19 17:18:03 -0500 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-05-23 10:38:40 -0500 |
| commit | 9a421348cd7d0704663e26e6171828bed6e0a2cf (patch) | |
| tree | 8bdbf5e9d77420298f1795467dda50ed4e39afb0 /elf | |
| parent | 3d155d4b6c29ddfd0b3318fa58dbf8ef20e7bca0 (diff) | |
| download | glibc-9a421348cd7d0704663e26e6171828bed6e0a2cf.tar glibc-9a421348cd7d0704663e26e6171828bed6e0a2cf.tar.gz glibc-9a421348cd7d0704663e26e6171828bed6e0a2cf.tar.bz2 glibc-9a421348cd7d0704663e26e6171828bed6e0a2cf.zip | |
elf: Optimize _dl_new_hash in dl-new-hash.h
Unroll slightly and enforce good instruction scheduling. This improves
performance on out-of-order machines. The unrolling allows for
pipelined multiplies.
As well, as an optional sysdep, reorder the operations and prevent
reassosiation for better scheduling and higher ILP. This commit
only adds the barrier for x86, although it should be either no
change or a win for any architecture.
Unrolling further started to induce slowdowns for sizes [0, 4]
but can help the loop so if larger sizes are the target further
unrolling can be beneficial.
Results for _dl_new_hash
Benchmarked on Tigerlake: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
Time as Geometric Mean of N=30 runs
Geometric of all benchmark New / Old: 0.674
type, length, New Time, Old Time, New Time / Old Time
fixed, 0, 2.865, 2.72, 1.053
fixed, 1, 3.567, 2.489, 1.433
fixed, 2, 2.577, 3.649, 0.706
fixed, 3, 3.644, 5.983, 0.609
fixed, 4, 4.211, 6.833, 0.616
fixed, 5, 4.741, 9.372, 0.506
fixed, 6, 5.415, 9.561, 0.566
fixed, 7, 6.649, 10.789, 0.616
fixed, 8, 8.081, 11.808, 0.684
fixed, 9, 8.427, 12.935, 0.651
fixed, 10, 8.673, 14.134, 0.614
fixed, 11, 10.69, 15.408, 0.694
fixed, 12, 10.789, 16.982, 0.635
fixed, 13, 12.169, 18.411, 0.661
fixed, 14, 12.659, 19.914, 0.636
fixed, 15, 13.526, 21.541, 0.628
fixed, 16, 14.211, 23.088, 0.616
fixed, 32, 29.412, 52.722, 0.558
fixed, 64, 65.41, 142.351, 0.459
fixed, 128, 138.505, 295.625, 0.469
fixed, 256, 291.707, 601.983, 0.485
random, 2, 12.698, 12.849, 0.988
random, 4, 16.065, 15.857, 1.013
random, 8, 19.564, 21.105, 0.927
random, 16, 23.919, 26.823, 0.892
random, 32, 31.987, 39.591, 0.808
random, 64, 49.282, 71.487, 0.689
random, 128, 82.23, 145.364, 0.566
random, 256, 152.209, 298.434, 0.51
Co-authored-by: Alexander Monakov <amonakov@ispras.ru>
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Diffstat (limited to 'elf')
| -rw-r--r-- | elf/simple-dl-new-hash.h (renamed from elf/dl-new-hash.h) | 20 | ||||
| -rw-r--r-- | elf/tst-dl-hash.c | 1 |
2 files changed, 9 insertions, 12 deletions
diff --git a/elf/dl-new-hash.h b/elf/simple-dl-new-hash.h index 8641bb4196..1437b1bd36 100644 --- a/elf/dl-new-hash.h +++ b/elf/simple-dl-new-hash.h @@ -1,4 +1,4 @@ -/* _dl_new_hash for elf symbol lookup +/* __simple_dl_new_hash for testing true elf symbol lookup. Copyright (C) 2022 Free Software Foundation, Inc. This file is part of the GNU C Library. @@ -16,16 +16,16 @@ License along with the GNU C Library; if not, see <https://www.gnu.org/licenses/>. */ -#ifndef _DL_NEW_HASH_H -#define _DL_NEW_HASH_H 1 +#ifndef _SIMPLE_DL_NEW_HASH_H +#define _SIMPLE_DL_NEW_HASH_H 1 #include <stdint.h> -/* For __always_inline. */ -#include <sys/cdefs.h> -static __always_inline uint32_t +/* For testing/benchmarking purposes. Real implementation in + sysdeps/generic/dl-new-hash.h. */ +static uint32_t __attribute__ ((unused)) -_dl_new_hash (const char *s) +__simple_dl_new_hash (const char *s) { uint32_t h = 5381; for (unsigned char c = *s; c != '\0'; c = *++s) @@ -33,8 +33,4 @@ _dl_new_hash (const char *s) return h; } -/* For testing/benchmarking purposes. */ -#define __simple_dl_new_hash _dl_new_hash - - -#endif /* dl-new-hash.h */ +#endif /* simple-dl-new-hash.h */ diff --git a/elf/tst-dl-hash.c b/elf/tst-dl-hash.c index 8697eb73a0..b21766c63d 100644 --- a/elf/tst-dl-hash.c +++ b/elf/tst-dl-hash.c @@ -18,6 +18,7 @@ #include <simple-dl-hash.h> +#include <simple-dl-new-hash.h> #include <dl-hash.h> #include <dl-new-hash.h> #include <support/support.h> |