From patchwork Thu Dec 1 16:57:48 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Darnley X-Patchwork-Id: 1645 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.103.65.86 with SMTP id o83csp1049911vsa; Thu, 1 Dec 2016 09:12:07 -0800 (PST) X-Received: by 10.194.59.71 with SMTP id x7mr40522642wjq.74.1480612327650; Thu, 01 Dec 2016 09:12:07 -0800 (PST) Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id x6si976546wjk.170.2016.12.01.09.12.07; Thu, 01 Dec 2016 09:12:07 -0800 (PST) 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; dkim=neutral (body hash did not verify) header.i=@ob-encoder-com.20150623.gappssmtp.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 Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id DDA1D689F42; Thu, 1 Dec 2016 19:11:56 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-wm0-f68.google.com (mail-wm0-f68.google.com [74.125.82.68]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 40A35689F2C for ; Thu, 1 Dec 2016 19:11:50 +0200 (EET) Received: by mail-wm0-f68.google.com with SMTP id m203so35145345wma.3 for ; Thu, 01 Dec 2016 09:11:58 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ob-encoder-com.20150623.gappssmtp.com; s=20150623; h=sender:from:to:subject:date:message-id:in-reply-to:references; bh=JCiEOI+2MTaAQZxsKxatOjxqwgBF3mbZItCfR+sP7x4=; b=Tj0BTuuf0hNcTgOfUx1iHXX/4zrvNrD7fkaXeDopAZ8JNVOQxCitj3FLqh6rAv3QzS 8o4SjN8k8a3DhbEciyFRgm8YVJYtA0ufuWnvRG0FVBcWYdXJ4dIaytmVjt3Y5ZMJI2YD Gcd3A0XJ7G1XC87O77cx6XLNM7WrxSE3APcDEb+Bl9PKi0+PIhpawg3zosBYN5VFZPoH d0q4uvGiS45u6v3glk2wo2rOOOZG18GeaJ4KMfngwp2PgwilfU68hAO248dZJcSBZs+s Afhtgpk2tGGq14Fwy5b1GhZXI3nK6gtltDzibuB8KOB79qgq3VMNRLkyJVQ3tGvaL1U+ +FIg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:sender:from:to:subject:date:message-id :in-reply-to:references; bh=JCiEOI+2MTaAQZxsKxatOjxqwgBF3mbZItCfR+sP7x4=; b=bc29RTJBVqP+KZ6DMZi4ixpQLbt0Nj7MrR15r+27fvoVTGuALI1YmBHzgaOzD6K+4o Jzp7iWkzACc2aGUpJYjzQaUtw7rCqQAGxkHROsvokeKrhTOeBtPaS6oq/shl3Ga+oSXu OAwWXb1VSLsTvlD3RmtGL7laaFgsxwDnvRre8rtaPIJuTPFiw5aq7lNDkZypN5497qhR pwjP9FZ7vs8aeGRDJK4EoMCKCjguH15wpY2t156cYwPxIqEurf/WUw/iSr6CLuIIWgNy ubHgLeV5B1ZCBJMbsUMyhYYjayueWCFU6AeuDwOKSTlE1MqRnT7QzdGc9nkzKKS9r6Tl DmHA== X-Gm-Message-State: AKaTC02xe8eC8lb9XOr7L6vuZX8gR+o4q/uOxEzOhmNKLOazdjg2Z/OPJGkf7a9Fjeb7Sg== X-Received: by 10.28.45.212 with SMTP id t203mr35012803wmt.46.1480611593234; Thu, 01 Dec 2016 08:59:53 -0800 (PST) Received: from Ifrit.systemlords.lan (d51a44418.access.telenet.be. [81.164.68.24]) by smtp.gmail.com with ESMTPSA id kp5sm1206172wjb.8.2016.12.01.08.59.52 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 01 Dec 2016 08:59:52 -0800 (PST) From: James Darnley To: FFmpeg development discussions and patches Date: Thu, 1 Dec 2016 17:57:48 +0100 Message-Id: <20161201165749.10368-6-jdarnley@obe.tv> X-Mailer: git-send-email 2.10.2 In-Reply-To: <20161201165749.10368-1-jdarnley@obe.tv> References: <20161201165749.10368-1-jdarnley@obe.tv> Subject: [FFmpeg-devel] [PATCH 5/6] avcodec/h264: mmx2, sse2, avx 10-bit h chroma intra deblock/loop filter X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.20 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 MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Yorkfield: - mmx2: 0.99x faster (180 vs. 181 cycles) - sse2: 1.05x faster (180 vs. 170 cycles) Skylake: - mmx2: 1.21x faster (125 vs. 103 cycles) - sse2: 1.54x faster (125 vs. 81 cycles) - avx: 1.29x faster (125 vs. 97 cycles) --- libavcodec/x86/h264_deblock_10bit.asm | 29 +++++++++++++++++++++++++++++ libavcodec/x86/h264dsp_init.c | 3 +++ 2 files changed, 32 insertions(+) diff --git a/libavcodec/x86/h264_deblock_10bit.asm b/libavcodec/x86/h264_deblock_10bit.asm index 4c1dc6a..fb10bfb 100644 --- a/libavcodec/x86/h264_deblock_10bit.asm +++ b/libavcodec/x86/h264_deblock_10bit.asm @@ -1071,6 +1071,35 @@ cglobal deblock_h_chroma422_10, 5, 7, 8, 3*mmsize, pix_, stride_, alpha_, beta_, jl .loop RET +;----------------------------------------------------------------------------- +; void ff_deblock_h_chroma_intra_10(uint16_t *pix, int stride, int alpha, +; int beta) +;----------------------------------------------------------------------------- +cglobal deblock_h_chroma_intra_10, 4, 6, 8, 2*mmsize, pix_, stride_, alpha_, beta_ + shl alpha_d, 2 + shl beta_d, 2 + mov r4, pix_q + lea r5, [3*stride_q] + add r4, r5 +%if mmsize == 8 + mov r5b, 2 + .loop: +%endif + + CHROMA_H_LOAD r4, r5, [rsp], [rsp + mmsize] + LOAD_AB m4, m5, alpha_d, beta_d + LOAD_MASK m0, m1, m2, m3, m4, m5, m7, m6, m4 + CHROMA_DEBLOCK_P0_Q0_INTRA m1, m2, m0, m3, m7, m5, m6 + CHROMA_H_STORE r4, r5, [rsp], [rsp + mmsize] + +%if mmsize == 8 + lea pix_q, [pix_q + 4*stride_q] + lea r4, [r4 + 4*stride_q] + dec r5b + jg .loop +%endif +RET + %endmacro %if ARCH_X86_64 == 0 diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c index 7b3d17f..395b8c3 100644 --- a/libavcodec/x86/h264dsp_init.c +++ b/libavcodec/x86/h264dsp_init.c @@ -315,6 +315,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_v_loop_filter_chroma_intra = ff_deblock_v_chroma_intra_10_mmxext; if (chroma_format_idc <= 1) { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma_10_mmxext; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma_intra_10_mmxext; } else { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma422_10_mmxext; } @@ -353,6 +354,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_v_loop_filter_chroma_intra = ff_deblock_v_chroma_intra_10_sse2; if (chroma_format_idc <= 1) { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma_10_sse2; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma_intra_10_sse2; } else { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma422_10_sse2; } @@ -393,6 +395,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_v_loop_filter_chroma_intra = ff_deblock_v_chroma_intra_10_avx; if (chroma_format_idc <= 1) { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma_10_avx; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma_intra_10_avx; } else { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma422_10_avx; }