From patchwork Thu Sep 30 08:43:52 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wu Jianhua X-Patchwork-Id: 30684 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a6b:6506:0:0:0:0:0 with SMTP id z6csp436430iob; Thu, 30 Sep 2021 01:44:19 -0700 (PDT) X-Google-Smtp-Source: ABdhPJzDq2YN7pAk+g1g/AUK5PBd1lFv96MFBl1+NXdoAyOKwLQiZTArtesbdPOly0KGB42N3GHn X-Received: by 2002:a17:906:6691:: with SMTP id z17mr5342752ejo.207.1632991459241; Thu, 30 Sep 2021 01:44:19 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1632991459; cv=none; d=google.com; s=arc-20160816; b=FOTjILh3FGSBjoE1xnc1eotEBkmwtUy3liz6tDJE2t7a/8B6X9CdFHWXaNZF3h1crl g64I/m3N0eOhUrtPE9IUknuG/e7jMrv16WogKG62R+NKYAJ70khk8/ZBIS3GVUafb7o9 wFEBasHRjSQ+bW0xAfrtEl89sSOKZpON/fog0J6e2d3d1VyxGBfLMOtUbJhV+E4I7G3E fx3GmuhQm6i5sh0ePuPwEtmQGEzQN/crGUPJ20Vlb85fUgMhi5jsZ3VREipyt6BH2XnR 4HnEsGChRjdZZD5h7KskKzMz66OZH4p74AKWYhgBp4GBoHNwvzhCGX0O6p99Ks1Hpfke sBrQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:message-id:date:to:from:delivered-to; bh=NKlJyhtc6JbT8SGZXIdRI4jd0GtqQgXmew3MPddO+YE=; b=o+1lGIW3dZLcNYELuXIagLfiMOC6WIGhyBjP1iFDZZJCIUCabHhEghoiIsRfXDwgNr bS3M5KWO3QJT9ki1girxJEGGnwF0+L5jlDRJN4RBAuyBzctJfbKcJn3qQU3QjgjUKGmn z566nXJ9dFDE08E+STNR/Aa6BXHv9yEOugZATa4O7SzoNJ7j6p8BrmCg2hEhSqN29I5b +D40Vgi5VUwsToBGrqG/7z0Vmw4cD/1zhMLqbF/fa0FYnlpIzGAb0J2jDom6O6kvAAc/ EZ8ZLHIlSxd7+A30GmUJB3MhewgmpjIUUcESdEoBXBNHjQm6VqC0lc5Gju65KdGsdM9T xXIg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id n3si2482192edd.109.2021.09.30.01.44.18; Thu, 30 Sep 2021 01:44:19 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 5FFC46899A7; Thu, 30 Sep 2021 11:44:14 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 1CA26680610 for ; Thu, 30 Sep 2021 11:44:06 +0300 (EEST) X-IronPort-AV: E=McAfee;i="6200,9189,10122"; a="224793897" X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="224793897" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2021 01:43:59 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="563956836" Received: from otc-skl-e5-server.sh.intel.com ([10.239.43.106]) by fmsmga002.fm.intel.com with ESMTP; 30 Sep 2021 01:43:58 -0700 From: Wu Jianhua To: ffmpeg-devel@ffmpeg.org Date: Thu, 30 Sep 2021 16:43:52 +0800 Message-Id: <20210930084355.76628-1-jianhua.wu@intel.com> X-Mailer: git-send-email 2.17.1 Subject: [FFmpeg-devel] [PATCH v3 1/4] libswscale/x86/rgb2rgb: add shuffle_bytes avx2 X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: Wu Jianhua MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: OU1s573pZpKQ Performance data(Less is better): shuffle_bytes_ssse3 3.64654 shuffle_bytes_avx2 0.94288 Signed-off-by: Wu Jianhua --- libswscale/x86/rgb2rgb.c | 17 +++++++++++++++-- libswscale/x86/rgb_2_rgb.asm | 11 +++++++++++ 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index c38a953277..0ab139aca4 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -146,6 +146,12 @@ void ff_shuffle_bytes_3012_ssse3(const uint8_t *src, uint8_t *dst, int src_size) void ff_shuffle_bytes_3210_ssse3(const uint8_t *src, uint8_t *dst, int src_size); #if ARCH_X86_64 +void