From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id A4D9E409F3 for ; Wed, 2 Feb 2022 12:22:07 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 6F2F168AE99; Wed, 2 Feb 2022 14:22:04 +0200 (EET) Received: from mail-yb1-f169.google.com (mail-yb1-f169.google.com [209.85.219.169]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 0139168A6F6 for ; Wed, 2 Feb 2022 14:21:57 +0200 (EET) Received: by mail-yb1-f169.google.com with SMTP id r65so60282849ybc.11 for ; Wed, 02 Feb 2022 04:21:57 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=mime-version:references:in-reply-to:from:date:message-id:subject:to; bh=XNB58sAJEIx9I8VeGspu60DBPp2FNeA6Qw6Z8TDGVy0=; b=ksC6m3gN9N3po+ZSN4JvR3zlZC+wYKFBsJ7j0FB6sDR7/JZpwbDkBkROOie89wGrec LBTdMgC7fnsuEjkl/TtMzaSH+1F2H86zORAfYCI3blOVt/hBZyARZ+QMh1M4zDSJvFCg KkhRPTqKuuDZ33FjF13ilBHU0JbDUPQL2/KbWFSvBw5jrwYclOlmZN7X/drVdXfPprzK MgLdtCoQyuieINkKWInPwK7oDgsX/7ODiC51/yjT93d+qgd086Kkcx1XRClgsI8jNiaJ UEvFtwI8HeyfcAR6DpTFoXfQ+HfDwDJUTO49x0+mEfw6uwsQvZVBaCKcqwJYf8XAWXpm lrww== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to; bh=XNB58sAJEIx9I8VeGspu60DBPp2FNeA6Qw6Z8TDGVy0=; b=IwGvVgXRlH2HzhUIFQku9pJ5q21Oh82juLvbm6aiaNOpazijo5biyfRQuesiJdPjBc E0+f/UzcOOLMqIzGYM3r0hQh1tHFwjr5kHQY8rqzYL+TmJ19MQOvT5XUHx5tuj58Amed daWGeekB67URcWS1A3ZIph5ZDctKSQOfm7ZiN+5oFGtMv4ld+s61eWGJv4IQKeL3wGdV MRHby2noP2VA9lNa04stRrERREKV+inme4pbB7VP4wf6JmInaKQSAFayGlNdv0r8CgvV ExOJG7Qa+AplOy+ZGBo3NwZS7lmaXKkPsi0JRowB3splfZvyHmia1UGywdkYVE8kdg92 nFRg== X-Gm-Message-State: AOAM533dDTurHqIHyFnB25KjYVGP/LkSeGiLXj5MKaQpB+ItHxQnZ1Og AxlrCWMNr/03L/s8jfwjTQHAt9/+GxdrzbO0vzCZEsDE8iQ= X-Google-Smtp-Source: ABdhPJytL925Je1XPLx2KshK3L32L2h/jgDnj9WR4Ol08vIV0fUkZSZO3TWWRjZwFmQv/6xIbcPI5vN3rZmysByZA14= X-Received: by 2002:a25:bbc1:: with SMTP id c1mr37842042ybk.68.1643804515873; Wed, 02 Feb 2022 04:21:55 -0800 (PST) MIME-Version: 1.0 References: <20220110145836.3449558-1-alankelly@google.com> In-Reply-To: <20220110145836.3449558-1-alankelly@google.com> From: Alan Kelly Date: Wed, 2 Feb 2022 13:21:44 +0100 Message-ID: To: FFmpeg development discussions and patches X-Content-Filtered-By: Mailman/MimeDel 2.1.29 Subject: Re: [FFmpeg-devel] [PATCH 1/4] libswscale: Re-factor ff_shuffle_filter_coefficients. X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 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 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: Hi, Is anybody interested in this patch set? Thanks! On Mon, Jan 10, 2022, 15:58 Alan Kelly wrote: > Make the code more readable, follow the style guide and propagate memory > allocation errors. > --- > libswscale/swscale_internal.h | 2 +- > libswscale/utils.c | 68 ++++++++++++++++++++--------------- > 2 files changed, 40 insertions(+), 30 deletions(-) > > diff --git a/libswscale/swscale_internal.h b/libswscale/swscale_internal.h > index 3a78d95ba6..26d28d42e6 100644 > --- a/libswscale/swscale_internal.h > +++ b/libswscale/swscale_internal.h > @@ -1144,5 +1144,5 @@ void ff_sws_slice_worker(void *priv, int jobnr, int > threadnr, > #define MAX_LINES_AHEAD 4 > > //shuffle filter and filterPos for hyScale and hcScale filters in avx2 > -void ff_shuffle_filter_coefficients(SwsContext *c, int* filterPos, int > filterSize, int16_t *filter, int dstW); > +int ff_shuffle_filter_coefficients(SwsContext *c, int* filterPos, int > filterSize, int16_t *filter, int dstW); > #endif /* SWSCALE_SWSCALE_INTERNAL_H */ > diff --git a/libswscale/utils.c b/libswscale/utils.c > index c5ea8853d5..52f07e1661 100644 > --- a/libswscale/utils.c > +++ b/libswscale/utils.c > @@ -278,39 +278,47 @@ static const FormatEntry format_entries[] = { > [AV_PIX_FMT_P416LE] = { 1, 1 }, > }; > > -void ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, int > filterSize, int16_t *filter, int dstW){ > +int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, > + int filterSize, int16_t *filter, > + int dstW) > +{ > #if ARCH_X86_64 > - int i, j, k, l; > + int i = 0, j = 0, k = 0; > int cpu_flags = av_get_cpu_flags(); > + if (!filter || dstW % 16 != 0) return 0; > if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & > AV_CPU_FLAG_SLOW_GATHER)) { > - if ((c->srcBpc == 8) && (c->dstBpc <= 14)){ > - if (dstW % 16 == 0){ > - if (filter != NULL){ > - for (i = 0; i < dstW; i += 8){ > - FFSWAP(int, filterPos[i + 2], filterPos[i+4]); > - FFSWAP(int, filterPos[i + 3], filterPos[i+5]); > - } > - if (filterSize > 4){ > - int16_t *tmp2 = av_malloc(dstW * filterSize * 2); > - memcpy(tmp2, filter, dstW * filterSize * 2); > - for (i = 0; i < dstW; i += 16){//pixel > - for (k = 0; k < filterSize / 4; ++k){//fcoeff > - for (j = 0; j < 16; ++j){//inner pixel > - for (l = 0; l < 4; ++l){//coeff > - int from = i * filterSize + j * > filterSize + k * 4 + l; > - int to = (i) * filterSize + j * 4 > + l + k * 64; > - filter[to] = tmp2[from]; > - } > - } > - } > - } > - av_free(tmp2); > - } > - } > - } > + if ((c->srcBpc == 8) && (c->dstBpc <= 14)) { > + int16_t *filterCopy = NULL; > + if (filterSize > 4) { > + if (!FF_ALLOC_TYPED_ARRAY(filterCopy, dstW * filterSize)) > + return AVERROR(ENOMEM); > + memcpy(filterCopy, filter, dstW * filterSize * > sizeof(int16_t)); > + } > + // Do not swap filterPos for pixels which won't be processed by > + // the main loop. > + for (i = 0; i + 8 <= dstW; i += 8) { > + FFSWAP(int, filterPos[i + 2], filterPos[i + 4]); > + FFSWAP(int, filterPos[i + 3], filterPos[i + 5]); > + } > + if (filterSize > 4) { > + // 16 pixels are processed at a time. > + for (i = 0; i + 16 <= dstW; i += 16) { > + // 4 filter coeffs are processed at a time. > + for (k = 0; k + 4 <= filterSize; k += 4) { > + for (j = 0; j < 16; ++j) { > + int from = (i + j) * filterSize + k; > + int to = i * filterSize + j * 4 + k * 16; > + memcpy(&filter[to], &filterCopy[from], 4 * > sizeof(int16_t)); > + } > + } > + } > + } > + if (filterCopy) > + av_free(filterCopy); > } > } > #endif > + return 0; > } > > int sws_isSupportedInput(enum AVPixelFormat pix_fmt) > @@ -1836,7 +1844,8 @@ av_cold int sws_init_context(SwsContext *c, > SwsFilter *srcFilter, > get_local_pos(c, 0, 0, 0), > get_local_pos(c, 0, 0, 0))) < 0) > goto fail; > - ff_shuffle_filter_coefficients(c, c->hLumFilterPos, > c->hLumFilterSize, c->hLumFilter, dstW); > + if ((ret = ff_shuffle_filter_coefficients(c, > c->hLumFilterPos, c->hLumFilterSize, c->hLumFilter, dstW)) != 0) > + goto nomem; > if ((ret = initFilter(&c->hChrFilter, &c->hChrFilterPos, > &c->hChrFilterSize, c->chrXInc, > c->chrSrcW, c->chrDstW, filterAlign, 1 << 14, > @@ -1846,7 +1855,8 @@ av_cold int sws_init_context(SwsContext *c, > SwsFilter *srcFilter, > get_local_pos(c, c->chrSrcHSubSample, > c->src_h_chr_pos, 0), > get_local_pos(c, c->chrDstHSubSample, > c->dst_h_chr_pos, 0))) < 0) > goto fail; > - ff_shuffle_filter_coefficients(c, c->hChrFilterPos, > c->hChrFilterSize, c->hChrFilter, c->chrDstW); > + if ((ret = ff_shuffle_filter_coefficients(c, > c->hChrFilterPos, c->hChrFilterSize, c->hChrFilter, c->chrDstW)) != 0) > + goto nomem; > } > } // initialize horizontal stuff > > -- > 2.34.1.575.g55b058a8bb-goog > > _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".