qiurui
/
glibc
mirror of git://sourceware.org/git/glibc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

x86-64: Remove Prefer_AVX2_STRCMP 

Remove Prefer_AVX2_STRCMP to enable EVEX strcmp.  When comparing 2 32-byte
strings, EVEX strcmp has been improved to require 1 load, 1 VPTESTM, 1
VPCMP, 1 KMOVD and 1 INCL instead of 2 loads, 3 VPCMPs, 2 KORDs, 1 KMOVD
and 1 TESTL while AVX2 strcmp requires 1 load, 2 VPCMPEQs, 1 VPMINU, 1
VPMOVMSKB and 1 TESTL.  EVEX strcmp is now faster than AVX2 strcmp by up
to 40% on Tiger Lake and Ice Lake.
This commit is contained in:
H.J. Lu 2021-10-29 12:56:53 -07:00
parent c46e9afb2d
commit 14dbbf46a0
5 changed files with 2 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
sysdeps/x86/cpu-features.c
View File

@ -546,14 +546,6 @@ init_cpu_features (struct cpu_features *cpu_features)
if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
cpu_features->preferred[index_arch_Prefer_No_VZEROUPPER] cpu_features->preferred[index_arch_Prefer_No_VZEROUPPER]
|= bit_arch_Prefer_No_VZEROUPPER; |= bit_arch_Prefer_No_VZEROUPPER;
/* Since to compare 2 32-byte strings, 256-bit EVEX strcmp
requires 2 loads, 3 VPCMPs and 2 KORDs while AVX2 strcmp
requires 1 load, 2 VPCMPEQs, 1 VPMINU and 1 VPMOVMSKB,
AVX2 strcmp is faster than EVEX strcmp. */
if (CPU_FEATURE_USABLE_P (cpu_features, AVX2))
cpu_features->preferred[index_arch_Prefer_AVX2_STRCMP]
|= bit_arch_Prefer_AVX2_STRCMP;
} }
/* Avoid avoid short distance REP MOVSB on processor with FSRM. */ /* Avoid avoid short distance REP MOVSB on processor with FSRM. */

2
sysdeps/x86/cpu-tunables.c
View File

@ -239,8 +239,6 @@ TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp)
CHECK_GLIBC_IFUNC_PREFERRED_BOTH (n, cpu_features, CHECK_GLIBC_IFUNC_PREFERRED_BOTH (n, cpu_features,
Fast_Copy_Backward, Fast_Copy_Backward,
disable, 18); disable, 18);
CHECK_GLIBC_IFUNC_PREFERRED_NEED_BOTH
(n, cpu_features, Prefer_AVX2_STRCMP, AVX2, disable, 18);
} }
break; break;
case 19: case 19:

1
sysdeps/x86/include/cpu-features-preferred_feature_index_1.def
View File

@ -32,5 +32,4 @@ BIT (Prefer_ERMS)
BIT (Prefer_No_AVX512) BIT (Prefer_No_AVX512)
BIT (MathVec_Prefer_No_AVX512) BIT (MathVec_Prefer_No_AVX512)
BIT (Prefer_FSRM) BIT (Prefer_FSRM)
BIT (Prefer_AVX2_STRCMP)
BIT (Avoid_Short_Distance_REP_MOVSB) BIT (Avoid_Short_Distance_REP_MOVSB)

3
sysdeps/x86_64/multiarch/strcmp.c
View File

@ -43,8 +43,7 @@ IFUNC_SELECTOR (void)
{ {
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
&& CPU_FEATURE_USABLE_P (cpu_features, AVX512BW) && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
&& CPU_FEATURE_USABLE_P (cpu_features, BMI2) && CPU_FEATURE_USABLE_P (cpu_features, BMI2))
&& !CPU_FEATURES_ARCH_P (cpu_features, Prefer_AVX2_STRCMP))
return OPTIMIZE (evex); return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) if (CPU_FEATURE_USABLE_P (cpu_features, RTM))

3
sysdeps/x86_64/multiarch/strncmp.c
View File

@ -43,8 +43,7 @@ IFUNC_SELECTOR (void)
{ {
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
&& CPU_FEATURE_USABLE_P (cpu_features, AVX512BW) && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
&& CPU_FEATURE_USABLE_P (cpu_features, BMI2) && CPU_FEATURE_USABLE_P (cpu_features, BMI2))
&& !CPU_FEATURES_ARCH_P (cpu_features, Prefer_AVX2_STRCMP))
return OPTIMIZE (evex); return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) if (CPU_FEATURE_USABLE_P (cpu_features, RTM))