From patchwork Fri Sep 6 15:28:29 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lance Wang X-Patchwork-Id: 14960 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 1D0FA449F06 for ; Fri, 6 Sep 2019 18:50:45 +0300 (EEST) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 2F1DE6880A8; Fri, 6 Sep 2019 18:28:47 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-pl1-f181.google.com (mail-pl1-f181.google.com [209.85.214.181]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 5CF15687FBD for ; Fri, 6 Sep 2019 18:28:40 +0300 (EEST) Received: by mail-pl1-f181.google.com with SMTP id d3so3344428plr.1 for ; Fri, 06 Sep 2019 08:28:40 -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=qxEPtf/m/7SY8v4DiS68uGXdf7SNK2PKkAPm8Mz2dec=; b=DnTD4okGspOfd7I6RevAhCzd1NudSd+WnZEyj/I4n1UBYGL3Mr2QnUR/f/HAh5msCh iw7COfvWaYptdTR67vN2qM7HYOXWZ9XhcjOqbSdx0Mp4Olj35aNYkqvcJO5ogJkunluc hTSEUPYWIHe1zY0eeuUpDaaL0K2gwy+onDFjbhoEMxB3EFZiTGWFFPidagRpvQIQqtFK j+fe7H5tqLB9zhX9Ol0jgvGSONxFBzumJ3Z33wOGC32NUtAfxhx7lYKL5xA85+DkJPYr Vl2ErgDle19xVl1JtiOPOdfG+tqw7xtDPntzscZJRi6E2kKvB90npq71n4Vil2/LZoaV ljKQ== 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=qxEPtf/m/7SY8v4DiS68uGXdf7SNK2PKkAPm8Mz2dec=; b=c/g/Z7OVaENlM6x4jxShXKBluLrduh1Tq1s7KaP9gs7qCnp4OF3RnLmWYW14DfrhqQ 3AdEDrS7PzVACgYRc487TUXUx8NIZ7eNSzWD7Gj6kG9xJtLLWkrPMniG9IOjHTgf/Bmh Mx6umWjvgnJd4aIEAAfiVbIh+6/2xuPqglIbbdS9tg0HJwxTVWiMIWH65Qrzl1pn21Im m8e06IrgdU1mZdSft5EQxRnrZSsOZBXg5gsyDfDhtuzOgtoBgO8PfH0S3MSdLGQuW3/Z nTQi+0sHioeGI459F1T551vR3eLTwdvbEyOFwEYQ/0fVtZZ6CBBtXwOhRWgPwc01Y/2W ezRQ== X-Gm-Message-State: APjAAAU80zAAzuU9oeRL82m8UEz+ExbvHUHqFEdGJmI48NP44+wewIrw PoeC7Iwaj8awSVjagg/rMnC8eLfc X-Google-Smtp-Source: APXvYqxBbM/cQQhE2BoSh5+HwJEm+vG2FlvhdnaYB1zF46P9JV/8XV5YslgSaCB0IHEJW7/815lx1w== X-Received: by 2002:a17:902:a9c7:: with SMTP id b7mr9882138plr.133.1567783718360; Fri, 06 Sep 2019 08:28:38 -0700 (PDT) Received: from vpn.localdomain ([47.90.99.151]) by smtp.gmail.com with ESMTPSA id b18sm3066737pju.16.2019.09.06.08.28.37 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 06 Sep 2019 08:28:37 -0700 (PDT) From: lance.lmwang@gmail.com To: ffmpeg-devel@ffmpeg.org Date: Fri, 6 Sep 2019 23:28:29 +0800 Message-Id: <20190906152829.639-2-lance.lmwang@gmail.com> X-Mailer: git-send-email 2.9.5 In-Reply-To: <20190906152829.639-1-lance.lmwang@gmail.com> References: <20190830033752.26454-1-lance.lmwang@gmail.com> <20190906152829.639-1-lance.lmwang@gmail.com> Subject: [FFmpeg-devel] [PATCH v2 2/2] avcodec/v210dec: add the frame and slice threading support 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 The multithread is avoid one core cpu is full with other filter like scale etc. About the performance, the gain is very small, below is my testing for performance. In order to avoid the disk bottleneck, I'll use stream_loop mode for 10 frame only. ./ffmpeg -y -i ~/Movies/4k_Rec709_ProResHQ.mov -c:v v210 -f rawvideo -frames 10 ~/Movies/1.v210 master: ./ffmpeg -threads 1 -s 4096x3072 -stream_loop 100 -i ~/Movies/1.v210 -benchmark -f null - frame= 1010 fps= 42 q=-0.0 Lsize=N/A time=00:00:40.40 bitrate=N/A speed=1.69x video:529kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown bench: utime=10.082s stime=13.784s