From patchwork Mon Feb 13 12:44:17 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Darnley X-Patchwork-Id: 2540 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.103.89.21 with SMTP id n21csp894845vsb; Mon, 13 Feb 2017 04:55:28 -0800 (PST) X-Received: by 10.28.111.220 with SMTP id c89mr17982035wmi.102.1486990528794; Mon, 13 Feb 2017 04:55:28 -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 186si5404250wmx.129.2017.02.13.04.55.28; Mon, 13 Feb 2017 04:55:28 -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 A9CCA68921C; Mon, 13 Feb 2017 14:55:17 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-wr0-f196.google.com (mail-wr0-f196.google.com [209.85.128.196]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 9C8C06802F0 for ; Mon, 13 Feb 2017 14:55:11 +0200 (EET) Received: by mail-wr0-f196.google.com with SMTP id i10so24043436wrb.0 for ; Mon, 13 Feb 2017 04:55:16 -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=X5kjEBBiSE4GDi+1V1+JzSxdstySx9qCqyDOKSkGiZA=; b=dc/vOrI4TuUfDjgCGhIRAiJPMn5ZT1/P3qlhptII3TWT5SWKhsthi3MHXElGggHTgg KYiWpxm7E3JnmaJ18trV8WWnfOlO7c8T42P94D6wX8fP/yGRqapCk0WK66kOTnmlISuT kgoKgyoYhhrSjonlJZWH6pVIJVLBzeXJSX+LVJYxHKzB0U0sCM76WEl1pq21Qd46/OEW jvz25b82lSOnrBHk6pZho8XE6jheEt8gzEguYCnJBK0Boe5v10mbdFsFDiDAME40mArr KrgIJbOSeEIDQmuMAIWYWJkGKIc3AbK543c66a1GJRxHNdwDWn8twdgv8N9iMO688CiU gDyw== 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=X5kjEBBiSE4GDi+1V1+JzSxdstySx9qCqyDOKSkGiZA=; b=O0zju5goBv4IH0O8yrG8a4eO8UPjqG/5EW+/eLRkwC+G9Vu/FvC18N2CRnehbOTMt2 xgCFHgsFZ0zz49Tp3jj90BhIPF04egA+7P1e8IZgLTMGdXayOLBQi9JYtjyALVlu85o7 qR2cWeFbTATeZ+fNZFrX65gaZXuNbsi3Nxm892+VNGFbPPMPkEl32zk46yYx1tTu+ji/ tmu2mDs3GZcyG3DFw8FAC21SGVhirexpL6rFyGa9PkYIHCLuAYWTfiJ4CmkJR0AEiZwT xNuP/TgkoQF6Gw3wMU+5DTjEDqIFubL9a/9NCEsjVZuiFJKTC/7esUeY8/8UEKk1twxT IMZQ== X-Gm-Message-State: AMke39kWHqMnqieAQP9ILaTvfrvWTUMZyJwxj108Bg91tmyjlBgAIMQVh9zTHhUiuLIh+g== X-Received: by 10.223.136.16 with SMTP id d16mr21261770wrd.117.1486990047742; Mon, 13 Feb 2017 04:47:27 -0800 (PST) Received: from Ifrit.systemlords.lan (d51a44418.access.telenet.be. [81.164.68.24]) by smtp.gmail.com with ESMTPSA id 10sm13778137wrw.13.2017.02.13.04.47.26 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 13 Feb 2017 04:47:27 -0800 (PST) From: James Darnley To: FFmpeg development discussions and patches Date: Mon, 13 Feb 2017 13:44:17 +0100 Message-Id: <20170213124417.25808-4-jdarnley@obe.tv> X-Mailer: git-send-email 2.11.1 In-Reply-To: <20170213124417.25808-1-jdarnley@obe.tv> References: <20170213124417.25808-1-jdarnley@obe.tv> Subject: [FFmpeg-devel] [PATCH 4/4] avcodec/h264: sse2, avx h luma mbaff 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" x86-64 only Yorkfield: - sse2: 2.16x (434 vs. 201 cycles) Skylake: - sse2: 3.04x (378 vs. 124 cycles) - avx: 3.29x (378 vs. 115 cycles) --- libavcodec/x86/h264_deblock.asm | 119 ++++++++++++++++++++++++++++++++++++++++ libavcodec/x86/h264dsp_init.c | 10 ++++ 2 files changed, 129 insertions(+) diff --git a/libavcodec/x86/h264_deblock.asm b/libavcodec/x86/h264_deblock.asm index 509a0dbe0c..f47a199e8f 100644 --- a/libavcodec/x86/h264_deblock.asm +++ b/libavcodec/x86/h264_deblock.asm @@ -377,10 +377,129 @@ cglobal deblock_h_luma_8, 5,9,0,0x60+16*WIN64 RET %endmacro +; TODO: use macro arguments +%macro TRANSPOSE_8X8B_XMM 8 + punpcklbw m0, m1 + punpcklbw m2, m3 + punpcklbw m4, m5 + punpcklbw m6, m7 + + punpckhwd m1, m0, m2 + punpcklwd