From patchwork Mon Feb 20 15:33:21 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Darnley X-Patchwork-Id: 2616 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.103.89.22 with SMTP id n22csp12447vsb; Mon, 20 Feb 2017 07:42:11 -0800 (PST) X-Received: by 10.223.138.183 with SMTP id y52mr9011175wry.190.1487605330352; Mon, 20 Feb 2017 07:42:10 -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 y141si12759869wmc.96.2017.02.20.07.42.08; Mon, 20 Feb 2017 07:42:10 -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 54101689C81; Mon, 20 Feb 2017 17:41:56 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-wm0-f65.google.com (mail-wm0-f65.google.com [74.125.82.65]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 6D3B8689C23 for ; Mon, 20 Feb 2017 17:41:50 +0200 (EET) Received: by mail-wm0-f65.google.com with SMTP id r18so15041177wmd.3 for ; Mon, 20 Feb 2017 07:41:58 -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=0H5iILhAWph0d7Kr+tSBGtFp5rZqhgmGZfLKi6KndNQ=; b=GpjbsIAj1uH028OtwbaOtRADPbv+/LzStZMY/l4L6Pag3BD8lS7nLTXseoVOmFlZWT mOQvCYrmh2ZJKgcWlg/JuF2iDGdximTduxXjNqISW+Rzm/NoQ1HWpUmLIgyBMxQ3RYRe vVQOLqpHbv9YqW4c5ZT/fDaWNssXRLlywLhy0jCyIKJsQ7m3nPXAkA7v+qKFg8G5jOE2 4zpWoVzjHlCtBP1FaaQNkHo63A9bkYXG1KLK6MAwOGEKbyRT45pdyzX6n99vMIgL+omr S4xMJbvzm3cp5sCIYliEBZgTMUZanM8Dqg/BYxz1lVS8ze3HwC4j5leqD8ICI8Fhj9FS irjg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:subject:date:message-id :in-reply-to:references; bh=0H5iILhAWph0d7Kr+tSBGtFp5rZqhgmGZfLKi6KndNQ=; b=KkBCGrPkQboiQhOFj/spbVtfjQsLX/myRXVo/n5kbVyJrgENB3HuSVKOS2txvyVQJR 0k5fDTgceKM1yTPizskyfGtvKwVZCHNM0DZIQLXoKjXK71dNeI10Sm9Rt+VR/z7Q6DWw ix30jtu0lTD/LODWt4kmAu7FVjB+ya0OLZFDOrPwie+Z8OT3GysG5QTP78LRR+KKvSbl GD+p84TwwcED50TmBKiMo+lCCR8f5g3geNQVfX9eW4uC9++lplOBiVQNZNpFcC5Pc4EI WTKj6HY8s6XJNmmvqgqahH4XVpei9SxCuWyUbPN/WvluIAArPAHrm/2QA41ibSpSfOeC lhHA== X-Gm-Message-State: AMke39kqfL0MRNwCHXwJ1Lm6s49WXQgj5Lb4vo1UcHDM54XqbEZc2daoJ6pK15kZxwvFPA== X-Received: by 10.28.170.19 with SMTP id t19mr18122327wme.31.1487604834141; Mon, 20 Feb 2017 07:33:54 -0800 (PST) Received: from localhost.localdomain (d51A44418.access.telenet.be. [81.164.68.24]) by smtp.gmail.com with ESMTPSA id c133sm13865977wmd.13.2017.02.20.07.33.53 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 20 Feb 2017 07:33:53 -0800 (PST) From: James Darnley To: FFmpeg development discussions and patches Date: Mon, 20 Feb 2017 16:33:21 +0100 Message-Id: <20170220153324.1732-4-jdarnley@obe.tv> X-Mailer: git-send-email 2.8.3 In-Reply-To: <20170220153324.1732-1-jdarnley@obe.tv> References: <20170220153324.1732-1-jdarnley@obe.tv> Subject: [FFmpeg-devel] [PATCH 3/6] avcodec/h264: add avx 8-bit 4:2:2 chroma h 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" ~1.21x faster (68 vs. 56 cycles) compared with mmxext function --- libavcodec/x86/h264_deblock.asm | 27 +++++++++++++++++++++++++++ libavcodec/x86/h264dsp_init.c | 2 ++ 2 files changed, 29 insertions(+) diff --git a/libavcodec/x86/h264_deblock.asm b/libavcodec/x86/h264_deblock.asm index 0465c9f..e2eb002 100644 --- a/libavcodec/x86/h264_deblock.asm +++ b/libavcodec/x86/h264_deblock.asm @@ -1163,6 +1163,33 @@ cglobal deblock_h_chroma_8, 5, 7, 8, 0-16, pix_, stride_, alpha_, beta_, tc0_ STORE_8_ROWS PASS8ROWS(pix_q - 2, r5 - 2, stride_q, r6) RET +cglobal deblock_h_chroma422_8, 5, 7, 8, 0-16, pix_, stride_, alpha_, beta_, tc0_, + CHROMA_H_START_XMM r5, r6 + LOAD_8_ROWS PASS8ROWS(pix_q - 2, r5 - 2, stride_q, r6) + TRANSPOSE_8x4B_XMM + movq [rsp], m0 + movq [rsp + 8], m3 + CHROMA_INTER_BODY_XMM 2 + movq m0, [rsp] + movq m3, [rsp + 8] + TRANSPOSE_4x8B_XMM + STORE_8_ROWS PASS8ROWS(pix_q - 2, r5 - 2, stride_q, r6) + + lea pix_q, [pix_q + 8*stride_q] + lea r5, [r5 + 8*stride_q] + add tc0_q, 2 + + LOAD_8_ROWS PASS8ROWS(pix_q - 2, r5 - 2, stride_q, r6) + TRANSPOSE_8x4B_XMM + movq [rsp], m0 + movq [rsp + 8], m3 + CHROMA_INTER_BODY_XMM 2 + movq m0, [rsp] + movq m3, [rsp + 8] + TRANSPOSE_4x8B_XMM + STORE_8_ROWS PASS8ROWS(pix_q - 2, r5 - 2, stride_q, r6) +RET + %endmacro ; DEBLOCK_CHROMA_XMM DEBLOCK_CHROMA_XMM avx diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c index 0b15471..6073932 100644 --- a/libavcodec/x86/h264dsp_init.c +++ b/libavcodec/x86/h264dsp_init.c @@ -321,6 +321,8 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_v_loop_filter_chroma = ff_deblock_v_chroma_8_avx; if (chroma_format_idc <= 1) { c->h264_h_loop_filter_chroma = ff_deblock_h_chroma_8_avx; + } else { + c->h264_h_loop_filter_chroma = ff_deblock_h_chroma422_8_avx; } } } else if (bit_depth == 10) {