lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2026-01-06 11:51:29 +03:00
Code Activity

x86: Set Prefer_No_VZEROUPPER and add Prefer_AVX2_STRCMP

Browse Source 
1. Set Prefer_No_VZEROUPPER if RTM is usable to avoid RTM abort triggered
by VZEROUPPER inside a transactionally executing RTM region.
2. 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.  Add
Prefer_AVX2_STRCMP to prefer AVX2 strcmp family functions.
This commit is contained in:
H.J. Lu
2021-02-26 05:36:59 -08:00
parent 934d88d862
commit 1da50d4bda
3 changed files with 21 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
sysdeps/x86/cpu-features.c
View File

@@ -531,8 +531,24 @@ init_cpu_features (struct cpu_features *cpu_features)
cpu_features->preferred[index_arch_Prefer_No_VZEROUPPER]
|= bit_arch_Prefer_No_VZEROUPPER;
else
cpu_features->preferred[index_arch_Prefer_No_AVX512]
|= bit_arch_Prefer_No_AVX512;
{
cpu_features->preferred[index_arch_Prefer_No_AVX512]
|= bit_arch_Prefer_No_AVX512;
/* Avoid RTM abort triggered by VZEROUPPER inside a
transactionally executing RTM region. */
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;
}
}
/* This spells out "AuthenticAMD" or "HygonGenuine". */
else if ((ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)