ff_shuffle_bytes_2103_avx2(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_0321_avx2(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_1230_avx2(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_3012_avx2(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_3210_avx2(const uint8_t *src, uint8_t *dst, int src_size); + void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src, int width, int height, int lumStride, int chromStride, int srcStride); @@ -186,9 +192,16 @@ av_cold void rgb2rgb_init_x86(void) shuffle_bytes_3012 = ff_shuffle_bytes_3012_ssse3; shuffle_bytes_3210 = ff_shuffle_bytes_3210_ssse3; } - if (EXTERNAL_AVX(cpu_flags)) { #if ARCH_X86_64 + if (EXTERNAL_AVX2_FAST(cpu_flags)) { + shuffle_bytes_0321 = ff_shuffle_bytes_0321_avx2; + shuffle_bytes_2103 = ff_shuffle_bytes_2103_avx2; + shuffle_bytes_1230 = ff_shuffle_bytes_1230_avx2; + shuffle_bytes_3012 = ff_shuffle_bytes_3012_avx2; + shuffle_bytes_3210 = ff_shuffle_bytes_3210_avx2; + } + if (EXTERNAL_AVX(cpu_flags)) { uyvytoyuv422 = ff_uyvytoyuv422_avx; -#endif } +#endif } diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm index 29b856e281..c695c61d5c 100644 --- a/libswscale/x86/rgb_2_rgb.asm +++ b/libswscale/x86/rgb_2_rgb.asm @@ -159,6 +159,17 @@ SHUFFLE_BYTES 1, 2, 3, 0 SHUFFLE_BYTES 3, 0, 1, 2 SHUFFLE_BYTES 3, 2, 1, 0 +%if ARCH_X86_64 +%if HAVE_AVX2_EXTERNAL +INIT_YMM avx2 +SHUFFLE_BYTES 2, 1, 0, 3 +SHUFFLE_BYTES 0, 3, 2, 1 +SHUFFLE_BYTES 1, 2, 3, 0 +SHUFFLE_BYTES 3, 0, 1, 2 +SHUFFLE_BYTES 3, 2, 1, 0 +%endif +%endif + ;----------------------------------------------------------------------------------------------- ; uyvytoyuv422(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, ; const uint8_t *src, int width, int height, From patchwork Thu Sep 30 08:43:53 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wu Jianhua X-Patchwork-Id: 30685 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a6b:6506:0:0:0:0:0 with SMTP id z6csp436849iob; Thu, 30 Sep 2021 01:44:54 -0700 (PDT) X-Google-Smtp-Source: ABdhPJyu3h9dpTW+YUOpvTh8t8sTb4Kx4KGp1ZSpZ5D7R0IpGy/0e6kw2wxpPdBh8ChyyRjh4ymm X-Received: by 2002:aa7:d649:: with SMTP id v9mr5844183edr.38.1632991494083; Thu, 30 Sep 2021 01:44:54 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1632991494; cv=none; d=google.com; s=arc-20160816; b=bgkLRDjY9wtuQdeGrvIMydrRThodzysjl5J8xuIi8PzzIwzJtDuwzygO0kRjgDNMgK G9/urqngcA2KLC8mdL9zrXOtyqB2cIHO7hrB8EtJBfh4kA0gT2PaBWLhxurN03FAMJp1 5SGQNTrfMes22Ot8Bo5NTFdGOenwOG8+I5GP/TbdDneKupjlEvEvQpXdvAl3NVnbeeeS WjqEoObHx/TmLch5qRdBoOVlFK+MtkgU6IJkcgIwD7tVqk5D/gvjDtWksJXynr6sLc6B EzJH7Y+RyyCoNygtRlYnJN551GnNynLhtVME2T+b2CctFIalMPmLJ+sboE9M0Uwv+ZXs mHTw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:references:in-reply-to:message-id:date :to:from:delivered-to; bh=5LmGoIWB6ei3fRVhDYbfbPC4NjUkhm9ck+ioXBPsvrE=; b=Fqz/wumI47JlWcYJflRHP04df0ZZhm/5W9bhyJxnnYbV2daAs2Q+tcIJSMdHbeMymd BGB0c/oO+4h0izCfk2RCFiEuQmGl+mX7WJ6sUyJabD+4Ok5S+VrvnsukXN3B/sZugqnd kbORDZArOUsjcHhfTNqc4XvOnZyxkX1iEfF7fJuWlsh9MV7XMVCnf/c/Cs6K0Z0XpJzm 3b8QgGIPs45cxawmzxd8OI0S9HRjHFhNNObdlcaszVyFPOA2PQd/JNOQU/yfoUJAydRg Iyd5lUtKyP2DxuJGy/7Xk0e+gHj0Bm7w9vDvbyWdiKXETvXEV3+qSG+bletInme6Yq2d H+sA== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id s21si2615126edc.249.2021.09.30.01.44.53; Thu, 30 Sep 