From patchwork Thu Dec 1 16:57:49 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Darnley X-Patchwork-Id: 1646 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.103.65.86 with SMTP id o83csp1050915vsa; Thu, 1 Dec 2016 09:13:56 -0800 (PST) X-Received: by 10.194.236.135 with SMTP id uu7mr34798172wjc.195.1480612436369; Thu, 01 Dec 2016 09:13:56 -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 lg5si992330wjc.131.2016.12.01.09.13.55; Thu, 01 Dec 2016 09:13:56 -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 C7D7F689F6C; Thu, 1 Dec 2016 19:13:45 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-wm0-f66.google.com (mail-wm0-f66.google.com [74.125.82.66]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 3D117689F3D for ; Thu, 1 Dec 2016 19:13:40 +0200 (EET) Received: by mail-wm0-f66.google.com with SMTP id u144so35126214wmu.0 for ; Thu, 01 Dec 2016 09:13:48 -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=WGUWPN27oz91d04lGqPONGr4VSUaLYuBhKy2wAytYp0=; b=Tpb+Wy+7DKGcvxEWqAKs1wpEWIgeS6p9OSLgVe1Sk6/vRfqZFXGCNVbe83UGBKmBV0 BUMk+ZDVHEBjDZXHNITikTVcxZooArkbspTYNe9ngMQgQx7k4/Oq1h+rxIOh1Y20vYRy pnDFk4Bw+Ec1/P0guQYEYXo2ZFf5kiI/ohPVrkwaBnuS42k3y0eIy/xAuE97/IG+ZCux bTbFMUGhsNRsfEXi7uHE7UOefxvK0eo7J1iYAH+6odf62sUhzk+DRgj4gA1QI3vIEu5U SpgsgGUodzK53ikDvNpE8Gf0VvMneSUrNBW6YZE3sbhbKxaq2xMm08hOkgDp03JP03sn TdMg== 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=WGUWPN27oz91d04lGqPONGr4VSUaLYuBhKy2wAytYp0=; b=Tq5JNozaOi+BdYDpgpglS01E8Zxrz3WvHm5Bxl34U3F6PY4/XD/z9MPg7VokbtYwXs rhkIiAN4pun9wH8Fgo0U60RjdUgfrerHCpIwZ6DfUFxuSskQdWdLh6PdIpnk7qdMx2Iq iSqhExGwPl6RgcGPPatjVBwdVADNp19e82ltLBFv9JIBGwyc8L5+QZ3I1+lTCaXF/Ui3 QJqt9NaYZIW2NDaQ36RmV8M8vj5D/y4bMAn81+bzsCMKUGfN2BzVVtJK7LQSfmqVNYhC JoiCMNDH7X06p3TsVkROz4APGmLMMo1cT7xZFIpHcSI6tnXrtMceUSHAgYeJnrPXNHBE NAHw== X-Gm-Message-State: AKaTC03S8FtqXCmpOocZDACmtRAGeieH7oKo198pqpL0WK+f3ZUz5PFDVHONis8BDKy5Xw== X-Received: by 10.28.12.80 with SMTP id 77mr36257753wmm.106.1480611593810; 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.8.2016.12.01.08.59.53 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 01 Dec 2016 08:59:53 -0800 (PST) From: James Darnley To: FFmpeg development discussions and patches Date: Thu, 1 Dec 2016 17:57:49 +0100 Message-Id: <20161201165749.10368-7-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 6/6] avcodec/h264: mmx2, sse2, avx 10-bit 4:2:2 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: 1.21x faster (370 vs. 306 cycles) - sse2: 1.20x faster (370 vs. 308 cycles) Skylake: - mmx2: 1.39x faster (240 vs. 172 cycles) - sse2: 1.74x faster (240 vs. 138 cycles) - avx: 1.78x faster (240 vs. 134 cycles) --- libavcodec/x86/h264_deblock_10bit.asm | 27 +++++++++++++++++++++++++++ libavcodec/x86/h264dsp_init.c | 3 +++ 2 files changed, 30 insertions(+) diff --git a/libavcodec/x86/h264_deblock_10bit.asm b/libavcodec/x86/h264_deblock_10bit.asm index fb10bfb..8832210 100644 --- a/libavcodec/x86/h264_deblock_10bit.asm +++ b/libavcodec/x86/h264_deblock_10bit.asm @@ -1100,6 +1100,33 @@ cglobal deblock_h_chroma_intra_10, 4, 6, 8, 2*mmsize, pix_, stride_, alpha_, bet %endif RET +;----------------------------------------------------------------------------- +; void ff_deblock_h_chroma422_intra_10(uint16_t *pix, int stride, int alpha, +; int beta) +;----------------------------------------------------------------------------- +cglobal deblock_h_chroma422_intra_10, 4, 7, 8, 2*mmsize, pix_, stride_, alpha_, beta_ + shl alpha_d, 2 + shl beta_d, 2 + + mov r5, pix_q + lea r6, [3*stride_q] + add r5, r6 + + mov r4, -8 + .loop: + + CHROMA_H_LOAD r5, r6, [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 r5, r6, [rsp], [rsp + mmsize] + + lea pix_q, [pix_q + (mmsize/2)*stride_q] + lea r5, [r5 + (mmsize/2)*stride_q] + add r4, (mmsize/4) + jl .loop +RET + %endmacro %if ARCH_X86_64 == 0 diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c index 395b8c3..8154cd9 100644 --- a/libavcodec/x86/h264dsp_init.c +++ b/libavcodec/x86/h264dsp_init.c @@ -318,6 +318,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, 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; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma422_intra_10_mmxext; } c->h264_v_loop_filter_luma = ff_deblock_v_luma_10_mmxext; c->h264_h_loop_filter_luma = ff_deblock_h_luma_10_mmxext; @@ -357,6 +358,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, 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; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma422_intra_10_sse2; } #if HAVE_ALIGNED_STACK c->h264_v_loop_filter_luma = ff_deblock_v_luma_10_sse2; @@ -398,6 +400,7 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, 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; + c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma422_intra_10_avx; } #if HAVE_ALIGNED_STACK c->h264_v_loop_filter_luma = ff_deblock_v_luma_10_avx;