From patchwork Fri Apr 15 05:51:32 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Noah Goldstein X-Patchwork-Id: 1617651 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: bilbo.ozlabs.org; dkim=pass (1024-bit key; secure) header.d=sourceware.org header.i=@sourceware.org header.a=rsa-sha256 header.s=default header.b=MzlvQ4FW; dkim-atps=neutral Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=sourceware.org (client-ip=8.43.85.97; helo=sourceware.org; envelope-from=libc-alpha-bounces+incoming=patchwork.ozlabs.org@sourceware.org; receiver=) Received: from sourceware.org (server2.sourceware.org [8.43.85.97]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by bilbo.ozlabs.org (Postfix) with ESMTPS id 4Kflqr10djz9sCq for ; Fri, 15 Apr 2022 15:53:28 +1000 (AEST) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 169F6385B203 for ; Fri, 15 Apr 2022 05:53:26 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 169F6385B203 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1650002006; bh=oZNpfqu+nwMTAV+ZUe9HkbTvO0GYHHu0nQvM5MfVjr4=; h=To:Subject:Date:In-Reply-To:References:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To: From; b=MzlvQ4FWhqHGYbNdvk6Xjw19e/vO26Guh/AIulDbsmDnv9Pqld5dLzO3LeRWxkMDF Hkpnv94bzx+YwIwGEl+1MksQltoWtuAys22G55+XOsjEHN9HI8WBuUA53ULu25sU/6 VQE3+wPGm8ay88gJS5DczYsXIzhAuDFaUEuquWKc= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mail-io1-xd2b.google.com (mail-io1-xd2b.google.com [IPv6:2607:f8b0:4864:20::d2b]) by sourceware.org (Postfix) with ESMTPS id 33BA93857376 for ; Fri, 15 Apr 2022 05:51:43 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 33BA93857376 Received: by mail-io1-xd2b.google.com with SMTP id z6so7583643iot.0 for ; Thu, 14 Apr 2022 22:51:43 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=oZNpfqu+nwMTAV+ZUe9HkbTvO0GYHHu0nQvM5MfVjr4=; b=FJ25cFUZOsbsOnCUPq8NPVY50AcVRAlU1dXQ+33Jwx17u+21rZhvcInq2TOoCQpakd z6IWmTZpZB9gh2Hnxzbhiu7o2XKfCg15XVQuNBXMLR/dDTBPRbYH1BtfNagB2EBZ4aNj Ja/64Qkgq5eN5JUcCJGKjQpmzVbJYjQmt1TAJBr7n/m4FZawLz+4iVk7M3eiCCHbSA70 GuRlxDNYYsw4pAGcMxwSAl1SuPRYUnvQM2biFyo/XlBpxiGfUpj7vJqXjvsaFqUiaTIN gjcc6hqgcWlPkays52XHvvf3qlKucxBJwneeoltkbOwkTtK5PKZKNBJQMD1/mJn9aECg o2HQ== X-Gm-Message-State: AOAM530DOFps6tgGvTOM9A9k0GoSY9OGDtZSQZGIbN6ikUTYk4kH8XLe Hbatzo/Wz3Syr/8kAZxs+cgq+mmQwfI= X-Google-Smtp-Source: ABdhPJyTgM0fB/hbC3n0+On0w3XW4hrwPrKWQgjM4Pu0KgbIooLkeka2ouI9LMNwgUOkSTDGbVE0rQ== X-Received: by 2002:a05:6602:26cb:b0:648:f391:c37d with SMTP id g11-20020a05660226cb00b00648f391c37dmr2776208ioo.198.1650001902213; Thu, 14 Apr 2022 22:51:42 -0700 (PDT) Received: from localhost.localdomain (173-245-203-171.ipvanish.com. [173.245.203.171]) by smtp.googlemail.com with ESMTPSA id p10-20020a056e02104a00b002cbd0996ce8sm2218682ilj.16.2022.04.14.22.51.41 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 14 Apr 2022 22:51:42 -0700 (PDT) To: libc-alpha@sourceware.org Subject: [PATCH v1 3/3] x86: Cleanup page cross code in memcmp-avx2-movbe.S Date: Fri, 15 Apr 2022 00:51:32 -0500 Message-Id: <20220415055132.1257272-3-goldstein.w.n@gmail.