From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-yb1-xb29.google.com (mail-yb1-xb29.google.com [IPv6:2607:f8b0:4864:20::b29]) by sourceware.org (Postfix) with ESMTPS id ECE113850845 for ; Wed, 29 Jun 2022 22:11:57 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org ECE113850845 Received: by mail-yb1-xb29.google.com with SMTP id i7so30398122ybe.11 for ; Wed, 29 Jun 2022 15:11:57 -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=Nsu1AV+7es9FbaBa/wKDM1gV+ei1nNSxqO4FGIeAcRk=; b=cGgQN6qNFqmnR4JtZxS6UrwpLpK5o4azhiKJztJPhTQh+gI6jc67bpnjXc9ivr8k0j /u1MwBONmKYQPCEyCbZe+obY0kGDn/YuKrM7hF7GqOGZB1xMmLnYsuuv1u1npZa6w5bH U7ThxQoHuFgS1FUFWOUI3RfwTubyNjSQCYXQXfsMNFnYhLW1YGW1M+XU4J+Gu9i9a99i 6n7SOYFh8zNeHmisEknlWAVb/JTf9Z5EWhDf8rRjY2ekzgPxuBbeeN/kUhiRwvFGrj8x sceUFmCffhrhjoeqtQC4ipLMKPNxzyD1J8CbeWNcQ2vWApzAf3nIJLVMZ8mRCftu6IOK Zukg== X-Gm-Message-State: AJIora+0mXiTBPloigHrKO0q1axANL3sNbQqKiRMpUKjXiXOkcVmJx+a oSd7YbzavQWzZwOjBTt8Sm/LdXgurBl9Iu0i/D3IUZWzGSQ= X-Google-Smtp-Source: AGRyM1s2/wt40Y7GfzLv9vPEvDt93JDlyLn+CPcT9X8Xc5N+ITIXKyiccn9lY/wRhU9p/4czaRaR+QjVdpgwRYWHEqM= X-Received: by 2002:a25:d715:0:b0:66a:1c6a:3eb5 with SMTP id o21-20020a25d715000000b0066a1c6a3eb5mr6059201ybg.555.1656540717358; Wed, 29 Jun 2022 15:11:57 -0700 (PDT) MIME-Version: 1.0 References: <20220628152735.17863-1-goldstein.w.n@gmail.com> <20220628152735.17863-2-goldstein.w.n@gmail.com> In-Reply-To: From: Noah Goldstein Date: Wed, 29 Jun 2022 15:11:46 -0700 Message-ID: Subject: Re: [PATCH v1 2/3] x86: Move and slightly improve memset_erms To: "H.J. Lu" Cc: GNU C Library , "Carlos O'Donell" Content-Type: text/plain; charset="UTF-8" X-Spam-Status: No, score=-8.8 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 22:11:59 -0000 On Wed, Jun 29, 2022 at 12:32 PM Noah Goldstein wrote: > > On Wed, Jun 29, 2022 at 12:26 PM H.J. Lu wrote: > > > > On Tue, Jun 28, 2022 at 8:27 AM 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 L(memset_{chk}_erms) to its own file. Leaving it in between the > > > > It is ENTRY, not L. Did you mean to move them to the end of file? > > Will fix L -> ENTRY for V2. Fixed in V2. > > Yes it should be moved to new file in this patch. Was rebase mistake. The file > change is in the isa raising patch. Will fix both for v2. > > > > > memset_{impl}_unaligned both adds unnecessary complexity to the > > > file and wastes space in a relatively hot cache section. > > > --- > > > .../multiarch/memset-vec-unaligned-erms.S | 54 ++++++++----------- > > > 1 file changed, 23 insertions(+), 31 deletions(-) > > > > > > diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S > > > index abc12d9cda..d98c613651 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 > > > @@ -461,3 +430,26 @@ L(between_2_3): > > > #endif > > > ret > > > END (MEMSET_SYMBOL (__memset, unaligned_erms)) > > > + > > > +#if defined USE_MULTIARCH && IS_IN (libc) && 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 > > > + 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 > > > -- > > > 2.34.1 > > > > > > > > > -- > > H.J.