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 7647E4B47B for ; Wed, 5 Jun 2024 21:39:22 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id D3C9268D426; Thu, 6 Jun 2024 00:39:19 +0300 (EEST) Received: from EUR02-AM0-obe.outbound.protection.outlook.com (mail-am0eur02olkn2017.outbound.protection.outlook.com [40.92.49.17]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id D841568D426 for ; Thu, 6 Jun 2024 00:39:13 +0300 (EEST) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=YW+UJ0/jFq+a8XCxZ/+fEh+Yt7/HyqVdPOiz0s8QWjLl6zTSUQV/76hl28jCFDdp+hUJmwKAzIHvyQ4jkNi+STkzAGTt1JEjuH7H1O0SjHifEXTnQw/1v8WI/06fyZbGqp+H6h9DxX8jBfFPYR4tqmx3bZyRhykqUR8b4kromKiYXGo2a7PDfL1Loh4A7KYCOru9OpYhzDwA7bn2/WA0h6nFWM3My/sSg027dHPNSfzTPg+fGtojXpKbB72trDK5g8inGcTZLp+b65pQeb59dIJJJIohbU/AhUMo3lraBi5TORthNaotyxpwKtq9FUgv6B/ukltaJN1DnkBTS5/nRw== 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=0PG5cqkrGdTcKG4Zl9CpdsRQUwkLJvOhEeD6Ji0jD+w=; b=nr430su0uQfUBSTzF4IbY++82mc77dWcrR81ikO+mVMYp1tfpt4qgw6e/D6d1g5HsCpHMgsjTYQCyh8UVff3B4Ws/BksF0Mo9+sIxRoXpkAXU56nc6nIiErPsDI55285B3m61uia8OQNQdLSLTF2JmBK8uG8G2eGVjwav+SocOHAavtQRlIm9S/fk6LKryaUJ5KvoEa8VTfy8e2hY47wVLuENHv5p5gN6iQiT89YkDhVRGlcK4pJ+F5f57wAUU3NZohJfFKyfxVZp4+Iggi6npoosGYLKkOzmg1DUBKMszpGIWUtV099k9SFQ4k2348DEmxlI7ZY6ZiCXw/WAmNn6g== 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=0PG5cqkrGdTcKG4Zl9CpdsRQUwkLJvOhEeD6Ji0jD+w=; b=IcKfV6bxbXsj9drHXM99chOcDIuGfxcSiIC6kVWTLAUAxp3yP+dm2JRM5dpXp7eIHy7p+q+7Muvwsu+qDkI3bry3XTqTS3seaA8QoOzJkuLqdQXHGjWATcQyVki6QGRVjUtDdhH/pVnrb5EVNpQtX8KqFXeFQ+xShrE5GtJKdg8wkOGwAyXbyx/q6vo5QoL6sdmBTcuvuOUjltye6WQdOR2PoKJ1NBgbWHac71qgqkuXshVk/zrUfBdukpHD3lEZ1hMEVuS6EaOzDfCaMPPMIpqKz5kKDlVL4OQT7D7P52KeHXSXV7UAi0LHXgSHSSxULBUSGKncQdXTAS6dodVEhQ== Received: from GV1P250MB0737.EURP250.PROD.OUTLOOK.COM (2603:10a6:150:8e::17) by AM8P250MB0357.EURP250.PROD.OUTLOOK.COM (2603:10a6:20b:328::6) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.7633.27; Wed, 5 Jun 2024 21:39:10 +0000 Received: from GV1P250MB0737.EURP250.PROD.OUTLOOK.COM ([fe80::d6a1:e3af:a5f1:b614]) by GV1P250MB0737.EURP250.PROD.OUTLOOK.COM ([fe80::d6a1:e3af:a5f1:b614%4]) with mapi id 15.20.7633.021; Wed, 5 Jun 2024 21:39:10 +0000 From: Andreas Rheinhardt To: ffmpeg-devel@ffmpeg.org Date: Wed, 5 Jun 2024 23:38:59 +0200 Message-ID: X-Mailer: git-send-email 2.40.1 In-Reply-To: References: X-TMN: [d4mM6bEdoDyBWb/UNl9u8siHqTKv+bl7X1cQhf6FMgk=] X-ClientProxiedBy: ZR2P278CA0042.CHEP278.PROD.OUTLOOK.COM (2603:10a6:910:47::13) To GV1P250MB0737.EURP250.PROD.OUTLOOK.COM (2603:10a6:150:8e::17) X-Microsoft-Original-Message-ID: <20240605213901.2074109-1-andreas.rheinhardt@outlook.com> MIME-Version: 1.0 X-MS-Exchange-MessageSentRepresentingType: 1 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: GV1P250MB0737:EE_|AM8P250MB0357:EE_ X-MS-Office365-Filtering-Correlation-Id: fffe0c1b-c541-408f-a596-08dc85a7ef44 X-Microsoft-Antispam: BCL:0; ARA:14566002|461199019|440099019|3412199016|1710799017; X-Microsoft-Antispam-Message-Info: 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 X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?5YkLl+G8M98f60IXHrgK6BeK/tjLvCvd8ozsPdQlMl+4qHcIcnkU+d3kl6IZ?= =?us-ascii?Q?/Lpr4rqPflDzlJz2jHvWIGjpM6EIy7W53BNRSNoVUXnKUViZrkXJUBV3Y0Dc?= =?us-ascii?Q?96p8cpwzM3TWZeXOq4Nk1OcRJ1B6cPzUnVNyj6GkNlZ5sYJ6zMr7ZdnWQlXJ?= =?us-ascii?Q?Bf9gRhD9+s1zMuZUNrw2Q3Kl9xrSh9lzdNggJIAwrsipAXMyQxeo9IGdeiXz?= =?us-ascii?Q?bWEm2/ZSFoaSmmfzv5JLhrhydVYOFVfT8PoA2dXFOvMJw72DguHy/sgoVnAZ?= =?us-ascii?Q?9xgNCC6wXtCNEa2b9tBo4pXhlnvHA/PUrOTEqT2UTObxm85CV/wIM4fCJFgy?= =?us-ascii?Q?XWfJVJ5fXh466Zybz4a9K6VuPxBXo2cyaoc0JYD2SOX8Uz5qw33cxKDg7h2e?= =?us-ascii?Q?Nxz2ZoW+c0y/WaVng+/PmoFHlNKy2btpgic2KZkeidzykPVkqF3cX7FmtO4b?= =?us-ascii?Q?JuS3hKfFtdb5Zpn3yDvFZ0NicfMzOhEqcwP9TKlgkp2fubYoc+NvGumZshM2?= =?us-ascii?Q?qRvp4pJ4BaKBI0aFBWemttpIUgdRzT2RX/RqgMzlFdWNQ0f4SzV3k3M3DlW6?= =?us-ascii?Q?NR3oYF/gUjsKuJvsZh+npdo1WuCsOfsZ127HpCqXJi5TgPx94FUzdQ1dFIH4?= =?us-ascii?Q?JFq4dMXN0MuAgkvBqRhq77k5y8aVNTyMfADUl/xo+QeQyjHJA/ADn9amn62v?= =?us-ascii?Q?CVHg+e8glilVrjGC9PxI3HuJmEdIVcFVRSIc0XYwcPbkZDBkKyceYq4xrFzp?= =?us-ascii?Q?7Nq1BYNp2y8Y0j/W8qNO1xjkUDl3VAXOcL22PW4r/vtPl/E3aArFvBu8XiKe?= =?us-ascii?Q?SvnyqRo+CBf7CWWI83a+5CNDdCMhZSDUQGNhfXJRBRGWh4u5sjV0p660XbbQ?= =?us-ascii?Q?OCxnb2hgMmu9u8QUP64CEXN8k6MK77WTIBzm6SB5YAuDErL1yrxDM9e45J0i?= =?us-ascii?Q?qk52jgUim/UShmU8lcSQaP4v/6jjom6oQsGCp75eTlnCaUAZkWPNVeoTCaEL?= =?us-ascii?Q?+BUgoZa5Ry+DH1nUJUghEs7MlIXBAfEOsXBJ2aM2iQ8yjLDFRAge7khgdebE?= =?us-ascii?Q?eTPyefYIGuq3s81T8KElugVtdcA6kjAw7yIGD1PFRqXNpumTzIBbTqpQZJma?= =?us-ascii?Q?EsISKU1OL3sV2kduBKWu0ph9Zpluh++zdhHygWf9tWU1AD530A2/zGwnNUzs?= =?us-ascii?Q?qq41h1CQdEFSY9oHlllKJ7IgXMtDilvojp6ttizHItpsp2206rVlhBg3IiQK?= =?us-ascii?Q?jOzFgvVeZHnVaV9nO7H8POx3hr6lxCO47W4WSf3CIw=3D=3D?