From 7fbe4770ecd7b9d86b733af02f1182d214e52c45 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Thu, 22 Jul 2021 20:26:25 -0700 Subject: [PATCH v2] x86-64: Add Avoid_Short_Distance_REP_MOVSB commit 3ec5d83d2a237d39e7fd6ef7a0bc8ac4c171a4a5 Author: H.J. Lu Date: Sat Jan 25 14:19:40 2020 -0800 x86-64: Avoid rep movsb with short distance [BZ #27130] introduced some regressions on Intel processors without Fast Short REP MOV (FSRM). Add Avoid_Short_Distance_REP_MOVSB to avoid rep movsb with short distance only on Intel processors with FSRM. bench-memmove-large on Skylake server shows that cycles of __memmove_evex_unaligned_erms improves for the following data size: before after Improvement length=4127, align1=3, align2=0: 479.38 343.00 28% length=4223, align1=9, align2=5: 405.62 335.50 17% length=8223, align1=3, align2=0: 786.12 495.00 37% length=8319, align1=9, align2=5: 256.69 170.38 33% length=16415, align1=3, align2=0: 1436.88 839.50 41% length=16511, align1=9, align2=5: 1375.50 840.62 39% length=32799, align1=3, align2=0: 2890.00 1850.62 36% length=32895, align1=9, align2=5: 2891.38 1948.62 32% Add a 25-byte NOP padding after JMP for Avoid_Short_Distance_REP_MOVSB, which improves bench-memcpy-random performance on Tiger Lake by ~30%. --- sysdeps/x86/cacheinfo.h | 9 +++++++++ sysdeps/x86/cpu-features.c | 5 +++++ .../cpu-features-preferred_feature_index_1.def | 1 + sysdeps/x86/sysdep.h | 5 +++++ .../x86_64/multiarch/memmove-vec-unaligned-erms.S | 13 +++++++++++++ 5 files changed, 33 insertions(+) diff --git a/sysdeps/x86/cacheinfo.h b/sysdeps/x86/cacheinfo.h index eba8dbc4a6..41d2c81369 100644 --- a/sysdeps/x86/cacheinfo.h +++ b/sysdeps/x86/cacheinfo.h @@ -49,6 +49,11 @@ long int __x86_rep_stosb_threshold attribute_hidden = 2048; /* Threshold to stop using Enhanced REP MOVSB. */ long int __x86_rep_movsb_stop_threshold attribute_hidden; +/* A bit-wise OR of string/memory requirements for optimal performance + e.g. X86_STRING_CONTROL_AVOID_SHORT_DISTANCE_REP_MOVSB. These bits + are used at runtime to tune implementation behavior. */ +int __x86_string_control attribute_hidden; + static void init_cacheinfo (void) { @@ -71,5 +76,9 @@ init_cacheinfo (void) __x86_rep_movsb_threshold = cpu_features->rep_movsb_threshold; __x86_rep_stosb_threshold = cpu_features->rep_stosb_threshold; __x86_rep_movsb_stop_threshold = cpu_features->rep_movsb_stop_threshold; + + if (CPU_FEATURES_ARCH_P (cpu_features, Avoid_Short_Distance_REP_MOVSB)) + __x86_string_control + |= X86_STRING_CONTROL_AVOID_SHORT_DISTANCE_REP_MOVSB; } #endif diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 706a172ba9..645bba6314 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -555,6 +555,11 @@ init_cpu_features (struct cpu_features *cpu_features) cpu_features->preferred[index_arch_Prefer_AVX2_STRCMP] |= bit_arch_Prefer_AVX2_STRCMP; } + + /* Avoid avoid short distance REP MOVSB on processor with FSRM. */ + if (CPU_FEATURES_CPU_P (cpu_features, FSRM)) + cpu_features->preferred[index_arch_Avoid_Short_Distance_REP_MOVSB] + |= bit_arch_Avoid_Short_Distance_REP_MOVSB; } /* This spells out "AuthenticAMD" or "HygonGenuine". */ else if ((ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) 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 133aab19f1..d7c93f00c5 100644 --- a/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def +++ b/sysdeps/x86/include/cpu-features-preferred_feature_index_1.def @@ -33,3 +33,4 @@ 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/sysdep.h b/sysdeps/x86/sysdep.h index 51c069bfe1..cac1d762fb 100644 --- a/sysdeps/x86/sysdep.h +++ b/sysdeps/x86/sysdep.h @@ -57,6 +57,11 @@ enum cf_protection_level #define STATE_SAVE_MASK \ ((1 << 1) | (1 << 2) | (1 << 3) | (1 << 5) | (1 << 6) | (1 << 7)) +/* Constants for bits in __x86_string_control: */ + +/* Avoid short distance REP MOVSB. */ +#define X86_STRING_CONTROL_AVOID_SHORT_DISTANCE_REP_MOVSB (1 << 0) + #ifdef __ASSEMBLER__ /* Syntactic details of assembler. */ diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S index a783da5de2..8d42fe517b 100644 --- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S @@ -325,12 +325,24 @@ L(movsb): /* Avoid slow backward REP MOVSB. */ jb L(more_8x_vec_backward) # if AVOID_SHORT_DISTANCE_REP_MOVSB + andl $X86_STRING_CONTROL_AVOID_SHORT_DISTANCE_REP_MOVSB, __x86_string_control(%rip) + jz 3f movq %rdi, %rcx subq %rsi, %rcx jmp 2f + /* Add a 25-byte NOP padding here to improve bench-memcpy-random + performance on Skylake and Tiger Lake. */ + /* data16 cs nopw 0x0(%rax,%rax,1) */ + .byte 0x66, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 + /* data16 cs nopw 0x0(%rax,%rax,1) */ + .byte 0x66, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 + /* nopl (%rax) */ + .byte 0x0f, 0x1f, 0x00 # endif 1: # if AVOID_SHORT_DISTANCE_REP_MOVSB + andl $X86_STRING_CONTROL_AVOID_SHORT_DISTANCE_REP_MOVSB, __x86_string_control(%rip) + jz 3f movq %rsi, %rcx subq %rdi, %rcx 2: @@ -338,6 +350,7 @@ L(movsb): is N*4GB + [1..63] with N >= 0. */ cmpl $63, %ecx jbe L(more_2x_vec) /* Avoid "rep movsb" if ECX <= 63. */ +3: # endif mov %RDX_LP, %RCX_LP rep movsb -- 2.31.1