rtime=23.889s bench: maxrss=147836928kB patch applied: ./ffmpeg -threads 4 -thread_type frame+slice -s 4096x3072 -stream_loop 100 -i ~/Movies/1.v210 -benchmark -f null - frame= 1010 fps= 55 q=-0.0 Lsize=N/A time=00:00:40.40 bitrate=N/A speed=2.22x video:529kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown bench: utime=11.407s stime=17.258s rtime=18.279s bench: maxrss=442884096kB Signed-off-by: Limin Wang --- libavcodec/v210dec.c | 135 +++++++++++++++++++++++++++++++++------------------ libavcodec/v210dec.h | 1 + 2 files changed, 88 insertions(+), 48 deletions(-) diff --git a/libavcodec/v210dec.c b/libavcodec/v210dec.c index 6ce18aa..2cdb99e 100644 --- a/libavcodec/v210dec.c +++ b/libavcodec/v210dec.c @@ -28,6 +28,7 @@ #include "libavutil/internal.h" #include "libavutil/mem.h" #include "libavutil/intreadwrite.h" +#include "thread.h" #define READ_PIXELS(a, b, c) \ do { \ @@ -37,6 +38,13 @@ *c++ = (val >> 20) & 0x3FF; \ } while (0) +#define MAX_SLICES 32 +typedef struct ThreadData { + AVFrame *frame; + uint8_t *buf; + int stride; +} ThreadData; + static void v210_planar_unpack_c(const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width) { uint32_t val; @@ -67,58 +75,32 @@ static av_cold int decode_init(AVCodecContext *avctx) s->aligned_input = 0; ff_v210dec_init(s); + s->slice_count = av_clip(avctx->thread_count, 1, MAX_SLICES); return 0; } -static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame, - AVPacket *avpkt) +static int v210_decode_slice(AVCodecContext *avctx, void *arg, int jobnr, int nb_jobs) { V210DecContext *s = avctx->priv_data; - - int h, w, ret, stride, aligned_input; - AVFrame *pic = data; - const uint8_t *psrc = avpkt->data; + int h, w; + ThreadData *td = arg; + AVFrame *frame = td->frame; + int stride = td->stride; + int slice_h = avctx->height / s->slice_count; + int slice_m = avctx->height % s->slice_count; + int slice_start = jobnr * slice_h; + int slice_end = slice_start + slice_h; + const uint8_t *psrc = td->buf + stride * slice_start; uint16_t *y, *u, *v; - if (s->custom_stride ) - stride = s->custom_stride; - else { - int aligned_width = ((avctx->width + 47) / 48) * 48; - stride = aligned_width * 8 / 3; - } - - if (avpkt->size < stride * avctx->height) { - if ((((avctx->width + 23) / 24) * 24 * 8) / 3 * avctx->height == avpkt->size) { - stride = avpkt->size / avctx->height; - if (!s->stride_warning_shown) - av_log(avctx, AV_LOG_WARNING, "Broken v210 with too small padding (64 byte) detected\n"); - s->stride_warning_shown = 1; - } else { - av_log(avctx, AV_LOG_ERROR, "packet too small\n"); - return AVERROR_INVALIDDATA; - } - } - if (avctx->codec_tag == MKTAG('C', '2', '1', '0') - && AV_RN32(psrc) == AV_RN32("INFO") - && avpkt->size - 64 >= stride * avctx->height) - psrc += 64; - - aligned_input = !((uintptr_t)psrc & 0x1f) && !