m0, m2 + + punpckhwd m5, m4, m6 + punpcklwd m4, m6 + + punpckhdq m2, m0, m4 + punpckldq m0, m4 + + punpckhdq m6, m1, m5 + punpckldq m1, m5 + + MOVHL m4, m0 + MOVHL m3, m2 + MOVHL m7, m6 + MOVHL m5, m1 + SWAP 1, 4 +%endmacro + +%macro TRANSPOSE_8X8B_XMM 0 + TRANSPOSE_8X8B_XMM 0, 1, 2, 3, 4, 5, 6, 7 +%endmacro + +%macro DEBLOCK_H_LUMA_MBAFF 0 + +cglobal deblock_h_luma_mbaff_8, 5, 9, 10, 8*16, pix_, stride_, alpha_, beta_, tc0_ + movsxd stride_q, stride_d + dec alpha_d + dec beta_d + mov r5, pix_q + lea r6, [3*stride_q] + add r5, r6 + + movq m0, [pix_q - 4] + movq m1, [pix_q + stride_q - 4] + movq m2, [pix_q + 2*stride_q - 4] + movq m3, [r5 - 4] + movq m4, [r5 + stride_q - 4] + movq m5, [r5 + 2*stride_q - 4] + movq m6, [r5 + r6 - 4] + movq m7, [r5 +4*stride_q - 4] + + TRANSPOSE_8X8B_XMM + + %assign i 0 + %rep 8 + movq [rsp + 16*i], m %+ i + %assign i i+1 + %endrep + + ; p2 = m1 [rsp + 16] + ; p1 = m2 [rsp + 32] + ; p0 = m3 [rsp + 48] + ; q0 = m4 [rsp + 64] + ; q1 = m5 [rsp + 80] + ; q2 = m6 [rsp + 96] + + SWAP 0, 2 + SWAP 1, 3 + SWAP 2, 4 + SWAP 3, 5 + + LOAD_MASK alpha_d, beta_d + movd m8, [tc0_q] + punpcklbw m8, m8 + pcmpeqb m9, m9 + pcmpeqb m9, m8 + pandn m9, m7 + pand m8, m9 + + movdqa m3, [rsp + 16] ; p2 + DIFF_GT2 m1, m3, m5, m6, m7 ; |p2-p0| > beta-1 + pand m6, m9 + psubb m7, m8, m6 + pand m6, m8 + LUMA_Q1 m0, m3, [rsp + 16], [rsp + 32], m6, m4 + + movdqa m4, [rsp + 96] ; q2 + DIFF_GT2 m2, m4, m5, m6, m3 ; |q2-q0| > beta-1 + pand m6, m9 + pand m8, m6 + psubb m7, m6 + mova m3, [rsp + 80] + LUMA_Q1 m3, m4, [rsp + 96], [rsp + 80], m8, m6 + + DEBLOCK_P0_Q0 + SWAP 1, 3 + SWAP 2, 4 + movq m0, [rsp] + movq m1, [rsp + 16] + movq m2, [rsp + 32] + movq m5, [rsp + 80] + movq m6, [rsp + 96] + movq m7, [rsp + 112] + + TRANSPOSE_8X8B_XMM + movq [pix_q - 4], m0 + movq [pix_q + stride_q - 4], m1 + movq [pix_q + 2*stride_q - 4], m2 + movq [r5 - 4], m3 + movq [r5 + stride_q - 4], m4 + movq [r5 + 2*stride_q - 4], m5 + movq [r5 + r6 - 4], m6 + movq [r5 +4*stride_q - 4], m7 + +RET + +%endmacro + INIT_XMM sse2 +DEBLOCK_H_LUMA_MBAFF DEBLOCK_LUMA + %if HAVE_AVX_EXTERNAL INIT_XMM avx +DEBLOCK_H_LUMA_MBAFF DEBLOCK_LUMA %endif diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c index 7b3d17f971..10f19401ef 100644 --- a/libavcodec/x86/h264dsp_init.c +++ b/libavcodec/x86/h264dsp_init.c @@ -137,6 +137,9 @@ LF_IFUNC(h, chroma422_intra, depth, avx) \ LF_FUNC(v, chroma, depth, avx) \ LF_IFUNC(v, chroma_intra, depth, avx) +LF_FUNC(h, luma_mbaff, 8, sse2) +LF_FUNC(h, luma_mbaff, 8, avx) + LF_FUNCS(uint8_t, 8) LF_FUNCS(uint16_t, 10) @@ -297,6 +300,10 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_h_loop_filter_luma = ff_deblock_h_luma_8_sse2; c->h264_v_loop_filter_luma_intra = ff_deblock_v_luma_intra_8_sse2; c->h264_h_loop_filter_luma_intra = ff_deblock_h_luma_intra_8_sse2; + +#if ARCH_X86_64 + c->h264_h_loop_filter_luma_mbaff = ff_deblock_h_luma_mbaff_8_sse2; +#endif } if (EXTERNAL_SSSE3(cpu_flags)) { c->biweight_h264_pixels_tab[0] = ff_h264_biweight_16_ssse3; @@ -307,6 +314,9 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth, c->h264_h_loop_filter_luma = ff_deblock_h_luma_8_avx; c->h264_v_loop_filter_luma_intra = ff_deblock_v_luma_intra_8_avx; c->h264_h_loop_filter_luma_intra = ff_deblock_h_luma_intra_8_avx; +#if ARCH_X86_64 + c->h264_h_loop_filter_luma_mbaff = ff_deblock_h_luma_mbaff_8_avx; +#endif } } else if (bit_depth == 10) { if (EXTERNAL_MMXEXT(cpu_flags)) {