2021 01:44:54 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id A735C68A6A1; Thu, 30 Sep 2021 11:44:25 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 04F93689738 for ; Thu, 30 Sep 2021 11:44:18 +0300 (EEST) X-IronPort-AV: E=McAfee;i="6200,9189,10122"; a="224793902" X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="224793902" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2021 01:43:59 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="563956851" Received: from otc-skl-e5-server.sh.intel.com ([10.239.43.106]) by fmsmga002.fm.intel.com with ESMTP; 30 Sep 2021 01:43:59 -0700 From: Wu Jianhua To: ffmpeg-devel@ffmpeg.org Date: Thu, 30 Sep 2021 16:43:53 +0800 Message-Id: <20210930084355.76628-2-jianhua.wu@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20210930084355.76628-1-jianhua.wu@intel.com> References: <20210930084355.76628-1-jianhua.wu@intel.com> Subject: [FFmpeg-devel] [PATCH v3 2/4] libswscale/x86/rgb2rgb: add shuffle_bytes avx512 X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: Wu Jianhua MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: Pibb5uez2AQT Performance data(Less is better): shuffle_bytes_avx2 0.94288 shuffle_bytes_avx512 0.60049 Signed-off-by: Wu Jianhua --- libswscale/x86/rgb2rgb.c | 13 +++++++++++++ libswscale/x86/rgb_2_rgb.asm | 8 ++++++++ 2 files changed, 21 insertions(+) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index 0ab139aca4..c9ff33ab77 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -152,6 +152,12 @@ void ff_shuffle_bytes_1230_avx2(const uint8_t *src, uint8_t *dst, int src_size); void ff_shuffle_bytes_3012_avx2(const uint8_t *src, uint8_t *dst, int src_size); void ff_shuffle_bytes_3210_avx2(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_2103_avx512(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_0321_avx512(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_1230_avx512(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_3012_avx512(const uint8_t *src, uint8_t *dst, int src_size); +void ff_shuffle_bytes_3210_avx512(const uint8_t *src, uint8_t *dst, int src_size); + void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src, int width, int height, int lumStride, int chromStride, int srcStride); @@ -200,6 +206,13 @@ av_cold void rgb2rgb_init_x86(void) shuffle_bytes_3012 = ff_shuffle_bytes_3012_avx2; shuffle_bytes_3210 = ff_shuffle_bytes_3210_avx2; } + if (EXTERNAL_AVX512(cpu_flags)) { + shuffle_bytes_0321 = ff_shuffle_bytes_0321_avx512; + shuffle_bytes_2103 = ff_shuffle_bytes_2103_avx512; + shuffle_bytes_1230 = ff_shuffle_bytes_1230_avx512; + shuffle_bytes_3012 = ff_shuffle_bytes_3012_avx512; + shuffle_bytes_3210 = ff_shuffle_bytes_3210_avx512; + } if (EXTERNAL_AVX(cpu_flags)) { uyvytoyuv422 = ff_uyvytoyuv422_avx; } diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm index c695c61d5c..3380a1272c 100644 --- a/libswscale/x86/rgb_2_rgb.asm +++ b/libswscale/x86/rgb_2_rgb.asm @@ -168,6 +168,14 @@ SHUFFLE_BYTES 1, 2, 3, 0 SHUFFLE_BYTES 3, 0, 1, 2 SHUFFLE_BYTES 3, 2, 1, 0 %endif +%if HAVE_AVX512_EXTERNAL +INIT_ZMM avx512 +SHUFFLE_BYTES 2, 1, 0, 3 +SHUFFLE_BYTES 0, 3, 2, 1 +SHUFFLE_BYTES 1, 2, 3, 0 +SHUFFLE_BYTES 3, 0, 1, 