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220415055132.1257272-1-goldstein.w.n@gmail.com> References: <20220415055132.1257272-1-goldstein.w.n@gmail.com> MIME-Version: 1.0 X-Spam-Status: No, score=-11.9 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=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) 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-Patchwork-Original-From: Noah Goldstein via Libc-alpha From: Noah Goldstein Reply-To: Noah Goldstein Errors-To: libc-alpha-bounces+incoming=patchwork.ozlabs.org@sourceware.org Sender: "Libc-alpha" Old code was both inefficient and wasted code size. New code (-62 bytes) and comparable or better performance in the page cross case. geometric_mean(N=20) of page cross cases New / Original: 0.960 size, align0, align1, ret, New Time/Old Time 1, 4095, 0, 0, 1.001 1, 4095, 0, 1, 0.999 1, 4095, 0, -1, 1.0 2, 4094, 0, 0, 1.0 2, 4094, 0, 1, 1.0 2, 4094, 0, -1, 1.0 3, 4093, 0, 0, 1.0 3, 4093, 0, 1, 1.0 3, 4093, 0, -1, 1.0 4, 4092, 0, 0, 0.987 4, 4092, 0, 1, 1.0 4, 4092, 0, -1, 1.0 5, 4091, 0, 0, 0.984 5, 4091, 0, 1, 1.002 5, 4091, 0, -1, 1.005 6, 4090, 0, 0, 0.993 6, 4090, 0, 1, 1.001 6, 4090, 0, -1, 1.003 7, 4089, 0, 0, 0.991 7, 4089, 0, 1, 1.0 7, 4089, 0, -1, 1.001 8, 4088, 0, 0, 0.875 8, 4088, 0, 1, 0.881 8, 4088, 0, -1, 0.888 9, 4087, 0, 0, 0.872 9, 4087, 0, 1, 0.879 9, 4087, 0, -1, 0.883 10, 4086, 0, 0, 0.878 10, 4086, 0, 1, 0.886 10, 4086, 0, -1, 0.873 11, 4085, 0, 0, 0.878 11, 4085, 0, 1, 0.881 11, 4085, 0, -1, 0.879 12, 4084, 0, 0, 0.873 12, 4084, 0, 1, 0.889 12, 4084, 0, -1, 0.875 13, 4083, 0, 0, 0.873 13, 4083, 0, 1, 0.863 13, 4083, 0, -1, 0.863 14, 4082, 0, 0, 0.838 14, 4082, 0, 1, 0.869 14, 4082, 0, -1, 0.877 15, 4081, 0, 0, 0.841 15, 4081, 0, 1, 0.869 15, 4081, 0, -1, 0.876 16, 4080, 0, 0, 0.988 16, 4080, 0, 1, 0.99 16, 4080, 0, -1, 0.989 17, 4079, 0, 0, 0.978 17, 4079, 0, 1, 0.981 17, 4079, 0, -1, 0.98 18, 4078, 0, 0, 0.981 18, 4078, 0, 1, 0.98 18, 4078, 0, -1, 0.985 19, 4077, 0, 0, 0.977 19, 4077, 0, 1, 0.979 19, 4077, 0, -1, 0.986 20, 4076, 0, 0, 0.977 20, 4076, 0, 1, 0.986 20, 4076, 0, -1, 0.984 21, 4075, 0, 0, 0.977 21, 4075, 0, 1, 0.983 21, 4075, 0, -1, 0.988 22, 4074, 0, 0, 0.983 22, 4074, 0, 1, 0.994 22, 4074, 0, -1, 0.993 23, 4073, 0, 0, 0.98 23, 4073, 0, 1, 0.992 23, 4073, 0, -1, 0.995 24, 4072, 0, 0, 0.989 24, 4072, 0, 1, 0.989 24, 4072, 0, -1, 0.991 25, 4071, 0, 0, 0.99 25, 4071, 0, 1, 0.999 25, 4071, 0, -1, 0.996 26, 4070, 0, 0, 0.993 26, 4070, 0, 1, 0.995 26, 4070, 0, -1, 0.998 27, 4069, 0, 0, 0.993 27, 4069, 0, 1, 0.999 27, 4069, 0, -1, 1.0 28, 4068, 0, 0, 0.997 28, 4068, 0, 1, 1.0 28, 4068, 0, -1, 0.999 29, 4067, 0, 0, 0.996 29, 4067, 0, 1, 0.999 29, 4067, 0, -1, 0.999 30, 4066, 0, 0, 0.991 30, 4066, 0, 1, 1.001 30, 4066, 0, -1, 0.999 31, 4065, 0, 0, 0.988 31, 4065, 0, 1, 0.998 31, 4065, 0, -1, 0.998 Reviewed-by: H.J. Lu --- sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S | 98 ++++++++++++-------- 1 file changed, 61 insertions(+), 37 deletions(-) diff --git a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S index a34ea1645d..210c9925b6 