From patchwork Tue Sep 17 03:42:28 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lance Wang X-Patchwork-Id: 15114 Return-Path: X-Original-To: patchwork@ffaux-bg.ffmpeg.org Delivered-To: patchwork@ffaux-bg.ffmpeg.org Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by ffaux.localdomain (Postfix) with ESMTP id DFC15448C8A for ; Tue, 17 Sep 2019 06:42:50 +0300 (EEST) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id CA8216881C1; Tue, 17 Sep 2019 06:42:50 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-pg1-f194.google.com (mail-pg1-f194.google.com [209.85.215.194]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id F22F26880E9 for ; Tue, 17 Sep 2019 06:42:43 +0300 (EEST) Received: by mail-pg1-f194.google.com with SMTP id c17so1222126pgg.4 for ; Mon, 16 Sep 2019 20:42:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=TsvyNLkmazp+c9YxLvYTmxp7RTvu/BeF3a+ClFs3EeE=; b=APXIrxZas/fbFMdHv0pThupq2sLK7Tn/+NzlU7oGKEjYunHCpfWMjEwMzYnwzL317N zph6z5w3n1kDYbrJePAxLXWKrptefbCoFiGtaAfWd+SH4fnBiQqa3rLymQE46VEfqWqq Gl5QQ1vXGmaxir83SHoZLnbc6hpUDiBRseJpbEbLrP0qZicv9+2VVIznn4AEy7yHtufz orCYML5aVRRfzrgyCT42Sp3lCWvn+LEMmtJfbk4qTtIKGTOUFwaum7zaCYQ+kzrRIuxf AZFzZrU1HSUlTO0xR1LB3QVv8jaPcLULwZGR4cYHCHVJqWcl/tWeQs8iFsG+y/R2uUO1 sq5w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=TsvyNLkmazp+c9YxLvYTmxp7RTvu/BeF3a+ClFs3EeE=; b=Oz8JQfVcWh9gcNn6DoEpswAp9aA7MifEy1cvJCn3xiK2UCdhIlHgcN7mRxRmRhslrE qQBJ2ngae3PR9xlfuRFZMsvGj0lWVzuBslmXZVGbpU2hLV7w3ILvD+7K1G6yIgfUh+cm s71X3r1oX2lMgFVyM8kACDNXRpeaMoxq3yMkAauPAKEvzZyJOzqmsGUo28V2CVfKfy9k 8SPvqhRFt07DIqaRyYwLPE3mz2COL0/9Lk7BDrGb1zw9gxcwVfrS6/BQyS2Iu6Mk6/XR Om8FB4eYY4ieyseX4PVinVAiLqfycLW8SdxeGUSkn4Vu/kzuaFE4tna7dRLr+wUDxjTZ qBaA== X-Gm-Message-State: APjAAAVS3ITQL/OQFIH3sqrURqt7oiCVQu2RYOTzVhhGh6P/Ivw7Z57l PDsqDBRWKYQ7NZXVHqt3wBWZX3G+ X-Google-Smtp-Source: APXvYqyu+s2F+at5/cHwDvWsT7qfO67xwmbMcXOizbsmQEgmngb0NgsEYFMZhChBELuSIIsGaCuchw== X-Received: by 2002:a17:90a:c501:: with SMTP id k1mr2715440pjt.37.1568691761847; Mon, 16 Sep 2019 20:42:41 -0700 (PDT) Received: from vpn.localdomain ([47.90.99.151]) by smtp.gmail.com with ESMTPSA id o42sm765973pjo.32.2019.09.16.20.42.40 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 16 Sep 2019 20:42:41 -0700 (PDT) From: lance.lmwang@gmail.com To: ffmpeg-devel@ffmpeg.org Date: Tue, 17 Sep 2019 11:42:28 +0800 Message-Id: <20190917034228.31993-3-lance.lmwang@gmail.com> X-Mailer: git-send-email 2.9.5 In-Reply-To: <20190917034228.31993-1-lance.lmwang@gmail.com> References: <20190901132023.28531-1-lance.lmwang@gmail.com> <20190917034228.31993-1-lance.lmwang@gmail.com> Subject: [FFmpeg-devel] [PATCH v4 3/3] avcodec/v210enc: move v210_enc_8/10 function to template file 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 Cc: Limin Wang MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" From: Limin Wang Signed-off-by: Limin Wang --- libavcodec/v210_template.c | 90 +++++++++++++++++++++++++ libavcodec/v210enc.c | 135 +++++++------------------------------ 2 files changed, 114 insertions(+), 111 deletions(-) create mode 100644 libavcodec/v210_template.c diff --git a/libavcodec/v210_template.c