From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 7852) id 580CE3857348; Mon, 2 May 2022 21:31:00 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 580CE3857348 Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Sunil Pandey To: glibc-cvs@sourceware.org Subject: [glibc/release/2.33/master] x86-64: Remove Prefer_AVX2_STRCMP X-Act-Checkin: glibc X-Git-Author: H.J. Lu X-Git-Refname: refs/heads/release/2.33/master X-Git-Oldrev: 1a7af4e140f0e8e4633a5938a804d429e9a82d52 X-Git-Newrev: ce7859217072eca6cca888b8307d16db8b775ba5 Message-Id: <20220502213100.580CE3857348@sourceware.org> Date: Mon, 2 May 2022 21:31:00 +0000 (GMT) X-BeenThere: glibc-cvs@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Glibc-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 May 2022 21:31:00 -0000 https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=ce7859217072eca6cca888b8307d16db8b775ba5 commit ce7859217072eca6cca888b8307d16db8b775ba5 Author: H.J. Lu 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: --- sysdeps/x86/cpu-features.c | 8 -------- sysdeps/x86/cpu-tunables.c | 2 -- sysdeps/x86/include/cpu-features-preferred_feature_index_1.def | 1 - sysdeps/x86_64/multiarch/strcmp.c | 3 +-- sysdeps/x86_64/multiarch/strncmp.c | 3 +-- 5 files changed, 2 insertions(+), 15 deletions(-) diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 76882dc0ed..e7dc25aaf5 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -563,14 +563,6 @@ 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 a90df39b78..126896f41b 100644 --- a/sysdeps/x86/cpu-tunables.c +++ b/sysdeps/x86/cpu-tunables.c @@ -238,8 +238,6 @@ 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 d7c93f00c5..1530d594b3 100644 --- a/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def +++ b/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def @@ -32,5 +32,4 @@ 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 62b7abeeee..7c2901bf44 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 60ba0fe356..f94a421784 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))