From patchwork Tue Jul 26 19:41:06 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Martijn van Beurden X-Patchwork-Id: 36964 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a21:1649:b0:8b:613a:194d with SMTP id no9csp2848109pzb; Tue, 26 Jul 2022 12:41:39 -0700 (PDT) X-Google-Smtp-Source: AGRyM1vk8b462d4+BLve7ZXmcgWlZJULuLYSH0ZXmQTQTeAA0qGJIZkLI2IB8eReNylZb8G4+Vc/ X-Received: by 2002:a05:6402:345a:b0:43c:abfe:5b75 with SMTP id l26-20020a056402345a00b0043cabfe5b75mr450551edc.416.1658864498898; Tue, 26 Jul 2022 12:41:38 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1658864498; cv=none; d=google.com; s=arc-20160816; b=MwQRjxiPujUx02pkZazVyNGgIsj16ve5SHElfX3fQZX70RkdCaGCdU9hunUp41nSnU UNCYNba5lvY9gWkUmEgsnxUlL71lsF14uifeuFOzZY1g/zToX2NAp/CeHBpUKimg6gS4 oRvlR+9WeXZiVPiDkGN29VJtuxf914hkAXDWbnJZP+ibkOeeCyfmLj9AG/+1TQK2Q0Ys hR8v/Zbyv+en4sgT5WRrwy9oJSfMLOVYy+wQlMY/Zhz0w/N9I+xYKd+sH3VykuHfiu9X sRbBSGJwDlEw7zU9224cIu9aFXfto6A1XiYdh5UdLhejcW1s946sTF0HSLVKfWCVoiRt 5GAg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:mime-version:references:in-reply-to :message-id:date:to:from:dkim-signature:delivered-to; bh=XnndafglbZ9gpR57suYZtdKwMguIoSMZoQneV+QV5kk=; b=GGAjyetFQL/izoRiM60Kx+861dZ3npXRNUyOQkUj8MLpwNgIC3Bnoz9hpG9bdBfnzR 0EDtckgaEPaVI7ZiGc1MMiDf9ruX9mrtKFF1ZVmu4y02DnRj7O+N0sWCOcb2jTfN1zeh h8dxbCj2u8cfe8lS3fHnpc4Zr2f39GkExI2KHjtlfjkzuULAa8SMkb6UFUdAcDzgxC0p 5nuIq7NbTiMSeFVSMVGXXdsQSqQfWr2U7XhDcBOXTmCEgI0md+9pkVjB2XfMZZ0GsNQj Ecbaa1gN+a6dFSbhaL/V48PpgmVId61djdZnwD+o0X5GUaB8DRaErtwYxvCIa2TyZvbh kzYw== ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@gmail.com header.s=20210112 header.b=f4hPhi6U; 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; dmarc=fail (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id dn15-20020a17090794cf00b0072a605a57e8si17033186ejc.684.2022.07.26.12.41.38; Tue, 26 Jul 2022 12:41:38 -0700 (PDT) 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=@gmail.com header.s=20210112 header.b=f4hPhi6U; 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; dmarc=fail (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 205BD68B889; Tue, 26 Jul 2022 22:41:35 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-ed1-f50.google.com (mail-ed1-f50.google.com [209.85.208.50]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 4898468B868 for ; Tue, 26 Jul 2022 22:41:28 +0300 (EEST) Received: by mail-ed1-f50.google.com with SMTP id z15so7102447edc.7 for ; Tue, 26 Jul 2022 12:41:28 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=5IlAHM22npJi81Kr2O16ji82xLl0LWQvYyaEhuFFbC4=; b=f4hPhi6UIdSe78qD4mglafcP3kqo3OnEssbfIf6IvK7GJhp1/tAhbAQ8HShR9uDNGS 5l/d52ZUjp98wVrc/8hbAL4JBkAG5iCnShdikgB/CuiZcx2H0zAYZ+gDCQxxg4bFfU47 gfKqC+2LaTjTH/tW956DGyZO8IkMSEFjM81LcH175E84TfAB4TI8IqS7fiU8D33DibeF erXIhIrY9BPBmN524hVY6tf9lIVXXTtL4ccYb8Y6GjLWtWyrmecUhxjM+QBwgwO+fkLc L6ZvECQUz4k0WVh6jj12NgNMRfBZlIe5RjwGdiKvFRkFyQWhqSZBml+t3cPCHBlizOPG 7JNA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=5IlAHM22npJi81Kr2O16ji82xLl0LWQvYyaEhuFFbC4=; b=5EOMehBtB+mwQiW7KHvLxLHaVXbP0B48TN3sF5Bvl6ukCkShBynNT1XmKZxuBZ78c1 jvY/LST06sEsX+ZhW5JWDbOKX86Ci2/F0ji6OvmPiSwQoD5qYYRG8fqlezToBUzhFLRs SpFkvAY+xQLWNgniRYJGKLrtArGLv5XI7KkiAvD7n8y6k+4rInl3+uxdhPrQnBUsuePD hEiVRZgnc08ZW0A7wIs5KOIwVjSGzLoR3CaYL1uIabq+z2M6mEzPdVFpZ4rlFErhYXSj 90SgSKYQV3Y+FoxcJgEawlf08PkUc3suxKzxiX0g9VXWp1ZLs40RwKlUD/BjhY2kJOka r8yA== X-Gm-Message-State: AJIora+SPA1i59vUWx075lzwMvAyKY3fvfXuxNip9cyYcD025+Y/qz28 xL2W5p8D/pNQGa+epFkVQd2cYAoesoMh/w== X-Received: by 2002:a05:6402:34c8:b0:43b:e7b1:353c with SMTP id w8-20020a05640234c800b0043be7b1353cmr14787674edc.171.1658864487372; Tue, 26 Jul 2022 12:41:27 -0700 (PDT) Received: from localhost.localdomain (92-64-99-37.biz.kpn.net. [92.64.99.37]) by smtp.googlemail.com with ESMTPSA id l12-20020aa7cacc000000b0043bc300c499sm8817341edt.79.2022.07.26.12.41.26 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 26 Jul 2022 12:41:27 -0700 (PDT) From: Martijn van Beurden To: ffmpeg-devel@ffmpeg.org Date: Tue, 26 Jul 2022 21:41:06 +0200 Message-Id: <20220726194107.316153-2-mvanb1@gmail.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20220726194107.316153-1-mvanb1@gmail.com> References: <20220726194107.316153-1-mvanb1@gmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 1/2] libavcodec/flacdec: Implement decoding of 32 bit-per-sample PCM 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 Cc: Martijn van Beurden Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: AuX35m7q9ti3 Add decoding of FLAC files coding for 32 bit-per-sample PCM to libavcodec. --- libavcodec/flac.c | 4 +- libavcodec/flacdec.c | 248 ++++++++++++++++++++++++++++++++++++++---- libavcodec/get_bits.h | 12 ++ libavcodec/mathops.h | 9 ++ 4 files changed, 250 insertions(+), 23 deletions(-) diff --git a/libavcodec/flac.c b/libavcodec/flac.c index dd68830622..f326d8fa5c 100644 --- a/libavcodec/flac.c +++ b/libavcodec/flac.c @@ -27,7 +27,7 @@ #include "flac.h" #include "flacdata.h" -static const int8_t sample_size_table[] = { 0, 8, 12, 0, 16, 20, 24, 0 }; +static const int8_t sample_size_table[] = { 0, 8, 12, 0, 16, 20, 24, 32 }; static const AVChannelLayout flac_channel_layouts[8] = { AV_CHANNEL_LAYOUT_MONO, @@ -81,7 +81,7 @@ int ff_flac_decode_frame_header(AVCodecContext *avctx, GetBitContext *gb, /* bits per sample */ bps_code = get_bits(gb, 3); - if (bps_code == 3 || bps_code == 7) { + if (bps_code == 3) { av_log(avctx, AV_LOG_ERROR + log_level_offset, "invalid sample size code (%d)\n", bps_code); diff --git a/libavcodec/flacdec.c b/libavcodec/flacdec.c index 17f1821c50..403cfa419e 100644 --- a/libavcodec/flacdec.c +++ b/libavcodec/flacdec.c @@ -63,6 +63,9 @@ typedef struct FLACContext { int32_t *decoded[FLAC_MAX_CHANNELS]; ///< decoded samples uint8_t *decoded_buffer; unsigned int decoded_buffer_size; + int64_t *decoded_33bps; ///< decoded samples for a 33 bps subframe + uint8_t *decoded_buffer_33bps; + unsigned int decoded_buffer_size_33bps; int buggy_lpc; ///< use workaround for old lavc encoded files FLACDSPContext dsp; @@ -154,6 +157,24 @@ static int allocate_buffers(FLACContext *s) s->flac_stream_info.channels, s->flac_stream_info.max_blocksize, AV_SAMPLE_FMT_S32P, 0); + if (ret >= 0 && s->flac_stream_info.bps == 32 && s->flac_stream_info.channels == 2) { + buf_size = av_samples_get_buffer_size(NULL, 1, + s->flac_stream_info.max_blocksize, + AV_SAMPLE_FMT_S64P, 0); + if (buf_size < 0) + return buf_size; + + av_fast_malloc(&s->decoded_buffer_33bps, &s->decoded_buffer_size_33bps, buf_size); + if (!s->decoded_buffer) + return AVERROR(ENOMEM); + + ret = av_samples_fill_arrays((uint8_t **)&s->decoded_33bps, NULL, + s->decoded_buffer_33bps, + 1, + s->flac_stream_info.max_blocksize, + AV_SAMPLE_FMT_S64P, 0); + + } return ret < 0 ? ret : 0; } @@ -331,6 +352,94 @@ static int decode_subframe_fixed(FLACContext *s, int32_t *decoded, return 0; } +static int decode_subframe_fixed_wide(FLACContext *s, int32_t *decoded, + int pred_order, int bps) +{ + const int blocksize = s->blocksize; + int i; + int ret; + + /* warm up samples */ + for (i = 0; i < pred_order; i++) { + decoded[i] = get_sbits_long(&s->gb, bps); + } + + if ((ret = decode_residuals(s, decoded, pred_order)) < 0) + return ret; + + switch (pred_order) { + case 0: + break; + case 1: + for (i = pred_order; i < blocksize; i++) + decoded[i] += decoded[i-1]; + break; + case 2: + for (i = pred_order; i < blocksize; i++) + decoded[i] = (int64_t)decoded[i] + 2*(int64_t)decoded[i-1] - (int64_t)decoded[i-2]; + break; + case 3: + for (i = pred_order; i < blocksize; i++) + decoded[i] = (int64_t)decoded[i] + 3*(int64_t)decoded[i-1] - 3*(int64_t)decoded[i-2] + (int64_t)decoded[i-3]; + break; + case 4: + for (i = pred_order; i < blocksize; i++) + decoded[i] = (int64_t)decoded[i] + 4*(int64_t)decoded[i-1] - 6*(int64_t)decoded[i-2] + 4*(int64_t)decoded[i-3] - (int64_t)decoded[i-4]; + break; + default: + av_log(s->avctx, AV_LOG_ERROR, "illegal pred order %d\n", pred_order); + return AVERROR_INVALIDDATA; + } + + return 0; +} + + +static int decode_subframe_fixed_33bps(FLACContext *s, int64_t *decoded, + int32_t *residual, int pred_order) +{ + const int blocksize = s->blocksize; + int i; + int ret; + + /* warm up samples */ + for (i = 0; i < pred_order; i++) { + decoded[i] = get_sbits64(&s->gb, 33); + av_log(s->avctx, AV_LOG_DEBUG, "warm-up %d = %" PRId64 "\n", i, decoded[i]); + } + + if ((ret = decode_residuals(s, residual, pred_order)) < 0) + return ret; + + switch (pred_order) { + case 0: + for (i = pred_order; i < blocksize; i++) + decoded[i] = residual[i]; + break; + case 1: + for (i = pred_order; i < blocksize; i++) + decoded[i] = residual[i] + decoded[i-1]; + break; + case 2: + for (i = pred_order; i < blocksize; i++) + decoded[i] = residual[i] + 2*decoded[i-1] - decoded[i-2]; + break; + case 3: + for (i = pred_order; i < blocksize; i++) + decoded[i] = residual[i] + 3*decoded[i-1] - 3*decoded[i-2] + decoded[i-3]; + break; + case 4: + for (i = pred_order; i < blocksize; i++) + decoded[i] = residual[i] + 4*decoded[i-1] - 6*decoded[i-2] + 4*decoded[i-3] - decoded[i-4]; + break; + default: + av_log(s->avctx, AV_LOG_ERROR, "illegal pred order %d\n", pred_order); + return AVERROR_INVALIDDATA; + } + + return 0; +} + static void lpc_analyze_remodulate(SUINT32 *decoded, const int coeffs[32], int order, int qlevel, int len, int bps) { @@ -402,12 +511,53 @@ static int decode_subframe_lpc(FLACContext *s, int32_t *decoded, int pred_order, return 0; } +static int decode_subframe_lpc_33bps(FLACContext *s, int64_t *decoded, + int32_t *residual, int pred_order) +{ + int i, j, ret; + int coeff_prec, qlevel; + int coeffs[32]; + + /* warm up samples */ + for (i = 0; i < pred_order; i++) { + decoded[i] = get_sbits64(&s->gb, 33); + } + + coeff_prec = get_bits(&s->gb, 4) + 1; + if (coeff_prec == 16) { + av_log(s->avctx, AV_LOG_ERROR, "invalid coeff precision\n"); + return AVERROR_INVALIDDATA; + } + qlevel = get_sbits(&s->gb, 5); + if (qlevel < 0) { + av_log(s->avctx, AV_LOG_ERROR, "qlevel %d not supported, maybe buggy stream\n", + qlevel); + return AVERROR_INVALIDDATA; + } + + for (i = 0; i < pred_order; i++) { + coeffs[pred_order - i - 1] = get_sbits(&s->gb, coeff_prec); + } + + if ((ret = decode_residuals(s, residual, pred_order)) < 0) + return ret; + + for (i = pred_order; i < s->blocksize; i++, decoded++) { + int64_t sum = 0; + for (j = 0; j < pred_order; j++) + sum += (int64_t)coeffs[j] * decoded[j]; + decoded[j] = residual[i] + (sum >> qlevel); + } + + return 0; +} + static inline int decode_subframe(FLACContext *s, int channel) { int32_t *decoded = s->decoded[channel]; int type, wasted = 0; int bps = s->flac_stream_info.bps; - int i, tmp, ret; + int i, ret; if (channel == 0) { if (s->ch_mode == FLAC_CHMODE_RIGHT_SIDE) @@ -436,34 +586,63 @@ static inline int decode_subframe(FLACContext *s, int channel) wasted = 1 + get_unary(&s->gb, 1, get_bits_left(&s->gb)); bps -= wasted; } - if (bps > 32) { - avpriv_report_missing_feature(s->avctx, "Decorrelated bit depth > 32"); - return AVERROR_PATCHWELCOME; - } //FIXME use av_log2 for types if (type == 0) { - tmp = get_sbits_long(&s->gb, bps); - for (i = 0; i < s->blocksize; i++) - decoded[i] = tmp; + if (bps < 33) { + int32_t tmp = get_sbits_long(&s->gb, bps); + for (i = 0; i < s->blocksize; i++) + decoded[i] = tmp; + } else { + int64_t tmp = get_sbits64(&s->gb, 33); + for (i = 0; i < s->blocksize; i++) + s->decoded_33bps[i] = tmp; + } } else if (type == 1) { - for (i = 0; i < s->blocksize; i++) - decoded[i] = get_sbits_long(&s->gb, bps); + if (bps < 33) { + for (i = 0; i < s->blocksize; i++) + decoded[i] = get_sbits_long(&s->gb, bps); + } else { + for (i = 0; i < s->blocksize; i++) + s->decoded_33bps[i] = get_sbits64(&s->gb, 33); + } } else if ((type >= 8) && (type <= 12)) { - if ((ret = decode_subframe_fixed(s, decoded, type & ~0x8, bps)) < 0) - return ret; + int order = type & ~0x8; + if (bps < 33) { + if (bps + order <= 32) { + if ((ret = decode_subframe_fixed(s, decoded, order, bps)) < 0) + return ret; + } else { + if ((ret = decode_subframe_fixed_wide(s, decoded, order, bps)) < 0) + return ret; + } + } else { + if ((ret = decode_subframe_fixed_33bps(s, s->decoded_33bps, decoded, order)) < 0) + return ret; + } } else if (type >= 32) { - if ((ret = decode_subframe_lpc(s, decoded, (type & ~0x20)+1, bps)) < 0) - return ret; + if (bps < 33) { + if ((ret = decode_subframe_lpc(s, decoded, (type & ~0x20)+1, bps)) < 0) + return ret; + } else { + if ((ret = decode_subframe_lpc_33bps(s, s->decoded_33bps, decoded, (type & ~0x20)+1)) < 0) + return ret; + } } else { av_log(s->avctx, AV_LOG_ERROR, "invalid coding type\n"); return AVERROR_INVALIDDATA; } - if (wasted && wasted < 32) { - int i; - for (i = 0; i < s->blocksize; i++) - decoded[i] = (unsigned)decoded[i] << wasted; + if (wasted) { + if (wasted+bps == 33) { + int i; + for (i = 0; i < s->blocksize; i++) + s->decoded_33bps[i] = (uint64_t)decoded[i] << wasted; + } else if (wasted < 32) { + int i; + for (i = 0; i < s->blocksize; i++) + decoded[i] = (unsigned)decoded[i] << wasted; + } } return 0; @@ -554,6 +733,26 @@ static int decode_frame(FLACContext *s) return 0; } +static void decorrelate_33bps(int ch_mode, int32_t **decoded, int64_t *decoded_33bps, int len) +{ + int i; + if (ch_mode == FLAC_CHMODE_LEFT_SIDE ) { + for (i = 0; i < len; i++) + decoded[1][i] = decoded[0][i] - decoded_33bps[i]; + } else if (ch_mode == FLAC_CHMODE_RIGHT_SIDE ) { + for (i = 0; i < len; i++) + decoded[0][i] = decoded[1][i] + decoded_33bps[i]; + } else if (ch_mode == FLAC_CHMODE_MID_SIDE ) { + for (i = 0; i < len; i++) { + uint64_t a = decoded[0][i]; + int64_t b = decoded_33bps[i]; + a -= b >> 1; + decoded[0][i] = (a + b); + decoded[1][i] = a; + } + } +} + static int flac_decode_frame(AVCodecContext *avctx, AVFrame *frame, int *got_frame_ptr, AVPacket *avpkt) { @@ -618,9 +817,15 @@ static int flac_decode_frame(AVCodecContext *avctx, AVFrame *frame, if ((ret = ff_thread_get_buffer(avctx, frame, 0)) < 0) return ret; - s->dsp.decorrelate[s->ch_mode](frame->data, s->decoded, - s->flac_stream_info.channels, - s->blocksize, s->sample_shift); + if (s->flac_stream_info.bps == 32 && s->ch_mode > 0) { + decorrelate_33bps(s->ch_mode, s->decoded, s->decoded_33bps, s->blocksize); + s->dsp.decorrelate[0](frame->data, s->decoded, s->flac_stream_info.channels, + s->blocksize, s->sample_shift); + } else { + s->dsp.decorrelate[s->ch_mode](frame->data, s->decoded, + s->flac_stream_info.channels, + s->blocksize, s->sample_shift); + } if (bytes_read > buf_size) { av_log(s->avctx, AV_LOG_ERROR, "overread: %d\n", bytes_read - buf_size); @@ -641,6 +846,7 @@ static av_cold int flac_decode_close(AVCodecContext *avctx) FLACContext *s = avctx->priv_data; av_freep(&s->decoded_buffer); + av_freep(&s->decoded_buffer_33bps); return 0; } diff --git a/libavcodec/get_bits.h b/libavcodec/get_bits.h index 992765dc92..52d13b8242 100644 --- a/libavcodec/get_bits.h +++ b/libavcodec/get_bits.h @@ -596,6 +596,18 @@ static inline int get_sbits_long(GetBitContext *s, int n) return sign_extend(get_bits_long(s, n), n); } +/** + * Read 0-64 bits as a signed integer. + */ +static inline int64_t get_sbits64(GetBitContext *s, int n) +{ + // sign_extend(x, 0) is undefined + if (!n) + return 0; + + return sign_extend64(get_bits64(s, n), n); +} + /** * Show 0-32 bits. */ diff --git a/libavcodec/mathops.h b/libavcodec/mathops.h index f81d21f9c4..8a82d9d086 100644 --- a/libavcodec/mathops.h +++ b/libavcodec/mathops.h @@ -137,6 +137,15 @@ static inline av_const int sign_extend(int val, unsigned bits) } #endif +#ifndef sign_extend64 +static inline av_const int64_t