b/libavcodec/v210_template.c new file mode 100644 index 0000000000..9e1d9f9cd3 --- /dev/null +++ b/libavcodec/v210_template.c @@ -0,0 +1,90 @@ +/* + * Copyright (C) 2009 Michael Niedermayer + * Copyright (c) 2009 Baptiste Coudurier + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "bytestream.h" +#include "internal.h" + +#define CLIP(v, depth) av_clip(v, 1<<(depth-8), ((1<priv_data; + int aligned_width = ((avctx->width + 47) / 48) * 48; + int stride = aligned_width * 8 / 3; + int line_padding = stride - ((avctx->width * 8 + 11) / 12) * 4; + int h, w; + const TYPE *y = (const TYPE *)pic->data[0]; + const TYPE *u = (const TYPE *)pic->data[1]; + const TYPE *v = (const TYPE *)pic->data[2]; + const int sample_size = 6 * s->RENAME(sample_factor); + const int sample_w = avctx->width / sample_size; + + for (h = 0; h < avctx->height; h++) { + uint32_t val; + w = sample_w * sample_size; + s->RENAME(pack_line)(y, u, v, dst, w); + + y += w; + u += w >> 1; + v += w >> 1; + dst += sample_w * 16 * s->RENAME(sample_factor); + + for (; w < avctx->width - 5; w += 6) { + WRITE_PIXELS(u, y, v, DEPTH); + WRITE_PIXELS(y, u, y, DEPTH); + WRITE_PIXELS(v, y, u, DEPTH); + WRITE_PIXELS(y, v, y, DEPTH); + } + if (w < avctx->width - 1) { + WRITE_PIXELS(u, y, v, DEPTH); + + val = CLIP(*y++, DEPTH) << (10-DEPTH); + if (w == avctx->width - 2) { + AV_WL32(dst, val); + dst += 4; + } + } + if (w < avctx->width - 3) { + val |= (CLIP(*u++, DEPTH) << (20-DEPTH)) | (CLIP(*y++, DEPTH) << (30-DEPTH)); + AV_WL32(dst, val); + dst += 4; + + val = CLIP(*v++, DEPTH) << (10-DEPTH) | (CLIP(*y++, DEPTH) << (20-DEPTH)); + AV_WL32(dst, val); + dst += 4; + } + + memset(dst, 0, line_padding); + dst += line_padding; + y += pic->linesize[0] / BYTES_PER_PIXEL - avctx->width; + u += pic->linesize[1] / BYTES_PER_PIXEL - avctx->width / 2; + v += pic->linesize[2] / BYTES_PER_PIXEL - avctx->width / 2; + } +} diff --git a/libavcodec/v210enc.c b/libavcodec/v210enc.c index f545e43c6c..16e8810271 100644 --- a/libavcodec/v210enc.c +++ b/libavcodec/v210enc.c @@ -26,15 +26,25 @@ #include "internal.h" #include "v210enc.h" -#define CLIP(v, depth) av_clip(v, 1 << (depth-8), ((1 << depth)-(1 << (depth-8)) -1)) -#define WRITE_PIXELS(a, b, c, depth) \ - do { \ - val = CLIP(*a++, depth) << (10-depth); \ - val |= (CLIP(*b++, depth) << (20-depth)) | \ - (CLIP(*c++, depth) << (30-depth)); \ - AV_WL32(dst, val); \ - dst += 4; \ - } while (0) +#define TYPE uint8_t +#define DEPTH 8 +#define BYTES_PER_PIXEL 1 +#define RENAME(a) a ## _ ## 8 +#include "v210_template.c" +#undef RENAME +#undef DEPTH +#undef BYTES_PER_PIXEL +#undef TYPE + +#define TYPE uint16_t +#define DEPTH 10 +#define BYTES_PER_PIXEL 2 +#define RENAME(a) a ## _ ## 10 +#include "v210_template.c" +#undef RENAME +#undef DEPTH +#undef BYTES_PER_PIXEL +#undef TYPE static void v210_planar_pack_8_c(const uint8_t *y, const uint8_t *u, const uint8_t *v, uint8_t *dst, @@ -108,12 +118,10 @@ FF_ENABLE_DEPRECATION_WARNINGS static int encode_frame(AVCodecContext *avctx, AVPacket *pkt, const AVFrame *pic, int *got_packet) { - V210EncContext *s = avctx->priv_data; int aligned_width = ((avctx->width + 