2 +SHUFFLE_BYTES 3, 2, 1, 0 +%endif %endif ;----------------------------------------------------------------------------------------------- From patchwork Thu Sep 30 08:43:54 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wu Jianhua X-Patchwork-Id: 30686 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a6b:6506:0:0:0:0:0 with SMTP id z6csp436746iob; Thu, 30 Sep 2021 01:44:43 -0700 (PDT) X-Google-Smtp-Source: ABdhPJwAPr9LtHZSnvAxrNFa5rrE6hi5JTc6Cs8tjzhVar/ziTfZGhB2Rahajx8pKEkbCoY1aomQ X-Received: by 2002:a50:8405:: with SMTP id 5mr5493285edp.111.1632991483654; Thu, 30 Sep 2021 01:44:43 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1632991483; cv=none; d=google.com; s=arc-20160816; b=N72zHtNNeUHayWZiInSFPTP5FcbS0KVfcUivkZzMZOZJ7IE85yzBxSAAMhPq+c1UzD KOnPmKyWMwp77TKRWRE5S9bhjQedY+g0x9gtPePuR5ojbv7sheJe0OylGEGo7TRyclC8 eO7NcQQPsUHRiR83WTILgTqY5xSgEez9iE9GvlYEoghiwEXLAriWcbBhmaMR2RvcVSFe MPfy7HZwVVBB/5yknNX2ZbYo7F8qnlA2fFkijkBCl+cvAAc2qa4KnJLX4BXxmQfKT4hf cmFFngEszIMiv1r2a88OEutAKZtY/H2zAXDRXtz8ByJjFEfy73Ol3WLDijzPKUOwvjM6 x1GA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:references:in-reply-to:message-id:date :to:from:delivered-to; bh=pGGHiH3bLVxg0syfpysYwLmKz4cTINslaM4hpO+vSEw=; b=jY8xDcycZqWM0HouvvwJX4Xn7OgIhcUrfhynVrSEVepFUXHhxSpQ6eC8TodaCYOtZR j05D4eKX//cH4pXOxYkp1fMXBM/roGOeaMGKsse044SebCMESIUqzQnLzq60JZbo0Ksk D7zzBbYOIWmkhRFlZKHRP69WN+qCL8U9YnTB3wZR5THo3oX+1Gc6tfwM7wlDVEAMi+CD w9tcuo9zp3mDkw/3AQvc/DyEJDGV0rEJUxECS+DLkkHeXe4FmJ2qNciaw76RkSbAOcyJ a0wIWhiu2arks1h0ZudtA6+ZA39fI2j9qpmsEL8F7BQESIKMYqaOT+Iq4PjaIPl5o2hh Nfmw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id r9si2439740ejj.752.2021.09.30.01.44.42; Thu, 30 Sep 2021 01:44:43 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 9849C68A545; Thu, 30 Sep 2021 11:44:22 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 3E98B680610 for ; Thu, 30 Sep 2021 11:44:14 +0300 (EEST) X-IronPort-AV: E=McAfee;i="6200,9189,10122"; a="224793904" X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="224793904" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2021 01:44:01 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="563956873" Received: from otc-skl-e5-server.sh.intel.com ([10.239.43.106]) by fmsmga002.fm.intel.com with ESMTP; 30 Sep 2021 01:44:00 -0700 From: Wu Jianhua To: ffmpeg-devel@ffmpeg.org Date: Thu, 30 Sep 2021 16:43:54 +0800 Message-Id: <20210930084355.76628-3-jianhua.wu@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20210930084355.76628-1-jianhua.wu@intel.com> References: <20210930084355.76628-1-jianhua.wu@intel.com> Subject: [FFmpeg-devel] [PATCH v3 3/4] With the accelerating by means of AVX2, the uyvytoyuv422 can be faster X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: Wu Jianhua MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: IltpRfQxsqjd Performance data(Less is better): uyvytoyuv422_sse2 0.50388 uyvytoyuv422_avx 0.46132 uyvytoyuv422_avx2 0.27309 Signed-off-by: Wu Jianhua --- libswscale/x86/rgb2rgb.c | 6 ++++ libswscale/x86/rgb_2_rgb.asm | 60 ++++++++++++++++++++++++++++-------- 2 files changed, 53 insertions(+), 13 deletions(-) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index