(stride & 0x1f); - if (aligned_input != s->aligned_input) { - s->aligned_input = aligned_input; - ff_v210dec_init(s); - } - - if ((ret = ff_get_buffer(avctx, pic, 0)) < 0) - return ret; - - y = (uint16_t*)pic->data[0]; - u = (uint16_t*)pic->data[1]; - v = (uint16_t*)pic->data[2]; - pic->pict_type = AV_PICTURE_TYPE_I; - pic->key_frame = 1; + /* add the remaining slice for the last job */ + if (jobnr == s->slice_count - 1) + slice_end += slice_m; - for (h = 0; h < avctx->height; h++) { + y = (uint16_t*)frame->data[0] + slice_start * frame->linesize[0] / 2; + u = (uint16_t*)frame->data[1] + slice_start * frame->linesize[1] / 2; + v = (uint16_t*)frame->data[2] + slice_start * frame->linesize[2] / 2; + for (h = slice_start; h < slice_end; h++) { const uint32_t *src = (const uint32_t*)psrc; uint32_t val; @@ -154,10 +136,63 @@ static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame, } psrc += stride; - y += pic->linesize[0] / 2 - avctx->width + (avctx->width & 1); - u += pic->linesize[1] / 2 - avctx->width / 2; - v += pic->linesize[2] / 2 - avctx->width / 2; + y += frame->linesize[0] / 2 - avctx->width + (avctx->width & 1); + u += frame->linesize[1] / 2 - avctx->width / 2; + v += frame->linesize[2] / 2 - avctx->width / 2; + } + + return 0; +} + +static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame, + AVPacket *avpkt) +{ + V210DecContext *s = avctx->priv_data; + ThreadData td; + int ret, stride, aligned_input; + ThreadFrame frame = { .f = data }; + AVFrame *pic = data; + const uint8_t *psrc = avpkt->data; + + if (s->custom_stride ) + stride = s->custom_stride; + else { + int aligned_width = ((avctx->width + 47) / 48) * 48; + stride = aligned_width * 8 / 3; + } + td.stride = stride; + + if (avpkt->size < stride * avctx->height) { + if ((((avctx->width + 23) / 24) * 24 * 8) / 3 * avctx->height == avpkt->size) { + stride = avpkt->size / avctx->height; + if (!s->stride_warning_shown) + av_log(avctx, AV_LOG_WARNING, "Broken v210 with too small padding (64 byte) detected\n"); + s->stride_warning_shown = 1; + } else { + av_log(avctx, AV_LOG_ERROR, "packet too small\n"); + return AVERROR_INVALIDDATA; + } } + if (avctx->codec_tag == MKTAG('C', '2', '1', '0') + && AV_RN32(psrc) == AV_RN32("INFO") + && avpkt->size - 64 >= stride * avctx->height) + psrc += 64; + + aligned_input = !((uintptr_t)psrc & 0x1f) && !(stride & 0x1f); + if (aligned_input != s->aligned_input) { + s->aligned_input = aligned_input; + ff_v210dec_init(s); + } + + if ((ret = ff_thread_get_buffer(avctx, &frame, 0)) < 0) + return ret; + + pic->pict_type = AV_PICTURE_TYPE_I; + pic->key_frame = 1; + + td.buf = (uint8_t*)psrc; + td.frame = pic; + avctx->execute2(avctx, v210_decode_slice, &td, NULL, s->slice_count); if (avctx->field_order > AV_FIELD_PROGRESSIVE) { /* we have interlaced material flagged in container */ @@ -193,6 +228,10 @@ AVCodec ff_v210_decoder = { .priv_data_size = sizeof(V210DecContext), .init = decode_init, .decode = decode_frame, - .capabilities = AV_CODEC_CAP_DR1, + .capabilities = AV_CODEC_CAP_DR1 | + AV_CODEC_CAP_SLICE_THREADS | + AV_CODEC_CAP_FRAME_THREADS, .priv_class = &v210dec_class, + .caps_internal = FF_CODEC_CAP_INIT_THREADSAFE | + FF_CODEC_CAP_INIT_CLEANUP, }; diff --git a/libavcodec/v210dec.h b/libavcodec/v210dec.h index cfdb29d..3581943 100644 --- a/libavcodec/v210dec.h +++ b/libavcodec/v210dec.h @@ -26,6 +26,7 @@ typedef struct { AVClass *av_class; int custom_stride; + int slice_count; // Number of slices for threaded operations int aligned_input; int stride_warning_shown; void (*unpack_frame)(const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width);