From patchwork Sun Nov 6 16:27:51 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andreas Rheinhardt X-Patchwork-Id: 39207 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a21:999a:b0:a4:2148:650a with SMTP id ve26csp1636012pzb; Sun, 6 Nov 2022 08:28:07 -0800 (PST) X-Google-Smtp-Source: AMsMyM5a09nJbLl/jdxD0JU7G+rGxFcljh0WH8Otl+tM83j55OIRv62mBrXY/iHIxUmDU0vriGiG X-Received: by 2002:a17:907:3e87:b0:7ae:46a8:af0a with SMTP id hs7-20020a1709073e8700b007ae46a8af0amr8471445ejc.554.1667752087005; Sun, 06 Nov 2022 08:28:07 -0800 (PST) Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id du10-20020a17090772ca00b007ae17fd2f2dsi7029455ejc.996.2022.11.06.08.28.06; Sun, 06 Nov 2022 08:28:06 -0800 (PST) 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=utdfQxLR; 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 DE52068B743; Sun, 6 Nov 2022 18:28:01 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from EUR05-AM6-obe.outbound.protection.outlook.com (mail-am6eur05olkn2072.outbound.protection.outlook.com [40.92.91.72]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id C61B668B4EF for ; Sun, 6 Nov 2022 18:27:54 +0200 (EET) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=MfIxjqoD3l6XTmSRLDVRJtIqZynRtxT5iOZgLHSMXrMPdqJCUAtHUIJ+EZRzIr6u4SBPS4WHGjvI9tAcaXVD1F9fdOLyCFK16BGu7kAc+wdwTq/ykzBqUoF9xxwq/XHKg7t9EIjasLVWC5f96zM3p3L6gJefKnS1THKq8hWjQlStrPr8k7I1hXXPxgOd4izDTPvcuBe8zwJvAQieMcAb+mg7MdHMdEMzD/AeQTms7/HdKacdRpBbCqhGvPl91H3NeCsRNpTGbtx4Mljll5Lb0mUpr8y5GftX+3w9/248OL5iL67naxS4lrVuT9CkCVuXer29gF4zYHQru9UD8TDxHQ== 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=safPHWT9tI6uwD2YAfdPlr0JfG+1RfA8WJe0ocuT6ps=; b=fdkgMXUV9cblRshX97/z6VLsw7y7ZZpxNeYJKG2XU2KefNseAsih8hkIR91Bfr9UYUaSRRdUretkl4RrNhdJO4Td+AN9aA3Soc02NUkxBCCW9D/ALGsArjc87jjsuodkeRF2Bcpd8E07Pquoy1w2zsdn6H3W2KLwAKFmukStL1RxOgOPjEJ4B9T2xJpN+RYmIHc1otopAw2EF531qYnU5He9NNb1C3d8Hn9ypaozbXThw2ZMDIQoMeLpnRhQvdBBN3yVrImKpVwstNaAiAK35afWYCC4/pkxLmsNHULWt8j9+v0z8+p/NACZgAiFCdB86BIq7uEi7wCapkbv768zPQ== 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=safPHWT9tI6uwD2YAfdPlr0JfG+1RfA8WJe0ocuT6ps=; b=utdfQxLRVTJhUurYy/uFVh00AndL+FdjBF+JSdIsezfeTnBdYZmPLx2lN6RmVTyypTA7IC0sDrt/o/d2zOCtdy2xOmoPR8YT6Wa4QhHnSPoSnZK5rrNqtY9zSFGUj14HwR4llEGQ3n05vje7w+xpMYBaRnvQkmKbE0/XJf/nDQ2Gyq6yBNXIapxAkCIbwNmTEt+NP+103NrBwr+aWd2qkqk5LrAM6uDp4wpVY1JnNGjFuBmQRkw2jqMmwCqZJgWL92FXdEmmv03aA+pzJqmXV137AwwHWYl/kdreN2VUFOoMtXve+HuMsmiGpM6a1Ick8nEAQzerZBAoh80crY6hQA== Received: from GV1P250MB0737.EURP250.PROD.OUTLOOK.COM (2603:10a6:150:8e::17) by DU0P250MB0458.EURP250.PROD.OUTLOOK.COM (2603:10a6:10:346::7) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.5791.25; Sun, 6 Nov 2022 16:27:52 +0000 Received: from GV1P250MB0737.EURP250.PROD.OUTLOOK.COM ([fe80::c323:d08c:85d0:dafe]) by GV1P250MB0737.EURP250.PROD.OUTLOOK.COM ([fe80::c323:d08c:85d0:dafe%4]) with mapi id 15.20.5791.026; Sun, 6 Nov 2022 16:27:52 +0000 