100644 --- a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S +++ b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S @@ -429,22 +429,21 @@ L(page_cross_less_vec): # ifndef USE_AS_WMEMCMP cmpl $8, %edx jae L(between_8_15) + /* Fall through for [4, 7]. */ cmpl $4, %edx - jae L(between_4_7) + jb L(between_2_3) - /* Load as big endian to avoid branches. */ - movzwl (%rdi), %eax - movzwl (%rsi), %ecx - shll $8, %eax - shll $8, %ecx - bswap %eax - bswap %ecx - movzbl -1(%rdi, %rdx), %edi - movzbl -1(%rsi, %rdx), %esi - orl %edi, %eax - orl %esi, %ecx - /* Subtraction is okay because the upper 8 bits are zero. */ - subl %ecx, %eax + movbe (%rdi), %eax + movbe (%rsi), %ecx + shlq $32, %rax + shlq $32, %rcx + movbe -4(%rdi, %rdx), %edi + movbe -4(%rsi, %rdx), %esi + orq %rdi, %rax + orq %rsi, %rcx + subq %rcx, %rax + /* Fast path for return zero. */ + jnz L(ret_nonzero) /* No ymm register was touched. */ ret @@ -457,9 +456,33 @@ L(one_or_less): /* No ymm register was touched. */ ret + .p2align 4,, 5 +L(ret_nonzero): + sbbl %eax, %eax + orl $1, %eax + /* No ymm register was touched. */ + ret + + .p2align 4,, 2 +L(zero): + xorl %eax, %eax + /* No ymm register was touched. */ + ret + .p2align 4 L(between_8_15): -# endif + movbe (%rdi), %rax + movbe (%rsi), %rcx + subq %rcx, %rax + jnz L(ret_nonzero) + movbe -8(%rdi, %rdx), %rax + movbe -8(%rsi, %rdx), %rcx + subq %rcx, %rax + /* Fast path for return zero. */ + jnz L(ret_nonzero) + /* No ymm register was touched. */ + ret +# else /* If USE_AS_WMEMCMP fall through into 8-15 byte case. */ vmovq (%rdi), %xmm1 vmovq (%rsi), %xmm2 @@ -475,16 +498,13 @@ L(between_8_15): VPCMPEQ %xmm1, %xmm2, %xmm2 vpmovmskb %xmm2, %eax subl $0xffff, %eax + /* Fast path for return zero. */ jnz L(return_vec_0) /* No ymm register was touched. */ ret +# endif - .p2align 4 -L(zero): - xorl %eax, %eax - ret - - .p2align 4 + .p2align 4,, 10 L(between_16_31): /* From 16 to 31 bytes. No branch when size == 16. */ vmovdqu (%rsi), %xmm2 @@ -501,11 +521,17 @@ L(between_16_31): VPCMPEQ (%rdi), %xmm2, %xmm2 vpmovmskb %xmm2, %eax subl $0xffff, %eax + /* Fast path for return zero. */ jnz L(return_vec_0) /* No ymm register was touched. */ ret # ifdef USE_AS_WMEMCMP + .p2align 4,, 2 +L(zero): + xorl %eax, %eax + ret + .p2align 4 L(one_or_less): jb L(zero) @@ -520,22 +546,20 @@ L(one_or_less): # else .p2align 4 -L(between_4_7): - /* Load as big endian with overlapping movbe to avoid branches. - */ - movbe (%rdi), %eax - movbe (%rsi), %ecx - shlq $32, %rax - shlq $32, %rcx - movbe -4(%rdi, %rdx), %edi - movbe -4(%rsi, %rdx), %esi - orq %rdi, %rax - orq %rsi, %rcx - subq %rcx, %rax - jz L(zero_4_7) - sbbl %eax, %eax - orl $1, %eax -L(zero_4_7): +L(between_2_3): + /* Load as big endian to avoid branches. */ + movzwl (%rdi), %eax + movzwl (%rsi), %ecx + bswap %eax + bswap %ecx + shrl %eax + shrl %ecx + movzbl -1(%rdi, %rdx), %edi + movzbl -1(%rsi, %rdx), %esi + orl %edi, %eax + orl %esi, %ecx + /* Subtraction is okay because the upper bit is zero. */ + subl %ecx, %eax /* No ymm register was touched. */ ret # endif