= X-OriginatorOrg: outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: fffe0c1b-c541-408f-a596-08dc85a7ef44 X-MS-Exchange-CrossTenant-AuthSource: GV1P250MB0737.EURP250.PROD.OUTLOOK.COM X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 05 Jun 2024 21:39:10.2343 (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: AM8P250MB0357 Subject: [FFmpeg-devel] [PATCH 2/4] swscale/x86/rgb2rgb: Don't unnecessarily check for inline ASM 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 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: The SSE2 and AVX versions of deinterleaveBytes are external ASM. Move them out of the inline ASM template. Signed-off-by: Andreas Rheinhardt --- libswscale/x86/rgb2rgb.c | 48 +++++++++++++++++++++++-------- libswscale/x86/rgb2rgb_template.c | 30 ------------------- 2 files changed, 36 insertions(+), 42 deletions(-) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index b325e5dbd5..be6f5abc95 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -100,13 +100,6 @@ DECLARE_ALIGNED(8, extern const uint64_t, ff_bgr2UVOffset); #define RENAME(a) a ## _sse2 #include "rgb2rgb_template.c" -//AVX versions -#undef RENAME -#undef COMPILE_TEMPLATE_AVX -#define COMPILE_TEMPLATE_AVX 1 -#define RENAME(a) a ## _avx -#include "rgb2rgb_template.c" - /* RGB15->RGB16 original by Strepto/Astral ported to gcc & bugfixed : A'rpi @@ -138,6 +131,33 @@ void ff_uyvytoyuv422_avx(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, int lumStride, int chromStride, int srcStride); #endif +#define DEINTERLEAVE_BYTES(cpuext) \ +void ff_nv12ToUV_ ## cpuext(uint8_t *dstU, uint8_t *dstV, \ + const uint8_t *unused, \ + const uint8_t *src1, \ + const uint8_t *src2, \ + int w, \ + uint32_t *unused2, \ + void *opq); \ +static void deinterleave_bytes_ ## cpuext(const uint8_t *src, uint8_t *dst1, uint8_t *dst2, \ + int width, int height, int srcStride, \ + int dst1Stride, int dst2Stride) \ +{ \ + for (int h = 0; h < height; h++) { \ + ff_nv12ToUV_ ## cpuext(dst1, dst2, NULL, src, NULL, width, NULL, NULL); \ + src += srcStride; \ + dst1 += dst1Stride; \ + dst2 += dst2Stride; \ + } \ +} + +#if HAVE_SSE2_EXTERNAL +DEINTERLEAVE_BYTES(sse2) +#endif +#if HAVE_AVX_EXTERNAL +DEINTERLEAVE_BYTES(avx) +#endif + av_cold void rgb2rgb_init_x86(void) { int cpu_flags = av_get_cpu_flags(); @@ -147,18 +167,19 @@ av_cold void rgb2rgb_init_x86(void) rgb2rgb_init_mmxext(); if (INLINE_SSE2(cpu_flags)) rgb2rgb_init_sse2(); - if (INLINE_AVX(cpu_flags)) - rgb2rgb_init_avx(); #endif /* HAVE_INLINE_ASM */ if (EXTERNAL_MMXEXT(cpu_flags)) { shuffle_bytes_2103 = ff_shuffle_bytes_2103_mmxext; } +#if HAVE_SSE2_EXTERNAL if (EXTERNAL_SSE2(cpu_flags)) { #if ARCH_X86_64 uyvytoyuv422 = ff_uyvytoyuv422_sse2; #endif + deinterleaveBytes = deinterleave_bytes_sse2; } +#endif if (EXTERNAL_SSSE3(cpu_flags)) { shuffle_bytes_0321 = ff_shuffle_bytes_0321_ssse3; shuffle_bytes_2103 = ff_shuffle_bytes_2103_ssse3; @@ -166,16 +187,19 @@ av_cold void rgb2rgb_init_x86(void) shuffle_bytes_3012 = ff_shuffle_bytes_3012_ssse3; shuffle_bytes_3210 = ff_shuffle_bytes_3210_ssse3; } +#if HAVE_AVX_EXTERNAL + if (EXTERNAL_AVX(cpu_flags)) { + deinterleaveBytes = deinterleave_bytes_avx; #if ARCH_X86_64 + uyvytoyuv422 = ff_uyvytoyuv422_avx; + } if (EXTERNAL_AVX2_FAST(cpu_flags)) { shuffle_bytes_0321 = ff_shuffle_bytes_0321_avx2; shuffle_bytes_2103 = ff_shuffle_bytes_2103_avx2; shuffle_bytes_1230 = ff_shuffle_bytes_1230_avx2; shuffle_bytes_3012 = ff_shuffle_bytes_3012_avx2; shuffle_bytes_3210 = ff_shuffle_bytes_3210_avx2; - } - if (EXTERNAL_AVX(cpu_flags)) { - uyvytoyuv422 = ff_uyvytoyuv422_avx; +#endif } #endif } diff --git a/libswscale/x86/rgb2rgb_template.c b/libswscale/x86/rgb2rgb_template.c index e4e884827c..5c73fa4e16 100644 --- a/libswscale/x86/rgb2rgb_template.c +++ b/libswscale/x86/rgb2rgb_template.c @@ -1816,31 +1816,6 @@ static void RENAME(interleaveBytes)(const uint8_t *src1, const uint8_t *src2, ui } #endif /* !COMPILE_TEMPLATE_AVX && COMPILE_TEMPLATE_SSE2 */ -#if !COMPILE_TEMPLATE_AVX || HAVE_AVX_EXTERNAL -#if COMPILE_TEMPLATE_SSE2 && HAVE_X86ASM -void RENAME(ff_nv12ToUV)(uint8_t *dstU, uint8_t *dstV, - const uint8_t *unused, - const uint8_t *src1, - const uint8_t *src2, - int w, - uint32_t *unused2, - void *opq); -static void RENAME(deinterleaveBytes)(const uint8_t *src, uint8_t *dst1, uint8_t *dst2, - int width, int height, int srcStride, - int dst1Stride, int dst2Stride) -{ - int h; - - for (h = 0; h < height; h++) { - RENAME(ff_nv12ToUV)(dst1, dst2, NULL, src, NULL, width, NULL, NULL); - src += srcStride; - dst1 += dst1Stride; - dst2 += dst2Stride; - } -} -#endif /* COMPILE_TEMPLATE_SSE2 && HAVE_X86ASM */ -#endif /* !COMPILE_TEMPLATE_AVX || HAVE_AVX_EXTERNAL */ - #if !COMPILE_TEMPLATE_SSE2 static inline void RENAME(vu9_to_vu12)(const uint8_t *src1, const uint8_t *src2, uint8_t *dst1, uint8_t *dst2, @@ -2441,9 +2416,4 @@ static av_cold void RENAME(rgb2rgb_init)(void) #if !COMPILE_TEMPLATE_AVX && COMPILE_TEMPLATE_SSE2 interleaveBytes = RENAME(interleaveBytes); #endif /* !COMPILE_TEMPLATE_AVX && COMPILE_TEMPLATE_SSE2 */ -#if !COMPILE_TEMPLATE_AVX || HAVE_AVX_EXTERNAL -#if COMPILE_TEMPLATE_SSE2 && HAVE_X86ASM - deinterleaveBytes = RENAME(deinterleaveBytes); -#endif -#endif } -- 2.40.1 _______________________________________________ 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".