From patchwork Tue May 21 16:28:50 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jun Zhao X-Patchwork-Id: 13224 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 DED5C447186 for ; Tue, 21 May 2019 19:34:56 +0300 (EEST) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id BC58E68A3D5; Tue, 21 May 2019 19:34:56 +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 C0AE2689F27 for ; Tue, 21 May 2019 19:34:49 +0300 (EEST) Received: by mail-pg1-f194.google.com with SMTP id n2so2170052pgp.11 for ; Tue, 21 May 2019 09:34:49 -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; bh=ql/4pqc6BdpgzVRy6BWAQtFxmN9t0T5Yo+EQcz6wf6I=; b=QqBkfi2ZJSgyD1Sbg9wMpjEiPqdOylrtn4UqH53B/c8SVcWB01wpHDy9I/nGHyMSL6 j53cks15kbQEBgMC43eKVev26TMqtlbVGacsU5v6OdV/dhQ6a4xpb1nOJshwLa0quldr zExTF/nsu4rRjzbmRzcSGxgwdWFlODuGhBDX3Amoa56bOcHFDyfiR6r4hLKACW9KZZuw i4YJgI3QGphWvgCDFz5FoxFGzdMGMNloSWdXjx5A1kKctbHEt/CaJiw55W01KiuUr/Jr RNN8p+QSj57AL1vMHb9PNaLnM13wr8+v47ze/cwuz5gonkkAfZCQHCuhrbhvCExUx6UG C8Eg== 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; bh=ql/4pqc6BdpgzVRy6BWAQtFxmN9t0T5Yo+EQcz6wf6I=; b=MMEjkALQqsavwzINrIR8w9PdQDM6T//OeP/BXCuDyi+pCDY+eOcAOB6SMBrKgAw9u/ mwQVlW6sKWEw826tj3TRfk+ogRxXNxc4RhUDaJ3fRmJjqbtdtl6+CVzWavIDh5u942Zd c1XLZ8yVRBZ7KhulVbHKZ11DeMxeo68h8cWc0kD+HGSiejExULSLTaPfpAe9wn1PHVYJ gIh/3O355FdtNBs4fAtbNKjKKuOKAFk3y6m5pySrkRI/vlOoasQmnYIlWE3n4T/rd6/+ zlzymdv+Tbp0k46m03LPgwly6614/I6VjJlx/gM90oMKx1jJssGkrfuy/IV0Yu7kY4rs WEYg== X-Gm-Message-State: APjAAAUND6RIikIJZwMeT0sVZshOKv2iNBgxCnaagDGhiuZwjfGn2GMN yBl90Z3htVLy4pNDYTMxkQlEhcO2 X-Google-Smtp-Source: APXvYqxS1q6IBRsIRro9QVO/LjFEme6180gWIvVKcgItvRCNN5uYa6Ga790kD9zt+esqVnLi1gFtbQ== X-Received: by 2002:a62:a511:: with SMTP id v17mr61223501pfm.129.1558456134988; Tue, 21 May 2019 09:28:54 -0700 (PDT) Received: from localhost.localdomain ([47.90.47.25]) by smtp.gmail.com with ESMTPSA id a18sm34130828pfr.22.2019.05.21.09.28.53 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Tue, 21 May 2019 09:28:54 -0700 (PDT) From: Jun Zhao To: ffmpeg-devel@ffmpeg.org Date: Wed, 22 May 2019 00:28:50 +0800 Message-Id: <1558456130-9819-1-git-send-email-mypopydev@gmail.com> X-Mailer: git-send-email 1.7.1 Subject: [FFmpeg-devel] [PATCH V1] lavfi/lut: Add 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: Jun Zhao MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" From: Jun Zhao Used the command for 1080p h264 clip as follow: a). ffmpeg -i input -vf lutyuv="u=128:v=128" -f null /dev/null b). ffmpeg -i input -vf lutrgb="g=0:b=0" -f null /dev/null after enabled the slice threading, the fps change from: a). 144fps to 258fps (lutyuv) b). 94fps to 153fps (lutrgb) in Intel(R) Core(TM) i5-8265U CPU @ 1.60GHz Signed-off-by: Jun Zhao --- libavfilter/vf_lut.c | 328 +++++++++++++++++++++++++++++++++----------------- 1 files changed, 216 insertions(+), 112 deletions(-) diff --git a/libavfilter/vf_lut.c b/libavfilter/vf_lut.c index c815ddc..61550ee 100644 --- a/libavfilter/vf_lut.c +++ b/libavfilter/vf_lut.c @@ -337,13 +337,194 @@ static int config_props(AVFilterLink *inlink) return 0; } +struct thread_data { + AVFrame *in; + AVFrame *out; + + int w; + int h; +}; + +/* packed, 16-bit */ +static int lut_packed_16bits(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs) +{ + LutContext *s = ctx->priv; + const struct thread_data *td = arg; + + uint16_t *inrow, *outrow, *inrow0, *outrow0; + int i, j; + const int w = td->w; + const int h = td->h; + AVFrame *in = td->in; + AVFrame *out = td->out; + const uint16_t (*tab)[256*256] = (const uint16_t (*)[256*256])s->lut; + const int in_linesize = in->linesize[0] / 2; + const int out_linesize = out->linesize[0] / 2; + const int step = s->step; + + const int slice_start = (h * jobnr ) / nb_jobs; + const int slice_end = (h * (jobnr+1)) / nb_jobs; + + inrow0 = (uint16_t *)in ->data[0]; + outrow0 = (uint16_t *)out->data[0]; + + for (i = slice_start; i < slice_end; i++) { + inrow = inrow0 + i * in_linesize; + outrow = outrow0 + i * out_linesize; + for (j = 0; j < w; j++) { + + switch (step) { +#if HAVE_BIGENDIAN + case 4: outrow[3] = av_bswap16(tab[3][av_bswap16(inrow[3])]); // Fall-through + case 3: outrow[2] = av_bswap16(tab[2][av_bswap16(inrow[2])]); // Fall-through + case 2: outrow[1] = av_bswap16(tab[1][av_bswap16(inrow[1])]); // Fall-through + default: outrow[0] = av_bswap16(tab[0][av_bswap16(inrow[0])]); +#else + case 4: outrow[3] = tab[3][inrow[3]]; // Fall-through + case 3: outrow[2] = tab[2][inrow[2]]; // Fall-through + case 2: outrow[1] = tab[1][inrow[1]]; // Fall-through + default: outrow[0] = tab[0][inrow[0]]; +#endif + } + outrow += step; + inrow += step; + } + } + + return 0; +} + +/* packed, 16-bit */ +static int lut_packed_8bits(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs) +{ + LutContext *s = ctx->priv; + const struct thread_data *td = arg; + + uint8_t *inrow, *outrow, *inrow0, *outrow0; + int i, j; + const int w = td->w; + const int h = td->h; + AVFrame *in = td->in; + AVFrame *out = td->out; + const uint16_t (*tab)[256*256] = (const uint16_t (*)[256*256])s->lut; + const int in_linesize = in->linesize[0]; + const int out_linesize = out->linesize[0]; + const int step = s->step; + + const int slice_start = (h * jobnr ) / nb_jobs; + const int slice_end = (h * (jobnr+1)) / nb_jobs; + + inrow0 = in ->data[0]; + outrow0 = out->data[0]; + + for (i = slice_start; i < slice_end; i++) { + inrow = inrow0 + i * in_linesize; + outrow = outrow0 + i * out_linesize; + for (j = 0; j < w; j++) { + switch (step) { + case 4: outrow[3] = tab[3][inrow[3]]; // Fall-through + case 3: outrow[2] = tab[2][inrow[2]]; // Fall-through + case 2: outrow[1] = tab[1][inrow[1]]; // Fall-through + default: outrow[0] = tab[0][inrow[0]]; + } + outrow += step; + inrow += step; + } + } + + return 0; +} + + +static int lut_planar_16bits(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs) +{ + // planar >8 bit depth + LutContext *s = ctx->priv; + const struct thread_data *td = arg; + + uint16_t *inrow, *outrow; + int i, j, plane; + + AVFrame *in = td->in; + AVFrame *out = td->out; + + for (plane = 0; plane < 4 && in->data[plane] && in->linesize[plane]; plane++) { + int vsub = plane == 1 || plane == 2 ? s->vsub : 0; + int hsub = plane == 1 || plane == 2 ? s->hsub : 0; + int h = AV_CEIL_RSHIFT(td->h, vsub); + int w = AV_CEIL_RSHIFT(td->w, hsub); + const uint16_t *tab = s->lut[plane]; + const int in_linesize = in->linesize[plane] / 2; + const int out_linesize = out->linesize[plane] / 2; + + const int slice_start = (h * jobnr ) / nb_jobs; + const int slice_end = (h * (jobnr+1)) / nb_jobs; + + inrow = (uint16_t *)(in ->data[plane] + slice_start * in_linesize); + outrow = (uint16_t *)(out->data[plane] + slice_start * out_linesize); + + for (i = slice_start; i < slice_end; i++) { + for (j = 0; j < w; j++) { +#if HAVE_BIGENDIAN + outrow[j] = av_bswap16(tab[av_bswap16(inrow[j])]); +#else + outrow[j] = tab[inrow[j]]; +#endif + } + inrow += in_linesize; + outrow += out_linesize; + } + } + + return 0; +} + + /* planar 8bit depth */ +static int lut_planar_8bits(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs) +{ + LutContext *s = ctx->priv; + const struct thread_data *td = arg; + + uint8_t *inrow, *outrow; + + int i, j, plane; + + AVFrame *in = td->in; + AVFrame *out = td->out; + + for (plane = 0; plane < 4 && in->data[plane] && in->linesize[plane]; plane++) { + int vsub = plane == 1 || plane == 2 ? s->vsub : 0; + int hsub = plane == 1 || plane == 2 ? s->hsub : 0; + int h = AV_CEIL_RSHIFT(td->h, vsub); + int w = AV_CEIL_RSHIFT(td->w, hsub); + const uint16_t *tab = s->lut[plane]; + const int in_linesize = in->linesize[plane]; + const int out_linesize = out->linesize[plane]; + + const int slice_start = (h * jobnr ) / nb_jobs; + const int slice_end = (h * (jobnr+1)) / nb_jobs; + + inrow = in ->data[plane] + slice_start * in_linesize; + outrow = out->data[plane] + slice_start * out_linesize; + + for (i = slice_start; i < slice_end; i++) { + for (j = 0; j < w; j++) + outrow[j] = tab[inrow[j]]; + inrow += in_linesize; + outrow += out_linesize; + } + } + + return 0; +} + static int filter_frame(AVFilterLink *inlink, AVFrame *in) { AVFilterContext *ctx = inlink->dst; LutContext *s = ctx->priv; AVFilterLink *outlink = ctx->outputs[0]; AVFrame *out; - int i, j, plane, direct = 0; + int direct = 0; if (av_frame_is_writable(in)) { direct = 1; @@ -359,121 +540,44 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *in) if (s->is_rgb && s->is_16bit && !s->is_planar) { /* packed, 16-bit */ - uint16_t *inrow, *outrow, *inrow0, *outrow0; - const int w = inlink->w; - const int h = in->height; - const uint16_t (*tab)[256*256] = (const uint16_t (*)[256*256])s->lut; - const int in_linesize = in->linesize[0] / 2; - const int out_linesize = out->linesize[0] / 2; - const int step = s->step; - - inrow0 = (uint16_t*) in ->data[0]; - outrow0 = (uint16_t*) out->data[0]; - - for (i = 0; i < h; i ++) { - inrow = inrow0; - outrow = outrow0; - for (j = 0; j < w; j++) { - - switch (step) { -#if HAVE_BIGENDIAN - case 4: outrow[3] = av_bswap16(tab[3][av_bswap16(inrow[3])]); // Fall-through - case 3: outrow[2] = av_bswap16(tab[2][av_bswap16(inrow[2])]); // Fall-through - case 2: outrow[1] = av_bswap16(tab[1][av_bswap16(inrow[1])]); // Fall-through - default: outrow[0] = av_bswap16(tab[0][av_bswap16(inrow[0])]); -#else - case 4: outrow[3] = tab[3][inrow[3]]; // Fall-through - case 3: outrow[2] = tab[2][inrow[2]]; // Fall-through - case 2: outrow[1] = tab[1][inrow[1]]; // Fall-through - default: outrow[0] = tab[0][inrow[0]]; -#endif - } - outrow += step; - inrow += step; - } - inrow0 += in_linesize; - outrow0 += out_linesize; - } + struct thread_data td = { + .in = in, + .out = out, + .w = inlink->w, + .h = in->height, + }; + ctx->internal->execute(ctx, lut_packed_16bits, &td, NULL, + FFMIN(in->height, ff_filter_get_nb_threads(ctx))); } else