mirror of git://sourceware.org/git/glibc.git
x86: Set rep_movsb_threshold to 2112 on processors with FSRM
The glibc memcpy benchmark on Intel Core i7-1065G7 (Ice Lake) showed
that REP MOVSB became faster after 2112 bytes:
Vector Move REP MOVSB
length=2112, align1=0, align2=0: 24.20 24.40
length=2112, align1=1, align2=0: 26.07 23.13
length=2112, align1=0, align2=1: 27.18 28.13
length=2112, align1=1, align2=1: 26.23 25.16
length=2176, align1=0, align2=0: 23.18 22.52
length=2176, align1=2, align2=0: 25.45 22.52
length=2176, align1=0, align2=2: 27.14 27.82
length=2176, align1=2, align2=2: 22.73 25.56
length=2240, align1=0, align2=0: 24.62 24.25
length=2240, align1=3, align2=0: 29.77 27.15
length=2240, align1=0, align2=3: 35.55 29.93
length=2240, align1=3, align2=3: 34.49 25.15
length=2304, align1=0, align2=0: 34.75 26.64
length=2304, align1=4, align2=0: 32.09 22.63
length=2304, align1=0, align2=4: 28.43 31.24
Use REP MOVSB for data size > 2112 bytes in memcpy on processors with
fast short REP MOVSB (FSRM).
* sysdeps/x86/dl-cacheinfo.h (dl_init_cacheinfo): Set
rep_movsb_threshold to 2112 on processors with fast short REP
MOVSB (FSRM).
This commit is contained in:
parent
98544f5bcf
commit
cf2c57526b
|
|
@ -891,6 +891,10 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
|
|||
minimum_rep_movsb_threshold = 16 * 8;
|
||||
#endif
|
||||
}
|
||||
/* NB: The default REP MOVSB threshold is 2112 on processors with fast
|
||||
short REP MOVSB (FSRM). */
|
||||
if (CPU_FEATURE_USABLE_P (cpu_features, FSRM))
|
||||
rep_movsb_threshold = 2112;
|
||||
|
||||
unsigned long int rep_movsb_stop_threshold;
|
||||
/* ERMS feature is implemented from AMD Zen3 architecture and it is
|
||||
|
|
|
|||
Loading…
Reference in New Issue