From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pg1-x531.google.com (mail-pg1-x531.google.com [IPv6:2607:f8b0:4864:20::531]) by sourceware.org (Postfix) with ESMTPS id 60AF338485AA for ; Wed, 29 Jun 2022 22:19:20 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 60AF338485AA Received: by mail-pg1-x531.google.com with SMTP id 23so16617909pgc.8 for ; Wed, 29 Jun 2022 15:19:20 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=fBkdyytqqKiWiDDKzXL2h5o6Z1vE67MDecQko4GcjyQ=; b=NmT42omq6sQCu412Mzn1EaA3YJbak3u1JhnqPD8RiCtm57ykOxTnAlixN1ummWE/aa l23PHwkgPlPzy3FEKAFvBi8D02T6BOgAs7mRTLWRwSMrgydvVZ7Hi2I1oyv7ITDYfR8R HyJ17Uwdx9edaPZHYcA16+4Qflo8B1Erw8rMkabMyITKrgkPzoNi+WDl3pe9Eb/g+DPz 8/SysJg721/Keg4Ykz0/6vgbwV8iOiMJOfY9ijPlbYQCDoK+9EuiLGawQxlYSEco0vKR M2T5REpQCiiHKuVli6AYkYSgd8IGxiW1RvyrAdHWhg2AIdS/7Tz1QZNfRSeUS5EW+4P7 6I/w== X-Gm-Message-State: AJIora/tLHin8zNLDnqSzJrbsZ3zQpaEnfXgYKKYWC9UyXcY1xshGpT2 F0LcNKoL34f7L+MeCrJ8Md8pEVl4jMHLBsiMgp9HItUl X-Google-Smtp-Source: AGRyM1vRwOMkMaCK+kfxTlt7TS93ZxiuPktS/mZP90KEnVpe2cOCi8pepf+BlrD7DVg7foNS+S7QKdlMeS2eCK4UN+w= X-Received: by 2002:a63:b54c:0:b0:40c:7b84:4f7f with SMTP id u12-20020a63b54c000000b0040c7b844f7fmr4621527pgo.586.1656541159365; Wed, 29 Jun 2022 15:19:19 -0700 (PDT) MIME-Version: 1.0 References: <20220628152735.17863-1-goldstein.w.n@gmail.com> <20220629221204.1242709-1-goldstein.w.n@gmail.com> <20220629221204.1242709-2-goldstein.w.n@gmail.com> In-Reply-To: <20220629221204.1242709-2-goldstein.w.n@gmail.com> From: "H.J. Lu" Date: Wed, 29 Jun 2022 15:18:43 -0700 Message-ID: Subject: Re: [PATCH v2 2/3] x86: Move and slightly improve memset_erms To: Noah Goldstein Cc: GNU C Library , "Carlos O'Donell" Content-Type: text/plain; charset="UTF-8" X-Spam-Status: No, score=-3024.5 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, FREEMAIL_FROM, GIT_PATCH_0, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 29 Jun 2022 22:19:22 -0000 On Wed, Jun 29, 2022 at 3:12 PM Noah Goldstein wrote: > > Implementation wise: > 1. Remove the VZEROUPPER as memset_{impl}_unaligned_erms does not > use the L(stosb) label that was previously defined. > > 2. Don't give the hotpath (fallthrough) to zero size. > > Code positioning wise: > > Move memset_{chk}_erms to its own file. Leaving it in between the > memset_{impl}_unaligned both adds unnecessary complexity to the > file and wastes space in a relatively hot cache section. > --- > sysdeps/x86_64/multiarch/Makefile | 1 + > sysdeps/x86_64/multiarch/memset-erms.S | 25 +++++++++++++++ > .../multiarch/memset-vec-unaligned-erms.S | 31 ------------------- > 3 files changed, 26 insertions(+), 31 deletions(-) > create mode 100644 sysdeps/x86_64/multiarch/memset-erms.S > > diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile > index 62a4d96fb8..18cea04423 100644 > --- a/sysdeps/x86_64/multiarch/Makefile > +++ b/sysdeps/x86_64/multiarch/Makefile > @@ -30,6 +30,7 @@ sysdep_routines += \ > memset-avx2-unaligned-erms-rtm \ > memset-avx512-no-vzeroupper \ > memset-avx512-unaligned-erms \ > + memset-erms \ > memset-evex-unaligned-erms \ > memset-sse2-unaligned-erms \ > rawmemchr-avx2 \ > diff --git a/sysdeps/x86_64/multiarch/memset-erms.S b/sysdeps/x86_64/multiarch/memset-erms.S > new file mode 100644 > index 0000000000..1fce0c9fcc > --- /dev/null > +++ b/sysdeps/x86_64/multiarch/memset-erms.S > @@ -0,0 +1,25 @@ Need copyright notice. > +#include > + > +#if defined USE_MULTIARCH && IS_IN (libc) > + .text > +ENTRY (__memset_chk_erms) > + cmp %RDX_LP, %RCX_LP > + jb HIDDEN_JUMPTARGET (__chk_fail) > +END (__memset_chk_erms) > + > +/* Only used to measure performance of REP STOSB. */ > +ENTRY (__memset_erms) > + /* Skip zero length. */ > + test %RDX_LP, %RDX_LP > + jz L(stosb_return_zero) > + mov %RDX_LP, %RCX_LP > + movzbl %sil, %eax > + mov %RDI_LP, %RDX_LP > + rep stosb > + mov %RDX_LP, %RAX_LP > + ret > +L(stosb_return_zero): > + movq %rdi, %rax > + ret > +END (__memset_erms) > +#endif > diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S > index abc12d9cda..905d0fa464 100644 > --- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S > +++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S > @@ -156,37 +156,6 @@ L(entry_from_wmemset): > #if defined USE_MULTIARCH && IS_IN (libc) > END (MEMSET_SYMBOL (__memset, unaligned)) > > -# if VEC_SIZE == 16 > -ENTRY (__memset_chk_erms) > - cmp %RDX_LP, %RCX_LP > - jb HIDDEN_JUMPTARGET (__chk_fail) > -END (__memset_chk_erms) > - > -/* Only used to measure performance of REP STOSB. */ > -ENTRY (__memset_erms) > - /* Skip zero length. */ > - test %RDX_LP, %RDX_LP > - jnz L(stosb) > - movq %rdi, %rax > - ret > -# else > -/* Provide a hidden symbol to debugger. */ > - .hidden MEMSET_SYMBOL (__memset, erms) > -ENTRY (MEMSET_SYMBOL (__memset, erms)) > -# endif > -L(stosb): > - mov %RDX_LP, %RCX_LP > - movzbl %sil, %eax > - mov %RDI_LP, %RDX_LP > - rep stosb > - mov %RDX_LP, %RAX_LP > - VZEROUPPER_RETURN > -# if VEC_SIZE == 16 > -END (__memset_erms) > -# else > -END (MEMSET_SYMBOL (__memset, erms)) > -# endif > - > # if defined SHARED && IS_IN (libc) > ENTRY_CHK (MEMSET_CHK_SYMBOL (__memset_chk, unaligned_erms)) > cmp %RDX_LP, %RCX_LP > -- > 2.34.1 > -- H.J.