86 lines
3.7 KiB
Diff
86 lines
3.7 KiB
Diff
commit a182bb7a3922404f79def09d79ef89678b4049f0
|
|
Author: H.J. Lu <hjl.tools@gmail.com>
|
|
Date: Fri Oct 29 12:56:53 2021 -0700
|
|
|
|
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.
|
|
|
|
(cherry picked from commit 14dbbf46a007ae5df36646b51ad0c9e5f5259f30)
|
|
|
|
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
|
|
index de4e3c3b7258120d..f4d4049e391cbabd 100644
|
|
--- a/sysdeps/x86/cpu-features.c
|
|
+++ b/sysdeps/x86/cpu-features.c
|
|
@@ -574,14 +574,6 @@ disable_tsx:
|
|
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. */
|
|
diff --git a/sysdeps/x86/cpu-tunables.c b/sysdeps/x86/cpu-tunables.c
|
|
index 58f2fad4323d5d91..957db3ad229ba39f 100644
|
|
--- a/sysdeps/x86/cpu-tunables.c
|
|
+++ b/sysdeps/x86/cpu-tunables.c
|
|
@@ -239,8 +239,6 @@ TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp)
|
|
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:
|
|
diff --git a/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def b/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def
|
|
index 3bdc76cf71007948..8250bfcbecd29a9f 100644
|
|
--- a/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def
|
|
+++ b/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def
|
|
@@ -31,5 +31,4 @@ BIT (Prefer_ERMS)
|
|
BIT (Prefer_No_AVX512)
|
|
BIT (MathVec_Prefer_No_AVX512)
|
|
BIT (Prefer_FSRM)
|
|
-BIT (Prefer_AVX2_STRCMP)
|
|
BIT (Avoid_Short_Distance_REP_MOVSB)
|
|
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c
|
|
index 62b7abeeee646ab4..7c2901bf44456259 100644
|
|
--- a/sysdeps/x86_64/multiarch/strcmp.c
|
|
+++ b/sysdeps/x86_64/multiarch/strcmp.c
|
|
@@ -43,8 +43,7 @@ IFUNC_SELECTOR (void)
|
|
{
|
|
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))
|
|
diff --git a/sysdeps/x86_64/multiarch/strncmp.c b/sysdeps/x86_64/multiarch/strncmp.c
|
|
index 60ba0fe356b31779..f94a421784bfe923 100644
|
|
--- a/sysdeps/x86_64/multiarch/strncmp.c
|
|
+++ b/sysdeps/x86_64/multiarch/strncmp.c
|
|
@@ -43,8 +43,7 @@ IFUNC_SELECTOR (void)
|
|
{
|
|
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))
|