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.
(cherry picked from commit
14dbbf46a007ae5df36646b51ad0c9e5f5259f30)
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
cpu_features->preferred[index_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. */
CHECK_GLIBC_IFUNC_PREFERRED_BOTH (n, cpu_features,
Fast_Copy_Backward,
disable, 18);
- CHECK_GLIBC_IFUNC_PREFERRED_NEED_BOTH
- (n, cpu_features, Prefer_AVX2_STRCMP, AVX2, disable, 18);
}
break;
case 19:
BIT (Prefer_No_AVX512)
BIT (MathVec_Prefer_No_AVX512)
BIT (Prefer_FSRM)
-BIT (Prefer_AVX2_STRCMP)
BIT (Avoid_Short_Distance_REP_MOVSB)
{
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
&& CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
- && CPU_FEATURE_USABLE_P (cpu_features, BMI2)
- && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_AVX2_STRCMP))
+ && CPU_FEATURE_USABLE_P (cpu_features, BMI2))
return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
{
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
&& CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
- && CPU_FEATURE_USABLE_P (cpu_features, BMI2)
- && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_AVX2_STRCMP))
+ && CPU_FEATURE_USABLE_P (cpu_features, BMI2))
return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))