c9ff33ab77..a965a1755c 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -164,6 +164,9 @@ void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, void ff_uyvytoyuv422_avx(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src, int width, int height, int lumStride, int chromStride, int srcStride); +void ff_uyvytoyuv422_avx2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, + const uint8_t *src, int width, int height, + int lumStride, int chromStride, int srcStride); #endif av_cold void rgb2rgb_init_x86(void) @@ -216,5 +219,8 @@ av_cold void rgb2rgb_init_x86(void) if (EXTERNAL_AVX(cpu_flags)) { uyvytoyuv422 = ff_uyvytoyuv422_avx; } + if (EXTERNAL_AVX2_FAST(cpu_flags)) { + uyvytoyuv422 = ff_uyvytoyuv422_avx2; + } #endif } diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm index 3380a1272c..1777a99faf 100644 --- a/libswscale/x86/rgb_2_rgb.asm +++ b/libswscale/x86/rgb_2_rgb.asm @@ -31,9 +31,17 @@ pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13 pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12 pb_shuffle3012: db 3, 0, 1, 2, 7, 4, 5, 6, 11, 8, 9, 10, 15, 12, 13, 14 pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 +pb_shuffle_low: db 1, 3, 5, 7, 9, 11, 13, 15 +pd_permd256_uv: dd 0, 4, 1, 5, 2, 6, 3, 7 SECTION .text +%macro VPERM 5 +%if mmsize == %2 + vperm%1 %3, %4, %5 +%endif +%endmacro + %macro RSHIFT_COPY 3 ; %1 dst ; %2 src ; %3 shift %if cpuflag(avx) @@ -198,11 +206,16 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s mov whalfq, wq shr whalfq, 1 ; whalf = width / 2 - lea srcq, [srcq + wq * 2] + lea srcq, [srcq + wq * 2] add ydstq, wq add udstq, whalfq add vdstq, whalfq +%if mmsize > 16 + vpbroadcastq m13, [pb_shuffle_low] + movu m15, [pd_permd256_uv] +%endif + .loop_line: mov xq, wq mov wtwoq, wq @@ -246,23 +259,35 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s movu m5, [srcq + wtwoq + mmsize * 3] ; extract y part 1 +%if mmsize < 32 RSHIFT_COPY m6, m2, 1 ; UYVY UYVY -> YVYU YVY... pand m6, m1; YxYx YxYx... RSHIFT_COPY m7, m3, 1 ; UYVY UYVY -> YVYU YVY... pand m7, m1 ; YxYx YxYx... - packuswb m6, m7 ; YYYY YYYY... +%else + pshufb m6, m2, m13 + pshufb m7, m3, m13 + punpcklqdq m6, m6, m7 + VPERM q, 32, m6, m6, 0xd8 +%endif movu [ydstq + wq], m6 ; extract y part 2 +%if mmsize < 32 RSHIFT_COPY m6, m4, 1 ; UYVY UYVY -> YVYU YVY... pand m6, m1; YxYx YxYx... RSHIFT_COPY m7, m5, 1 ; UYVY UYVY -> YVYU YVY... pand m7, m1 ; YxYx YxYx... - - packuswb m6, m7 ; YYYY YYYY... + packuswb m6, m7 ; YYYY YYYY... +%else + pshufb m6, m4, m13 + pshufb m7, m5, m13 + punpcklqdq m6, m6, m7 + VPERM q, 32, m6, m6, 0xd8 +%endif movu [ydstq + wq + mmsize], m6 ; extract uv @@ -275,17 +300,21 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s packuswb m4, m5 ; UVUV... ; U - pand m6, m2, m1 ; UxUx... - pand m7, m4, m1 ; UxUx... + pand m6, m2, m1 ; UxUx... + pand m7, m4, m1 ; UxUx... + packuswb m6, m7 ; UUUU - packuswb m6, m7 ; UUUU - movu [udstq + whalfq], m6 + VPERM d, 32, m6, m15, m6 + movu [udstq + whalfq], m6 ; V - psrlw m2, 8 ; VxVx... - psrlw m4, 8 ; VxVx... - packuswb m2, m4 ; VVVV + psrlw m2, 8 ; VxVx... + psrlw m4, 8 ; VxVx... + packuswb m2, m4 ; VVVV + + VPERM d, 32, m2, m15, m2 + movu [vdstq + whalfq], m2 add whalfq, mmsize @@ -294,13 +323,13 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s jl .loop_simd .end_line: - add srcq, src_strideq + add srcq, src_strideq add ydstq, lum_strideq add udstq, chrom_strideq add vdstq, chrom_strideq ;restore initial state of line variable - mov wq, back_wq + mov wq, back_wq mov xq, wq mov whalfq, wq shr whalfq, 1 ; whalf = width / 2 @@ -316,4 +345,9 @@ UYVY_TO_YUV422 INIT_XMM avx UYVY_TO_YUV422 + +%if HAVE_AVX2_EXTERNAL +INIT_YMM avx2 +UYVY_TO_YUV422 +%endif %endif From patchwork Thu Sep 30 08:43:55 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wu Jianhua X-Patchwork-Id: 30683 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a6b:6506:0:0:0:0:0 with SMTP id z6csp436571iob; Thu, 30 Sep 2021 01:44:30 -0700 (PDT) X-Google-Smtp-Source: ABdhPJz7h7myTd3g854mdBZecFfXjwiZ/ufR7QMx6XkqCaSyYuwYGU9ewwpGJa8PZt/v6Vs4a5Z9 X-Received: by 2002:a17:906:3a0f:: with SMTP id z15mr5489513eje.42.1632991470792; Thu, 30 Sep 2021 01:44:30 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1632991470; cv=none; d=google.com; s=arc-20160816; b=t019YdG4Lz9mRxFDZj0sNw2Cz+Nl7QuBGQ/BD+yCV7edJOcwTBUiYjeQVTCi2vqHyE OMa9o679UdIrZtWxXVn5gil9PYA/enEeLgnApu27PPf62vBBlycbJHLo+RoyLRJrUe/q ud9fwFBj9OQzsHeKi7wkJm5HhOuMdv4TUjypyVxmj2POm9BUZfXXrB5hmJJguqCABjtO 4Xyq7azb7mehF3KF6aBPuIdZTemeTl2Md9zHAKHdjTi8cdD2do/u+8xybxbnW06kxz4H Co8etrKfYkeM4j9HP2wul4qKqmU/XWu3E8InNlVu3hKkVwPedDDLmzOsdfAJT2vQT+zX qhLQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:references:in-reply-to:message-id:date :to:from:delivered-to; bh=p0L96rRnDe7IEuF4qY6SGIMPHQimEWM1gI/yy3Si/M0=; b=vQp/6AmmXq31L0sC3+2h12IF5bzBYMM/9cFqnoqvozWRsUxZ2LnvspaCAycNA0abRm IH/LJ9qrh8rm5B7F1TP63kExx0m7T4kDfdwvAUaI5uPUBvyPS5jC/TtKxehv3WIdjPH8 othTsM5nTOoXggsAoluxcudxSANXgR8TzIvcc6ZPzEfUxu92rr3djVg446yCaxIJk++q gTFg9/8OyEtBOEqv/TyR5gXWOnYw18Pb8lwiRWrimwj3BXAyrHbfL//J538jm8b0kvH5 WzWdDKcMP90nvzKdkEY6NLMV99FP1h8SNEoijg0eUF8k28Y5+yy3bvQK+tY3NUDZfphY prCw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id 14si2717712ejj.313.2021.09.30.01.44.30; Thu, 30 Sep 2021 01:44:30 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 8B76668A329; Thu, 30 Sep 2021 11:44:20 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 0206B680610 for ; Thu, 30 Sep 2021 11:44:12 +0300 (EEST) X-IronPort-AV: E=McAfee;i="6200,9189,10122"; a="224793905" X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="224793905" Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2021 01:44:02 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.85,335,1624345200"; d="scan'208";a="563956892" Received: from otc-skl-e5-server.sh.intel.com ([10.239.43.106]) by fmsmga002.fm.intel.com with ESMTP; 30 Sep 2021 01:44:01 -0700 From: Wu Jianhua To: ffmpeg-devel@ffmpeg.org Date: Thu, 30 Sep 2021 16:43:55 +0800 Message-Id: <20210930084355.76628-4-jianhua.wu@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20210930084355.76628-1-jianhua.wu@intel.com> References: <20210930084355.76628-1-jianhua.wu@intel.com> Subject: [FFmpeg-devel] [PATCH v3 4/4] With the accelerating by means of AVX512, the uyvytoyuv422 can be faster. X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: Wu Jianhua MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: mDZ7rBk7hnFM Performance data(Less is better): uyvytoyuv422_avx2 0.27309 uyvytoyuv422_avx512 0.16229 Signed-off-by: Wu Jianhua --- libswscale/x86/rgb2rgb.c | 6 ++++++ libswscale/x86/rgb_2_rgb.asm | 20 ++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index a965a1755c..c59136a352 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -167,6 +167,9 @@ void ff_uyvytoyuv422_avx(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, void ff_uyvytoyuv422_avx2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src, int width, int height, int lumStride, int chromStride, int srcStride); +void ff_uyvytoyuv422_avx512(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, + const uint8_t *src, int width, int height, + int lumStride, int chromStride, int srcStride); #endif av_cold void rgb2rgb_init_x86(void) @@ -222,5 +225,8 @@ av_cold void rgb2rgb_init_x86(void) if (EXTERNAL_AVX2_FAST(cpu_flags)) { uyvytoyuv422 = ff_uyvytoyuv422_avx2; } + if (EXTERNAL_AVX512(cpu_flags)) { + uyvytoyuv422 = ff_uyvytoyuv422_avx512; + } #endif } diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm index 1777a99faf..d55d2ca07f 100644 --- a/libswscale/x86/rgb_2_rgb.asm +++ b/libswscale/x86/rgb_2_rgb.asm @@ -31,8 +31,10 @@ pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13 pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12 pb_shuffle3012: db 3, 0, 1, 2, 7, 4, 5, 6, 11, 8, 9, 10, 15, 12, 13, 14 pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 +pd_permd512_uv: dd 0, 4, 8, 12, 1, 5, 9, 13, 2, 6, 10, 14, 3, 7, 11, 15 pb_shuffle_low: db 1, 3, 5, 7, 9, 11, 13, 15 pd_permd256_uv: dd 0, 4, 1, 5, 2, 6, 3, 7 +pq_permq512_yy: dq 0, 2, 4, 6, 1, 3, 5, 7 SECTION .text @@ -194,7 +196,11 @@ SHUFFLE_BYTES 3, 2, 1, 0 %macro UYVY_TO_YUV422 0 cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_stride, src_stride, wtwo, whalf, tmp, x, back_w pxor m0, m0 +%if mmsize == 64 + vpternlogd m1, m1, m1, 0xff +%else pcmpeqw m1, m1 +%endif psrlw m1, 8 movsxdifnidn wq, wd @@ -213,7 +219,12 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s %if mmsize > 16 vpbroadcastq m13, [pb_shuffle_low] +%if mmsize == 32 movu m15, [pd_permd256_uv] +%else + movu m14, [pq_permq512_yy] + movu m15, [pd_permd512_uv] +%endif %endif .loop_line: @@ -271,6 +282,7 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s pshufb m7, m3, m13 punpcklqdq m6, m6, m7 VPERM q, 32, m6, m6, 0xd8 + VPERM q, 64, m6, m14, m6 %endif movu [ydstq + wq], m6 @@ -287,6 +299,7 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s pshufb m7, m5, m13 punpcklqdq m6, m6, m7 VPERM q, 32, m6, m6, 0xd8 + VPERM q, 64, m6, m14, m6 %endif movu [ydstq + wq + mmsize], m6 @@ -305,6 +318,7 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s packuswb m6, m7 ; UUUU VPERM d, 32, m6, m15, m6 + VPERM d, 64, m6, m15, m6 movu [udstq + whalfq], m6 @@ -314,6 +328,7 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s packuswb m2, m4 ; VVVV VPERM d, 32, m2, m15, m2 + VPERM d, 64, m2, m15, m2 movu [vdstq + whalfq], m2 @@ -350,4 +365,9 @@ UYVY_TO_YUV422 INIT_YMM avx2 UYVY_TO_YUV422 %endif + +%if HAVE_AVX512_EXTERNAL +INIT_ZMM avx512 +UYVY_TO_YUV422 +%endif %endif