if (s->is_rgb && !s->is_planar) { /* packed */ - uint8_t *inrow, *outrow, *inrow0, *outrow0; - const int w = inlink->w; - const int h = in->height; - const uint16_t (*tab)[256*256] = (const uint16_t (*)[256*256])s->lut; - const int in_linesize = in->linesize[0]; - const int out_linesize = out->linesize[0]; - const int step = s->step; - - inrow0 = in ->data[0]; - outrow0 = out->data[0]; - - for (i = 0; i < h; i ++) { - inrow = inrow0; - outrow = outrow0; - for (j = 0; j < w; j++) { - switch (step) { - case 4: outrow[3] = tab[3][inrow[3]]; // Fall-through - case 3: outrow[2] = tab[2][inrow[2]]; // Fall-through - case 2: outrow[1] = tab[1][inrow[1]]; // Fall-through - default: outrow[0] = tab[0][inrow[0]]; - } - outrow += step; - inrow += step; - } - inrow0 += in_linesize; - outrow0 += out_linesize; - } + struct thread_data td = { + .in = in, + .out = out, + .w = inlink->w, + .h = in->height, + }; + ctx->internal->execute(ctx, lut_packed_8bits, &td, NULL, + FFMIN(in->height, ff_filter_get_nb_threads(ctx))); } else if (s->is_16bit) { - // planar >8 bit depth - uint16_t *inrow, *outrow; - - for (plane = 0; plane < 4 && in->data[plane] && in->linesize[plane]; plane++) { - int vsub = plane == 1 || plane == 2 ? s->vsub : 0; - int hsub = plane == 1 || plane == 2 ? s->hsub : 0; - int h = AV_CEIL_RSHIFT(inlink->h, vsub); - int w = AV_CEIL_RSHIFT(inlink->w, hsub); - const uint16_t *tab = s->lut[plane]; - const int in_linesize = in->linesize[plane] / 2; - const int out_linesize = out->linesize[plane] / 2; - - inrow = (uint16_t *)in ->data[plane]; - outrow = (uint16_t *)out->data[plane]; - - for (i = 0; i < h; i++) { - for (j = 0; j < w; j++) { -#if HAVE_BIGENDIAN - outrow[j] = av_bswap16(tab[av_bswap16(inrow[j])]); -#else - outrow[j] = tab[inrow[j]]; -#endif - } - inrow += in_linesize; - outrow += out_linesize; - } - } + /* planar >8 bit depth */ + struct thread_data td = { + .in = in, + .out = out, + .w = inlink->w, + .h = inlink->h, + }; + ctx->internal->execute(ctx, lut_planar_16bits, &td, NULL, + FFMIN(in->height, ff_filter_get_nb_threads(ctx))); } else { /* planar 8bit depth */ - uint8_t *inrow, *outrow; - - for (plane = 0; plane < 4 && in->data[plane] && in->linesize[plane]; plane++) { - int vsub = plane == 1 || plane == 2 ? s->vsub : 0; - int hsub = plane == 1 || plane == 2 ? s->hsub : 0; - int h = AV_CEIL_RSHIFT(inlink->h, vsub); - int w = AV_CEIL_RSHIFT(inlink->w, hsub); - const uint16_t *tab = s->lut[plane]; - const int in_linesize = in->linesize[plane]; - const int out_linesize = out->linesize[plane]; - - inrow = in ->data[plane]; - outrow = out->data[plane]; - - for (i = 0; i < h; i++) { - for (j = 0; j < w; j++) - outrow[j] = tab[inrow[j]]; - inrow += in_linesize; - outrow += out_linesize; - } - } + struct thread_data td = { + .in = in, + .out = out, + .w = inlink->w, + .h = inlink->h, + }; + ctx->internal->execute(ctx, lut_planar_8bits, &td, NULL, + FFMIN(in->height, ff_filter_get_nb_threads(ctx))); } if (!direct) @@ -508,7 +612,7 @@ static const AVFilterPad outputs[] = { .query_formats = query_formats, \ .inputs = inputs, \ .outputs = outputs, \ - .flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC, \ + .flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC | AVFILTER_FLAG_SLICE_THREADS, \ } #if CONFIG_LUT_FILTER