sign_extend64(int64_t val, unsigned bits) +{ + unsigned shift = 8 * sizeof(int64_t) - bits; + union { uint64_t u; int64_t s; } v = { (uint64_t) val << shift }; + return v.s >> shift; +} +#endif + #ifndef zero_extend static inline av_const unsigned zero_extend(unsigned val, unsigned bits) { From patchwork Tue Jul 26 19:41:07 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Martijn van Beurden X-Patchwork-Id: 36965 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a21:1649:b0:8b:613a:194d with SMTP id no9csp2848169pzb; Tue, 26 Jul 2022 12:41:48 -0700 (PDT) X-Google-Smtp-Source: AGRyM1si5rjLwh4mdWfFszrDCoFBT04k87WWrHoX0e4R4DGqvkayqHA2vd30mtFKSlyChi2eDWDs X-Received: by 2002:a05:6402:1f06:b0:43c:23c5:d879 with SMTP id b6-20020a0564021f0600b0043c23c5d879mr8973238edb.24.1658864508268; Tue, 26 Jul 2022 12:41:48 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1658864508; cv=none; d=google.com; s=arc-20160816; b=QuYXe7HEz/xQ73D2lCDf8ssFKD2rFkYRl1lzwSMt5aQTb8dgJVs/XsmM/39kcLm1E2 C+3gNYZ0JRwWbus9Ke5Fz5uS5Pojg2SSLjlX6Zg9AQGlsjffZOrtgLaxZ2CCHnu5YHHK 42Tsdk+5fyEHHbdSqPZ/U26/lCKp9wAGim8C4zV88ZZ0YWqM3jK4u6J5irpkzvRPPHkt 25kiMAzyQ/mtCBLzW0TxM5OVlPCjQ5vnSc9v4klpV3oCmd3LzAFJs+jiE86Ak5h3a1oP R6pQ/m1VjAK3CDxGZNKDh67gSOKjuCFULFC+/brrDEWNzvxE4zo5OklSCEcCYut6BggM 8ioA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:mime-version:references:in-reply-to :message-id:date:to:from:dkim-signature:delivered-to; bh=vTnVhExpxT8/Ccnwm9ND1KdHy0jrXCGOiN+PxN+4Ovw=; b=jO+V6HamW2+IrYoN+YWBp47UFrmyt76pD8q0kSiqJ8/YAk6FjZf/Sh5GfzIZIqscHn 1o/rogk//SqX50c8nLvw9M0wE2TqsDuwOWBbkpPLm+78qIQ4JVqo4WmmOApYGJpyQQsD jdNLc3YEJa6U7S+fqftIXYlzh2ZqzERPW1LYF/BKZ+Iw3IVruWJKEwsuoSiEqHWsWeFI gfghwkucVE1M5bdTA+csazuzOZlaLcPrZQAoHuxhiVm28BMhPyr1JcidlJG4knp8cA11 jDZ2yapwDKtnhowQMh+QOH6fhN78geprK/Aomg3PdzH5sk9hqDC8HMvhUElpQAvJe8NB +BGw== ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@gmail.com header.s=20210112 header.b=G7qiYu5F; 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; dmarc=fail (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id hr21-20020a1709073f9500b0072b88d59ce5si17565740ejc.461.2022.07.26.12.41.47; Tue, 26 Jul 2022 12:41:48 -0700 (PDT) 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=@gmail.com header.s=20210112 header.b=G7qiYu5F; 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; dmarc=fail (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 25ED368B894; Tue, 26 Jul 2022 22:41:44 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-ej1-f52.google.com (mail-ej1-f52.google.com [209.85.218.52]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 9603668B87D for ; Tue, 26 Jul 2022 22:41:37 +0300 (EEST) Received: by mail-ej1-f52.google.com with SMTP id ez10so27827090ejc.13 for ; Tue, 26 Jul 2022 12:41:37 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=OneDYxUqPBaSdLqp0c1UhtOeQ6yl098T4wx+4tKL7+M=; b=G7qiYu5FhLhsWHyD4cOyf1hlV9OdXMfJdxTkjUAG9yeZf2+0HFQENgO+1KFsM6TtWN 65b3wxRpm2nBl7/Y/mZprUGkYjFl+8LNfM3UEn82PlMyRBFd2lGk2sEXbc9w7g7wgYVJ xrRcOq6+nokgPWCODlmk8m7ao+YBbq9G88xAesOUFZWczLtCt0S1fG/TcUHQStFuuuHe 1feXqr1mOlUJhQ4SAZ7eOVCUlS2dxRsPml8bPVts3Uj4SL1PjG44nWfu6X2dmpPRityG y9Cz8FWu73IugHM2Uv0ctK5olSx1Tpnf1HqoCxG3cPxVfrEgM7vJK8ySNIZ6pS66lIw9 9P4g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=OneDYxUqPBaSdLqp0c1UhtOeQ6yl098T4wx+4tKL7+M=; b=3k+1E81N4o3IxoNk3AmeD3BCsK/Tc8xCPL1n8GY5kXSq6JNETfaiWNpQs2eapt0bBX +agB+OzZwfMe3c64kGqMAViVShMHu0cJwIqLt1gz5gDGq0HZnYqkMDYkj9/f5Ua/tf6F YtP7xE7JrB8Hob4qR5rlfXWG7bX9Hme/e2JQh/ihHYROBqHyMh17PzdGJEPm1vHSF86x LO/ZGuS30f2jStK9Ua2MBfSiRwhaHyNbgJbmCQputx5PnZJQGk/yKW85ujL0dErCPOFb l32pXoqri52dluGh3+w+H6bW+XX7OqXg68npY+M5kAMYCR88xPTVDQA+yJ2NNnvoNbug rq8w== X-Gm-Message-State: AJIora9I3tgj8mmQxiZInwsqiE3W1K0Z6nbhSWNaz9ODBSXxMZRVajne 8QxyKZcMK7T2xaqSzR425nqUFBpaFc1BrQ== X-Received: by 2002:a17:907:2c44:b0:72b:6160:c64c with SMTP id hf4-20020a1709072c4400b0072b6160c64cmr15614834ejc.55.1658864496707; Tue, 26 Jul 2022 12:41:36 -0700 (PDT) Received: from localhost.localdomain (92-64-99-37.biz.kpn.net. [92.64.99.37]) by smtp.googlemail.com with ESMTPSA id l12-20020aa7cacc000000b0043bc300c499sm8817341edt.79.2022.07.26.12.41.36 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 26 Jul 2022 12:41:36 -0700 (PDT) From: Martijn van Beurden To: ffmpeg-devel@ffmpeg.org Date: Tue, 26 Jul 2022 21:41:07 +0200 Message-Id: <20220726194107.316153-3-mvanb1@gmail.com> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20220726194107.316153-1-mvanb1@gmail.com> References: <20220726194107.316153-1-mvanb1@gmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 2/2] libavcodec/flacenc: Implement encoding of 32 bit-per-sample PCM 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 Cc: Martijn van Beurden Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: Nf88jIC4Vq+p Add encoding of 32 bit-per-sample PCM to FLAC files to libavcodec. Coding to this format is at this point considered experimental and -strict -2 is needed to get ffmpeg to encode such files. --- libavcodec/flacenc.c | 499 ++++++++++++++++++++++++++++++++-------- libavcodec/put_bits.h | 7 + libavcodec/put_golomb.h | 19 +- 3 files changed, 418 insertions(+), 107 deletions(-) diff --git a/libavcodec/flacenc.c b/libavcodec/flacenc.c