From patchwork Thu Sep 7 17:16:35 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andreas Rheinhardt X-Patchwork-Id: 43642 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:8b17:b0:149:dfde:5c0a with SMTP id l23csp756730pzh; Thu, 7 Sep 2023 10:31:33 -0700 (PDT) X-Google-Smtp-Source: AGHT+IEdpsRuE9cnzRutDDQdbPEEU/OkYrFZ/eIUS3lvAn6yi5SJGOwrBg540mpquj774yUQu0yZ X-Received: by 2002:a05:6512:3188:b0:500:b64e:4f40 with SMTP id i8-20020a056512318800b00500b64e4f40mr115339lfe.41.1694107892559; Thu, 07 Sep 2023 10:31:32 -0700 (PDT) Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id n14-20020aa7d04e000000b0052a397ce327si30190edo.605.2023.09.07.10.31.29; Thu, 07 Sep 2023 10:31:32 -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=@outlook.com header.s=selector1 header.b=lGJN76cO; arc=fail (body hash mismatch); 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=outlook.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 080B868C823; Thu, 7 Sep 2023 20:31:27 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from EUR05-AM6-obe.outbound.protection.outlook.com (mail-am6eur05olkn2051.outbound.protection.outlook.com [40.92.91.51]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 0635568C767 for ; Thu, 7 Sep 2023 20:31:20 +0300 (EEST) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=h3or+SAq7moeBGLJ36o8LCo5QjPxmQ7u97BSB4P2LMrFSVwSmloilYf6Xwd+xfEPnZCooNRltknzf/gWL/CRf4IhdOnVeu+n2oMaGWAxOXats0JzohSZjvUGUZ3aOc5jNuZoeTv7f7Nm1u5IunBUHrtX3IEl2UK9bRGsv7vvhsQEE1zg783BqpKpxkMF6DoQkaODnlgLZoCfQf6gvO7D6Dk666h75WBTqRQps2OXqjwIzzqy/bcjSGGipRwEZiF9rv0napULnvM2gqQK9FUnWbTCpUjH0LnS6sJuFxZDIjOj2cSIWc8KmbAqiZkP9ij5KpeG+Y85vmK3MmmzdwA/KQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=FLv1I+ASlBWg3aR5XTpIjjHvcqoP3qGXxHEP+7XwXcY=; b=Z9OKJM/DvPT+ZVsrUF/TSnTUme60FZfmUisZVulm9/Ou4bRwFvdbKMVbap/QvidbA2HZd6b1irsdVbgSdTp/l33vWHwqM439qFkdK+C5PH6r1dw75c6zO4b8FAaFif51XQRIjsgbvtsV5cUFWExjTXtPjtL377kRxAAJRz77gPIlvcvjiwWS20SQ9e9uKUDQX5qqkJwLNNZMpmM+OEmW7Yn4kHODvUU22sXRgj/3T05TjUUP6bEG3S13fM7EBG1DVZPYPCH7e5CLWMt544cEbVQUG597mtg8JNYvB8CKPM/TY/lebUMnYZg4vmsJ82fKkxAPZzvcUknJRJZcBT+v/A== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=none; dmarc=none; dkim=none; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=outlook.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=FLv1I+ASlBWg3aR5XTpIjjHvcqoP3qGXxHEP+7XwXcY=; b=lGJN76cOToAjxrVD4Fc6NqoCaEcjKWJ20GoI6KcPZ1uCcllDjNQHuNRaiAWTHgjeiIHAPjkRFYn0Mz7wZudD/GiEFmY5ySQdL95AXpmyUErBAEx7LPbOjaMNhR5DLhe2PvQOpp0dLXFMFNo9CgtJY6XuEw3pLUZ3/+10VU4qvmSnLLs5Z+re3WvYNTXABbjf7LpW0lS3cC0tRJBiP0bMmvCCLtoXAdJuKTs90KGuOcrE//isaWR08nIyGHSfTWGlvkDTvIaWO9nQX36LjYDJlX30D4I3jhFOtiakRzrL+L04RsGOa7xyxXAlCpchvl/ryLmewV67E9A87zgcXvMtAQ== Received: from AS8P250MB0744.EURP250.PROD.OUTLOOK.COM (2603:10a6:20b:541::14) by PR3P250MB0024.EURP250.PROD.OUTLOOK.COM (2603:10a6:102:14f::5) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6745.34; Thu, 7 Sep 2023 17:15:24 +0000 Received: from AS8P250MB0744.EURP250.PROD.OUTLOOK.COM ([fe80::5e01:aea5:d3a8:cafa]) by AS8P250MB0744.EURP250.PROD.OUTLOOK.COM ([fe80::5e01:aea5:d3a8:cafa%3]) with mapi id 15.20.6745.034; Thu, 7 Sep 2023 17:15:24 +0000 From: Andreas Rheinhardt To: ffmpeg-devel@ffmpeg.org Date: Thu, 7 Sep 2023 19:16:35 +0200 Message-ID: X-Mailer: git-send-email 2.34.1 X-TMN: [i9g6jH7w25jZNCbgs74dJTXwCRNJJNH8] X-ClientProxiedBy: ZR0P278CA0099.CHEP278.PROD.OUTLOOK.COM (2603:10a6:910:23::14) To AS8P250MB0744.EURP250.PROD.OUTLOOK.COM (2603:10a6:20b:541::14) X-Microsoft-Original-Message-ID: <20230907171635.1374765-1-andreas.rheinhardt@outlook.com> MIME-Version: 1.0 X-MS-Exchange-MessageSentRepresentingType: 1 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: AS8P250MB0744:EE_|PR3P250MB0024:EE_ X-MS-Office365-Filtering-Correlation-Id: 599e0cec-ca83-4e4c-dcf1-08dbafc605fd X-Microsoft-Antispam: BCL:0; X-Microsoft-Antispam-Message-Info: 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 X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: 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 X-OriginatorOrg: outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 599e0cec-ca83-4e4c-dcf1-08dbafc605fd X-MS-Exchange-CrossTenant-AuthSource: AS8P250MB0744.EURP250.PROD.OUTLOOK.COM X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Sep 2023 17:15:24.5089 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 84df9e7f-e9f6-40af-b435-aaaaaaaaaaaa X-MS-Exchange-CrossTenant-RMS-PersistedConsumerOrg: 00000000-0000-0000-0000-000000000000 X-MS-Exchange-Transport-CrossTenantHeadersStamped: PR3P250MB0024 Subject: [FFmpeg-devel] [PATCH] avcodec/get_bits: Avoid reading multiple times in get_bits_long 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: Andreas Rheinhardt Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: VjzjbuPc0ZWE Due to non-byte-alignment a read of 32 bits guarantees only 25 usable bits; therefore get_bits_long() (which is used to potentially read more than 25 bits) performs two reads in case it needs to read more than 25 bits and combines the result. Yet this is not necessary: One can just read 64 bits at a time to get 32 usable bits (57 would be possible). This commit does so. This reduced the size of .text by 30144B for GCC 11.4 and 5648B for Clang 14 (both with -O3). (get_bits_long() is a building block of show_bits_long() and get_ue_golomb_long(), so this patch affects these, too.) Signed-off-by: Andreas Rheinhardt --- libavcodec/get_bits.h | 38 +++++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/libavcodec/get_bits.h b/libavcodec/get_bits.h index 0594e104bb..f43bcae91e 100644 --- a/libavcodec/get_bits.h +++ b/libavcodec/get_bits.h @@ -187,21 +187,28 @@ static inline unsigned int show_bits(GetBitContext *s, int n); #define CLOSE_READER(name, gb) (gb)->index = name ## _index +#define UPDATE_CACHE_BE_EXT(name, gb, bits, dst_bits) name ## _cache = \ + AV_RB ## bits((gb)->buffer + (name ## _index >> 3)) << (name ## _index & 7) >> (bits - dst_bits) + +#define UPDATE_CACHE_LE_EXT(name, gb, bits, dst_bits) name ## _cache = \ + (uint ## dst_bits ## _t)(AV_RL ## bits((gb)->buffer + (name ## _index >> 3)) >> (name ## _index & 7)) + +/* Using these two macros ensures that 32 bits are available. */ +# define UPDATE_CACHE_LE_32(name, gb) UPDATE_CACHE_LE_EXT(name, (gb), 64, 32) + +# define UPDATE_CACHE_BE_32(name, gb) UPDATE_CACHE_BE_EXT(name, (gb), 64, 32) + # ifdef LONG_BITSTREAM_READER -# define UPDATE_CACHE_LE(name, gb) name ## _cache = \ - AV_RL64((gb)->buffer + (name ## _index >> 3)) >> (name ## _index & 7) +# define UPDATE_CACHE_LE(name, gb) UPDATE_CACHE_LE_32(name, (gb)) -# define UPDATE_CACHE_BE(name, gb) name ## _cache = \ - AV_RB64((gb)->buffer + (name ## _index >> 3)) >> (32 - (name ## _index & 7)) +# define UPDATE_CACHE_BE(name, gb) UPDATE_CACHE_BE_32(name, (gb)) #else -# define UPDATE_CACHE_LE(name, gb) name ## _cache = \ - AV_RL32((gb)->buffer + (name ## _index >> 3)) >> (name ## _index & 7) +# define UPDATE_CACHE_LE(name, gb) UPDATE_CACHE_LE_EXT(name, (gb), 32, 32) -# define UPDATE_CACHE_BE(name, gb) name ## _cache = \ - AV_RB32((gb)->buffer + (name ## _index >> 3)) << (name ## _index & 7) +# define UPDATE_CACHE_BE(name, gb) UPDATE_CACHE_BE_EXT(name, (gb), 32, 32) #endif @@ -209,12 +216,14 @@ static inline unsigned int show_bits(GetBitContext *s, int n); #ifdef BITSTREAM_READER_LE # define UPDATE_CACHE(name, gb) UPDATE_CACHE_LE(name, gb) +# define UPDATE_CACHE_32(name, gb) UPDATE_CACHE_LE_32(name, (gb)) # define SKIP_CACHE(name, gb, num) name ## _cache >>= (num) #else # define UPDATE_CACHE(name, gb) UPDATE_CACHE_BE(name, gb) +# define UPDATE_CACHE_32(name, gb) UPDATE_CACHE_BE_32(name, (gb)) # define SKIP_CACHE(name, gb, num) name ## _cache <<= (num) @@ -414,15 +423,26 @@ static inline unsigned int get_bits_long(GetBitContext *s, int n) av_assert2(n>=0 && n<=32); if (!n) { return 0; - } else if (n <= MIN_CACHE_BITS) { + } else if ((!HAVE_FAST_64BIT || av_builtin_constant_p(n <= MIN_CACHE_BITS)) + && n <= MIN_CACHE_BITS) { return get_bits(s, n); } else { +#if HAVE_FAST_64BIT + unsigned tmp; + OPEN_READER(re, s); + UPDATE_CACHE_32(re, s); + tmp = SHOW_UBITS(re, s, n); + LAST_SKIP_BITS(re, s, n); + CLOSE_READER(re, s); + return tmp; +#else #ifdef BITSTREAM_READER_LE unsigned ret = get_bits(s, 16); return ret | (get_bits(s, n - 16) << 16); #else unsigned ret = get_bits(s, 16) << (n - 16); return ret | get_bits(s, n - 16); +#endif #endif } }