From cf2c57526ba4b57e6863ad4db8a868e2678adce8 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Fri, 30 Apr 2021 05:58:59 -0700 Subject: [PATCH] x86: Set rep_movsb_threshold to 2112 on processors with FSRM Content-type: text/plain; charset=UTF-8 The glibc memcpy benchmark on Intel Core i7-1065G7 (Ice Lake) showed that REP MOVSB became faster after 2112 bytes: Vector Move REP MOVSB length=2112, align1=0, align2=0: 24.20 24.40 length=2112, align1=1, align2=0: 26.07 23.13 length=2112, align1=0, align2=1: 27.18 28.13 length=2112, align1=1, align2=1: 26.23 25.16 length=2176, align1=0, align2=0: 23.18 22.52 length=2176, align1=2, align2=0: 25.45 22.52 length=2176, align1=0, align2=2: 27.14 27.82 length=2176, align1=2, align2=2: 22.73 25.56 length=2240, align1=0, align2=0: 24.62 24.25 length=2240, align1=3, align2=0: 29.77 27.15 length=2240, align1=0, align2=3: 35.55 29.93 length=2240, align1=3, align2=3: 34.49 25.15 length=2304, align1=0, align2=0: 34.75 26.64 length=2304, align1=4, align2=0: 32.09 22.63 length=2304, align1=0, align2=4: 28.43 31.24 Use REP MOVSB for data size > 2112 bytes in memcpy on processors with fast short REP MOVSB (FSRM). * sysdeps/x86/dl-cacheinfo.h (dl_init_cacheinfo): Set rep_movsb_threshold to 2112 on processors with fast short REP MOVSB (FSRM). --- sysdeps/x86/cacheinfo.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sysdeps/x86/cacheinfo.h b/sysdeps/x86/cacheinfo.h index f72f634a..cc3941d3 100644 --- a/sysdeps/x86/cacheinfo.h +++ b/sysdeps/x86/cacheinfo.h @@ -430,6 +430,12 @@ init_cacheinfo (void) rep_movsb_threshold = 2048 * (16 / 16); minimum_rep_movsb_threshold = 16 * 8; } + + /* NB: The default REP MOVSB threshold is 2112 on processors with fast + short REP MOVSB (FSRM). */ + if (CPU_FEATURE_USABLE_P (cpu_features, FSRM)) + rep_movsb_threshold = 2112; + if (cpu_features->rep_movsb_threshold > minimum_rep_movsb_threshold) __x86_rep_movsb_threshold = cpu_features->rep_movsb_threshold; else -- GitLab