index 9350e42dbc..4ed0a3961a 100644 --- a/libavcodec/flacenc.c +++ b/libavcodec/flacenc.c @@ -96,6 +96,7 @@ typedef struct FlacSubframe { typedef struct FlacFrame { FlacSubframe subframes[FLAC_MAX_CHANNELS]; + int64_t samples_33bps[FLAC_MAX_BLOCKSIZE]; int blocksize; int bs_code[2]; uint8_t crc8; @@ -255,10 +256,23 @@ static av_cold int flac_encode_init(AVCodecContext *avctx) s->bps_code = 4; break; case AV_SAMPLE_FMT_S32: - if (avctx->bits_per_raw_sample != 24) - av_log(avctx, AV_LOG_WARNING, "encoding as 24 bits-per-sample\n"); - avctx->bits_per_raw_sample = 24; - s->bps_code = 6; + if (avctx->bits_per_raw_sample <= 24) { + if (avctx->bits_per_raw_sample < 24) + av_log(avctx, AV_LOG_WARNING, "encoding as 24 bits-per-sample\n"); + avctx->bits_per_raw_sample = 24; + s->bps_code = 6; + } else if (avctx->strict_std_compliance > FF_COMPLIANCE_EXPERIMENTAL) { + av_log(avctx, AV_LOG_WARNING, + "encoding as 24 bits-per-sample, more is considered " + "experimental. Add -strict %d if you want to encode " + "more than 24 bits-per-sample\n", + FF_COMPLIANCE_EXPERIMENTAL); + avctx->bits_per_raw_sample = 24; + s->bps_code = 6; + } else { + avctx->bits_per_raw_sample = 32; + s->bps_code = 7; + } break; } @@ -507,8 +521,7 @@ static uint64_t rice_count_exact(const int32_t *res, int n, int k) uint64_t count = 0; for (i = 0; i < n; i++) { - int32_t v = -2 * res[i] - 1; - v ^= v >> 31; + unsigned v = ((unsigned)(res[i]) << 1) ^ (res[i] >> 31); count += (v >> k) + 1 + k; } return count; @@ -687,8 +700,8 @@ static uint64_t calc_rice_params(RiceContext *rc, tmp_rc.coding_mode = rc->coding_mode; - for (i = 0; i < n; i++) - udata[i] = (2 * data[i]) ^ (data[i] >> 31); + for (i = pred_order; i < n; i++) + udata[i] = ((unsigned)(data[i]) << 1) ^ (data[i] >> 31); calc_sum_top(pmax, exact ? kmax : 0, udata, n, pred_order, sums); @@ -786,6 +799,180 @@ static void encode_residual_fixed(int32_t *res, const int32_t *smp, int n, } +static int encode_residual_fixed_with_residual_limit(int32_t *res, const int32_t *smp, + int n, int order) +{ + /* This function checks for every residual whether it can be + * contained in INT32_MAX) + return 1; + res[i] = res64; + } + } else if (order == 2) { + for (i = order; i < n; i++) { + res64 = (int64_t)smp[i] - 2*(int64_t)smp[i-1] + smp[i-2]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } else if (order == 3) { + for (i = order; i < n; i++) { + res64 = (int64_t)smp[i] - 3*(int64_t)smp[i-1] + 3*(int64_t)smp[i-2] - smp[i-3]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } else { + for (i = order; i < n; i++) { + res64 = (int64_t)smp[i] - 4*(int64_t)smp[i-1] + 6*(int64_t)smp[i-2] - 4*(int64_t)smp[i-3] + smp[i-4]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } + return 0; +} + + +static int encode_residual_fixed_with_residual_limit_33bps(int32_t *res, const int64_t *smp, + int n, int order) +{ + /* This function checks for every residual whether it can be + * contained in INT32_MAX) + return 1; + res[i] = smp[i]; + } + } else if (order == 1) { + for (i = order; i < n; i++) { + res64 = smp[i] - smp[i-1]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } else if (order == 2) { + for (i = order; i < n; i++) { + res64 = smp[i] - 2*smp[i-1] + smp[i-2]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } else if (order == 3) { + for (i = order; i < n; i++) { + res64 = smp[i] - 3*smp[i-1] + 3*smp[i-2] - smp[i-3]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } else { + for (i = order; i < n; i++) { + res64 = smp[i] - 4*smp[i-1] + 6*smp[i-2] - 4*smp[i-3] + smp[i-4]; + if (res64 <= INT32_MIN || res64 > INT32_MAX) + return 1; + res[i] = res64; + } + } + return 0; +} + + +static int lpc_encode_with_residual_limit(int32_t *res, const int32_t *smp, int len, + int order, int32_t *coefs, int shift) +{ + /* This function checks for every residual whether it can be + * contained in >= shift; + tmp = smp[i] - p; + if (tmp <= INT32_MIN || tmp > INT32_MAX) + return 1; + res[i] = tmp; + } + return 0; +} + +static int lpc_encode_with_residual_limit_33bps(int32_t *res, const int64_t *smp, int len, + int order, int32_t *coefs, int shift) +{ + /* This function checks for every residual whether it can be + * contained in >= shift; + tmp = smp[i] - p; + if (tmp <= INT32_MIN || tmp > INT32_MAX) + return 1; + res[i] = tmp; + } + return 0; +} + +static int lpc_encode_choose_datapath(FlacEncodeContext *s, int32_t bps, + int32_t *res, const int32_t *smp, + const int64_t *smp_33bps, int len, + int order, int32_t *coefs, int shift) +{ + uint64_t max_residual_value = 0; + int64_t max_sample_value = ((int64_t)(1) << (bps-1)); + /* This calculates the max size of any residual with the current + * predictor, so we know whether we need to check the residual */ + for (int i = 0; i < order; i++) + max_residual_value += FFABS(max_sample_value * coefs[i]); + max_residual_value >>= shift; + max_residual_value += max_sample_value; + if (bps > 32) { + if (lpc_encode_with_residual_limit_33bps(res, smp_33bps, len, order, coefs, shift)) + return 1; + } else if (max_residual_value > INT32_MAX) { + if (lpc_encode_with_residual_limit(res, smp, len, order, coefs, shift)) + return 1; + } else if (bps + s->options.lpc_coeff_precision + av_log2(order) <= 32) { + s->flac_dsp.lpc16_encode(res, smp, len, order, coefs, shift); + } else { + s->flac_dsp.lpc32_encode(res, smp, len, order, coefs, shift); + } + return 0; +} + +#define DEFAULT_TO_VERBATIM() \ +{ \ + sub->type = sub->type_code = FLAC_SUBFRAME_VERBATIM; \ + if (sub->obits <= 32) \ + memcpy(res, smp, n * sizeof(int32_t)); \ + return subframe_count_exact(s, sub, 0); \ +} + static int encode_residual_ch(FlacEncodeContext *s, int ch) { int i, n; @@ -795,28 +982,38 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) int32_t coefs[MAX_LPC_ORDER][MAX_LPC_ORDER]; int shift[MAX_LPC_ORDER]; int32_t *res, *smp; + int64_t *smp_33bps; - frame = &s->frame; - sub = &frame->subframes[ch]; - res = sub->residual; - smp = sub->samples; - n = frame->blocksize; + frame = &s->frame; + sub = &frame->subframes[ch]; + res = sub->residual; + smp = sub->samples; + smp_33bps = frame->samples_33bps; + n = frame->blocksize; /* CONSTANT */ - for (i = 1; i < n; i++) - if(smp[i] != smp[0]) - break; - if (i == n) { - sub->type = sub->type_code = FLAC_SUBFRAME_CONSTANT; - res[0] = smp[0]; - return subframe_count_exact(s, sub, 0); + if (sub->obits > 32) { + for (i = 1; i < n; i++) + if(smp_33bps[i] != smp_33bps[0]) + break; + if (i == n) { + sub->type = sub->type_code = FLAC_SUBFRAME_CONSTANT; + return subframe_count_exact(s, sub, 0); + } + } else { + for (i = 1; i < n; i++) + if(smp[i] != smp[0]) + break; + if (i == n) { + sub->type = sub->type_code = FLAC_SUBFRAME_CONSTANT; + res[0] = smp[0]; + return subframe_count_exact(s, sub, 0); + } } /* VERBATIM */ if (frame->verbatim_only || n < 5) { - sub->type = sub->type_code = FLAC_SUBFRAME_VERBATIM; - memcpy(res, smp, n * sizeof(int32_t)); - return subframe_count_exact(s, sub, 0); + DEFAULT_TO_VERBATIM(); } min_order = s->options.min_prediction_order; @@ -833,15 +1030,32 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) opt_order = 0; bits[0] = UINT32_MAX; for (i = min_order; i <= max_order; i++) { - encode_residual_fixed(res, smp, n, i); + if (sub->obits == 33) { + if (encode_residual_fixed_with_residual_limit_33bps(res, smp_33bps, n, i)) + continue; + } else if (sub->obits + i >= 32) { + if (encode_residual_fixed_with_residual_limit(res, smp, n, i)) + continue; + } else + encode_residual_fixed(res, smp, n, i); bits[i] = find_subframe_rice_params(s, sub, i); if (bits[i] < bits[opt_order]) opt_order = i; } + if (opt_order == 0 && bits[0] == UINT32_MAX) { + /* No predictor found with residuals within order = opt_order; sub->type_code = sub->type | sub->order; if (sub->order != max_order) { - encode_residual_fixed(res, smp, n, sub->order); + if (sub->obits == 33) + encode_residual_fixed_with_residual_limit_33bps(res, smp_33bps, n, sub->order); + else if (sub->obits + i >= 32) + encode_residual_fixed_with_residual_limit(res, smp, n, sub->order); + else + encode_residual_fixed(res, smp, n, sub->order); find_subframe_rice_params(s, sub, sub->order); } return subframe_count_exact(s, sub, sub->order); @@ -849,6 +1063,14 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) /* LPC */ sub->type = FLAC_SUBFRAME_LPC; + if (sub->obits == 33) + /* As ff_lpc_calc_coefs is shared with other codecs and the LSB + * probably isn't predictable anyway, throw away LSB for analysis + * so it fits 32 bit int and existing function can be used + * unmodified */ + for (i = 0; i < n; i++) + smp[i] = smp_33bps[i] >> 1; + opt_order = ff_lpc_calc_coefs(&s->lpc_ctx, smp, n, min_order, max_order, s->options.lpc_coeff_precision, coefs, shift, s->options.lpc_type, s->options.lpc_passes, omethod, @@ -869,13 +1091,8 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) order = av_clip(order, min_order - 1, max_order - 1); if (order == last_order) continue; - if (s->bps_code * 4 + s->options.lpc_coeff_precision + av_log2(order) <= 32) { - s->flac_dsp.lpc16_encode(res, smp, n, order+1, coefs[order], - shift[order]); - } else { - s->flac_dsp.lpc32_encode(res, smp, n, order+1, coefs[order], - shift[order]); - } + if(lpc_encode_choose_datapath(s, sub->obits, res, smp, smp_33bps, n, i+1, coefs[i], shift[i])) + continue; bits[i] = find_subframe_rice_params(s, sub, order+1); if (bits[i] < bits[opt_index]) { opt_index = i; @@ -889,11 +1106,8 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) opt_order = 0; bits[0] = UINT32_MAX; for (i = min_order-1; i < max_order; i++) { - if (s->bps_code * 4 + s->options.lpc_coeff_precision + av_log2(i) <= 32) { - s->flac_dsp.lpc16_encode(res, smp, n, i+1, coefs[i], shift[i]); - } else { - s->flac_dsp.lpc32_encode(res, smp, n, i+1, coefs[i], shift[i]); - } + if(lpc_encode_choose_datapath(s, sub->obits, res, smp, smp_33bps, n, i+1, coefs[i], shift[i])) + continue; bits[i] = find_subframe_rice_params(s, sub, i+1); if (bits[i] < bits[opt_order]) opt_order = i; @@ -911,11 +1125,8 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) for (i = last-step; i <= last+step; i += step) { if (i < min_order-1 || i >= max_order || bits[i] < UINT32_MAX) continue; - if (s->bps_code * 4 + s->options.lpc_coeff_precision + av_log2(i) <= 32) { - s->flac_dsp.lpc32_encode(res, smp, n, i+1, coefs[i], shift[i]); - } else { - s->flac_dsp.lpc16_encode(res, smp, n, i+1, coefs[i], shift[i]); - } + if(lpc_encode_choose_datapath(s, sub->obits, res, smp, smp_33bps, n, i+1, coefs[i], shift[i])) + continue; bits[i] = find_subframe_rice_params(s, sub, i+1); if (bits[i] < bits[opt_order]) opt_order = i; @@ -952,11 +1163,8 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) if (diffsum >8) continue; - if (s->bps_code * 4 + s->options.lpc_coeff_precision + av_log2(opt_order - 1) <= 32) { - s->flac_dsp.lpc16_encode(res, smp, n, opt_order, lpc_try, shift[opt_order-1]); - } else { - s->flac_dsp.lpc32_encode(res, smp, n, opt_order, lpc_try, shift[opt_order-1]); - } + if(lpc_encode_choose_datapath(s, sub->obits, res, smp, smp_33bps, n, i+1, coefs[i], shift[i])) + continue; score = find_subframe_rice_params(s, sub, opt_order); if (score < best_score) { best_score = score; @@ -973,10 +1181,10 @@ static int encode_residual_ch(FlacEncodeContext *s, int ch) for (i = 0; i < sub->order; i++) sub->coefs[i] = coefs[sub->order-1][i]; - if (s->bps_code * 4 + s->options.lpc_coeff_precision + av_log2(opt_order) <= 32) { - s->flac_dsp.lpc16_encode(res, smp, n, sub->order, sub->coefs, sub->shift); - } else { - s->flac_dsp.lpc32_encode(res, smp, n, sub->order, sub->coefs, sub->shift); + if(lpc_encode_choose_datapath(s, sub->obits, res, smp, smp_33bps, n, sub->order, coefs[sub->order-1], shift[sub->order-1])) { + /* No predictor found with residuals within order); @@ -1043,54 +1251,88 @@ static int encode_frame(FlacEncodeContext *s) static void remove_wasted_bits(FlacEncodeContext *s) { - int ch, i; + int ch, i, wasted_bits; for (ch = 0; ch < s->channels; ch++) { FlacSubframe *sub = &s->frame.subframes[ch]; - int32_t v = 0; - for (i = 0; i < s->frame.blocksize; i++) { - v |= sub->samples[i]; - if (v & 1) - break; - } + if (sub->obits > 32) { + int64_t v = 0; + for (i = 0; i < s->frame.blocksize; i++) { + v |= s->frame.samples_33bps[i]; + if (v & 1) + break; + } + + if (!v || (v & 1)) + return; - if (v && !(v & 1)) { v = ff_ctz(v); + /* If any wasted bits are found, samples are moved + * from frame.samples_33bps to frame.subframes[ch] */ for (i = 0; i < s->frame.blocksize; i++) - sub->samples[i] >>= v; + sub->samples[i] = s->frame.samples_33bps[i] >> v; + wasted_bits = v; + } else { + int32_t v = 0; + for (i = 0; i < s->frame.blocksize; i++) { + v |= sub->samples[i]; + if (v & 1) + break; + } + + if (!v || (v & 1)) + return; - sub->wasted = v; - sub->obits -= v; + v = ff_ctz(v); - /* for 24-bit, check if removing wasted bits makes the range better - suited for using RICE instead of RICE2 for entropy coding */ - if (sub->obits <= 17) - sub->rc.coding_mode = CODING_MODE_RICE; + for (i = 0; i < s->frame.blocksize; i++) + sub->samples[i] >>= v; + wasted_bits = v; } + + sub->wasted = wasted_bits; + sub->obits -= wasted_bits; + + /* for 24-bit, check if removing wasted bits makes the range better + * suited for using RICE instead of RICE2 for entropy coding */ + if (sub->obits <= 17) + sub->rc.coding_mode = CODING_MODE_RICE; } } static int estimate_stereo_mode(const int32_t *left_ch, const int32_t *right_ch, int n, - int max_rice_param) + int max_rice_param, int bps) { int i, best; - int32_t lt, rt; uint64_t sum[4]; uint64_t score[4]; int k; /* calculate sum of 2nd order residual for each channel */ sum[0] = sum[1] = sum[2] = sum[3] = 0; - for (i = 2; i < n; i++) { - lt = left_ch[i] - 2*left_ch[i-1] + left_ch[i-2]; - rt = right_ch[i] - 2*right_ch[i-1] + right_ch[i-2]; - sum[2] += FFABS((lt + rt) >> 1); - sum[3] += FFABS(lt - rt); - sum[0] += FFABS(lt); - sum[1] += FFABS(rt); + if(bps < 30) { + int32_t lt, rt; + for (i = 2; i < n; i++) { + lt = left_ch[i] - 2*left_ch[i-1] + left_ch[i-2]; + rt = right_ch[i] - 2*right_ch[i-1] + right_ch[i-2]; + sum[2] += FFABS((lt + rt) >> 1); + sum[3] += FFABS(lt - rt); + sum[0] += FFABS(lt); + sum[1] += FFABS(rt); + } + } else { + int64_t lt, rt; + for (i = 2; i < n; i++) { + lt = (int64_t)left_ch[i] - 2*(int64_t)left_ch[i-1] + left_ch[i-2]; + rt = (int64_t)right_ch[i] - 2*(int64_t)right_ch[i-1] + right_ch[i-2]; + sum[2] += FFABS((lt + rt) >> 1); + sum[3] += FFABS(lt - rt); + sum[0] += FFABS(lt); + sum[1] += FFABS(rt); + } } /* estimate bit counts */ for (i = 0; i < 4; i++) { @@ -1121,12 +1363,14 @@ static void channel_decorrelation(FlacEncodeContext *s) { FlacFrame *frame; int32_t *left, *right; + int64_t *side_33bps; int i, n; - frame = &s->frame; - n = frame->blocksize; - left = frame->subframes[0].samples; - right = frame->subframes[1].samples; + frame = &s->frame; + n = frame->blocksize; + left = frame->subframes[0].samples; + right = frame->subframes[1].samples; + side_33bps = frame->samples_33bps; if (s->channels != 2) { frame->ch_mode = FLAC_CHMODE_INDEPENDENT; @@ -1135,29 +1379,49 @@ static void channel_decorrelation(FlacEncodeContext *s) if (s->options.ch_mode < 0) { int max_rice_param = (1 << frame->subframes[0].rc.coding_mode) - 2; - frame->ch_mode = estimate_stereo_mode(left, right, n, max_rice_param); + frame->ch_mode = estimate_stereo_mode(left, right, n, max_rice_param, s->avctx->bits_per_raw_sample); } else frame->ch_mode = s->options.ch_mode; /* perform decorrelation and adjust bits-per-sample */ if (frame->ch_mode == FLAC_CHMODE_INDEPENDENT) return; - if (frame->ch_mode == FLAC_CHMODE_MID_SIDE) { - int32_t tmp; - for (i = 0; i < n; i++) { - tmp = left[i]; - left[i] = (tmp + right[i]) >> 1; - right[i] = tmp - right[i]; + if(s->avctx->bits_per_raw_sample == 32) { + if (frame->ch_mode == FLAC_CHMODE_MID_SIDE) { + int64_t tmp; + for (i = 0; i < n; i++) { + tmp = left[i]; + left[i] = (tmp + right[i]) >> 1; + side_33bps[i] = tmp - right[i]; + } + frame->subframes[1].obits++; + } else if (frame->ch_mode == FLAC_CHMODE_LEFT_SIDE) { + for (i = 0; i < n; i++) + side_33bps[i] = (int64_t)left[i] - right[i]; + frame->subframes[1].obits++; + } else { + for (i = 0; i < n; i++) + side_33bps[i] = (int64_t)left[i] - right[i]; + frame->subframes[0].obits++; } - frame->subframes[1].obits++; - } else if (frame->ch_mode == FLAC_CHMODE_LEFT_SIDE) { - for (i = 0; i < n; i++) - right[i] = left[i] - right[i]; - frame->subframes[1].obits++; } else { - for (i = 0; i < n; i++) - left[i] -= right[i]; - frame->subframes[0].obits++; + if (frame->ch_mode == FLAC_CHMODE_MID_SIDE) { + int32_t tmp; + for (i = 0; i < n; i++) { + tmp = left[i]; + left[i] = (tmp + right[i]) >> 1; + right[i] = tmp - right[i]; + } + frame->subframes[1].obits++; + } else if (frame->ch_mode == FLAC_CHMODE_LEFT_SIDE) { + for (i = 0; i < n; i++) + right[i] = left[i] - right[i]; + frame->subframes[1].obits++; + } else { + for (i = 0; i < n; i++) + left[i] -= right[i]; + frame->subframes[0].obits++; + } } } @@ -1226,14 +1490,38 @@ static void write_subframes(FlacEncodeContext *s) /* subframe */ if (sub->type == FLAC_SUBFRAME_CONSTANT) { - put_sbits(&s->pb, sub->obits, res[0]); + if(sub->obits == 33) + put_sbits64(&s->pb, 33, s->frame.samples_33bps[0]); + else if(sub->obits == 32) + put_bits32(&s->pb, res[0]); + else + put_sbits(&s->pb, sub->obits, res[0]); } else if (sub->type == FLAC_SUBFRAME_VERBATIM) { - while (res < frame_end) - put_sbits(&s->pb, sub->obits, *res++); + if (sub->obits == 33) { + int64_t *res64 = s->frame.samples_33bps; + int64_t *frame_end64 = &s->frame.samples_33bps[s->frame.blocksize]; + while (res64 < frame_end64) + put_sbits64(&s->pb, 33, (*res64++)); + } else if (sub->obits == 32) { + while (res < frame_end) + put_bits32(&s->pb, *res++); + } else { + while (res < frame_end) + put_sbits(&s->pb, sub->obits, *res++); + } } else { /* warm-up samples */ - for (i = 0; i < sub->order; i++) - put_sbits(&s->pb, sub->obits, *res++); + if (sub->obits == 33) { + for (i = 0; i < sub->order; i++) + put_sbits64(&s->pb, 33, s->frame.samples_33bps[i]); + res += sub->order; + } else if (sub->obits == 32) { + for (i = 0; i < sub->order; i++) + put_bits32(&s->pb, *res++); + } else { + for (i = 0; i < sub->order; i++) + put_sbits(&s->pb, sub->obits, *res++); + } /* LPC coefficients */ if (sub->type == FLAC_SUBFRAME_LPC) { @@ -1258,7 +1546,7 @@ static void write_subframes(FlacEncodeContext *s) int k = sub->rc.params[p]; put_bits(&s->pb, sub->rc.coding_mode, k); while (res < part_end) - set_sr_golomb_flac(&s->pb, *res++, k, INT32_MAX, 0); + set_sr_golomb_flac(&s->pb, *res++, k); part_end = FFMIN(frame_end, part_end + psize); } } @@ -1306,7 +1594,7 @@ static int update_md5_sum(FlacEncodeContext *s, const void *samples) (const uint16_t *) samples, buf_size / 2); buf = s->md5_buffer; #endif - } else { + } else if (s->avctx->bits_per_raw_sample <= 24) { int i; const int32_t *samples0 = samples; uint8_t *tmp = s->md5_buffer; @@ -1316,6 +1604,15 @@ static int update_md5_sum(FlacEncodeContext *s, const void *samples) AV_WL24(tmp + 3*i, v); } buf = s->md5_buffer; + } else { + /* s->avctx->bits_per_raw_sample <= 32 */ + int i; + const int32_t *samples0 = samples; + uint8_t *tmp = s->md5_buffer; + + for (i = 0; i < s->frame.blocksize * s->channels; i++) + AV_WL32(tmp + 4*i, samples0[i]); + buf = s->md5_buffer; } av_md5_update(s->md5ctx, buf, buf_size); diff --git a/libavcodec/put_bits.h b/libavcodec/put_bits.h index 4b4f977ad5..11360fe7a4 100644 --- a/libavcodec/put_bits.h +++ b/libavcodec/put_bits.h @@ -363,6 +363,13 @@ static inline void put_bits64(PutBitContext *s, int n, uint64_t value) } } +static inline void put_sbits64(PutBitContext *pb, int n, int64_t value) +{ + av_assert2(n >= 0 && n <= 64); + + put_bits64(pb, n, (uint64_t)(value) & (~(UINT64_MAX << n))); +} + /** * Return the pointer to the byte where the bitstream writer will put * the next bit. diff --git a/libavcodec/put_golomb.h b/libavcodec/put_golomb.h index 9ca911fc3c..ca4b182ae8 100644 --- a/libavcodec/put_golomb.h +++ b/libavcodec/put_golomb.h @@ -154,15 +154,22 @@ static inline void set_sr_golomb(PutBitContext *pb, int i, int k, int limit, /** * write signed golomb rice code (flac). */ -static inline void set_sr_golomb_flac(PutBitContext *pb, int i, int k, - int limit, int esc_len) +static inline void set_sr_golomb_flac(PutBitContext *pb, int i, int k) { - int v; + unsigned v, e; - v = -2 * i - 1; - v ^= (v >> 31); + v = ((unsigned)(i) << 1) ^ (i >> 31); - set_ur_golomb_jpegls(pb, v, k, limit, esc_len); + e = (v >> k) + 1; + while (e > 31) { + put_bits(pb, 31, 0); + e -= 31; + } + put_bits(pb, e, 1); + if (k) { + unsigned mask = UINT32_MAX >> (32-k); + put_bits(pb, k, v & mask); + } } #endif /* AVCODEC_PUT_GOLOMB_H */