47) / 48) * 48; int stride = aligned_width * 8 / 3; - int line_padding = stride - ((avctx->width * 8 + 11) / 12) * 4; AVFrameSideData *side_data; - int h, w, ret; + int ret; uint8_t *dst; ret = ff_alloc_packet2(avctx, pkt, avctx->height * stride, avctx->height * stride); @@ -123,105 +131,10 @@ static int encode_frame(AVCodecContext *avctx, AVPacket *pkt, } dst = pkt->data; - if (pic->format == AV_PIX_FMT_YUV422P10) { - const uint16_t *y = (const uint16_t *)pic->data[0]; - const uint16_t *u = (const uint16_t *)pic->data[1]; - const uint16_t *v = (const uint16_t *)pic->data[2]; - - const int sample_size = 6 * s->sample_factor_10; - const int sample_w = avctx->width / sample_size; - - for (h = 0; h < avctx->height; h++) { - uint32_t val; - w = sample_w * sample_size; - s->pack_line_10(y, u, v, dst, w); - - y += w; - u += w >> 1; - v += w >> 1; - dst += sample_w * 16 * s->sample_factor_10; - - for (; w < avctx->width - 5; w += 6) { - WRITE_PIXELS(u, y, v, 10); - WRITE_PIXELS(y, u, y, 10); - WRITE_PIXELS(v, y, u, 10); - WRITE_PIXELS(y, v, y, 10); - } - if (w < avctx->width - 1) { - WRITE_PIXELS(u, y, v, 10); - - val = CLIP(*y++, 10) << (10-10); - if (w == avctx->width - 2) { - AV_WL32(dst, val); - dst += 4; - } - } - if (w < avctx->width - 3) { - val |= (CLIP(*u++, 10) << (20-10)) | (CLIP(*y++, 10) << (30-10)); - AV_WL32(dst, val); - dst += 4; - - val = CLIP(*v++, 10) << (10-10) | (CLIP(*y++, 10) << (20-10)); - AV_WL32(dst, val); - dst += 4; - } - - memset(dst, 0, line_padding); - dst += line_padding; - y += pic->linesize[0] / 2 - avctx->width; - u += pic->linesize[1] / 2 - avctx->width / 2; - v += pic->linesize[2] / 2 - avctx->width / 2; - } - } else if(pic->format == AV_PIX_FMT_YUV422P) { - const uint8_t *y = pic->data[0]; - const uint8_t *u = pic->data[1]; - const uint8_t *v = pic->data[2]; - - const int sample_size = 6 * s->sample_factor_8; - const int sample_w = avctx->width / sample_size; - - for (h = 0; h < avctx->height; h++) { - uint32_t val; - w = sample_w * sample_size; - s->pack_line_8(y, u, v, dst, w); - - y += w; - u += w >> 1; - v += w >> 1; - dst += sample_w * 16 * s->sample_factor_8; - - for (; w < avctx->width - 5; w += 6) { - WRITE_PIXELS(u, y, v, 8); - WRITE_PIXELS(y, u, y, 8); - WRITE_PIXELS(v, y, u, 8); - WRITE_PIXELS(y, v, y, 8); - } - if (w < avctx->width - 1) { - WRITE_PIXELS(u, y, v, 8); - - val = CLIP(*y++, 8) << (10-8); - if (w == avctx->width - 2) { - AV_WL32(dst, val); - dst += 4; - } - } - if (w < avctx->width - 3) { - val |= (CLIP(*u++, 8) << (20-8)) | (CLIP(*y++, 8) << (30-8)); - AV_WL32(dst, val); - dst += 4; - - val = (CLIP(*v++, 8) << (10-8)) | (CLIP(*y++, 8) << (20-8)); - AV_WL32(dst, val); - dst += 4; - } - memset(dst, 0, line_padding); - dst += line_padding; - - y += pic->linesize[0] - avctx->width; - u += pic->linesize[1] - avctx->width / 2; - v += pic->linesize[2] - avctx->width / 2; - } - } + if (pic->format == AV_PIX_FMT_YUV422P10) + v210_enc_10(avctx, dst, pic); + else if(pic->format == AV_PIX_FMT_YUV422P) + v210_enc_8(avctx, dst, pic); side_data = av_frame_get_side_data(pic, AV_FRAME_DATA_A53_CC); if (side_data && side_data->size) {