From: Andreas Rheinhardt To: ffmpeg-devel@ffmpeg.org Date: Sun, 6 Nov 2022 17:27:51 +0100 Message-ID: X-Mailer: git-send-email 2.34.1 X-TMN: [f6+FAHsYD+QVk74c+JGlzm9ytHoYUa73K1yP898kUHc=] X-ClientProxiedBy: AM6PR08CA0003.eurprd08.prod.outlook.com (2603:10a6:20b:b2::15) To GV1P250MB0737.EURP250.PROD.OUTLOOK.COM (2603:10a6:150:8e::17) X-Microsoft-Original-Message-ID: <20221106162757.1130672-1-andreas.rheinhardt@outlook.com> MIME-Version: 1.0 X-MS-Exchange-MessageSentRepresentingType: 1 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: GV1P250MB0737:EE_|DU0P250MB0458:EE_ X-MS-Office365-Filtering-Correlation-Id: 03696443-d046-450b-24ec-08dac013d9ff X-MS-Exchange-SLBlob-MailProps: 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 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: 03696443-d046-450b-24ec-08dac013d9ff X-MS-Exchange-CrossTenant-AuthSource: GV1P250MB0737.EURP250.PROD.OUTLOOK.COM X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 06 Nov 2022 16:27:52.3614 (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: DU0P250MB0458 Subject: [FFmpeg-devel] [PATCH 1/7] postproc/postprocess: Remove obsolete MMX(EXT)/3Dnow functions 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: QM41HGFyn9FE postprocess.c currently has C, MMX, MMXEXT, 3DNow as well as SSE2 versions of its internal functions. But given that only ancient 32-bit x86 CPUs don't support SSE2, the MMX, MMXEXT and 3DNow versions are obsolete and are therefore removed by this commit. This saves about 56KB here. (The SSE2 version in particular is not really complete, so that it often falls back to MMXEXT (which means that there were some identical (apart from the name) MMXEXT and SSE2 functions; this duplication no longer exists with this commit.) Signed-off-by: Andreas Rheinhardt --- The PP_CPU_CAPS_MMX(2)/3DNOW could now be deprecated. libpostproc/postprocess.c | 69 ++-- libpostproc/postprocess_template.c | 521 ++--------------------------- 2 files changed, 57 insertions(+), 533 deletions(-) diff --git a/libpostproc/postprocess.c b/libpostproc/postprocess.c index 383c691cb4..0586e458b4 100644 --- a/libpostproc/postprocess.c +++ b/libpostproc/postprocess.c @@ -26,28 +26,27 @@ */ /* - C MMX MMX2 3DNow AltiVec -isVertDC Ec Ec Ec -isVertMinMaxOk Ec Ec Ec -doVertLowPass E e e Ec -doVertDefFilter Ec Ec e e Ec -isHorizDC Ec Ec Ec -isHorizMinMaxOk a E Ec -doHorizLowPass E e e Ec -doHorizDefFilter Ec Ec e e Ec -do_a_deblock Ec E Ec E -deRing E e e* Ecp -Vertical RKAlgo1 E a a -Horizontal RKAlgo1 a a -Vertical X1# a E E -Horizontal X1# a E E -LinIpolDeinterlace e E E* -CubicIpolDeinterlace a e e* -LinBlendDeinterlace e E E* + C MMX MMX2 AltiVec +isVertDC Ec Ec Ec +isVertMinMaxOk Ec Ec Ec +doVertLowPass E e Ec +doVertDefFilter Ec Ec e Ec +isHorizDC Ec Ec Ec +isHorizMinMaxOk a E Ec +doHorizLowPass E e Ec +doHorizDefFilter Ec Ec e Ec +do_a_deblock Ec E Ec +deRing E e Ecp +Vertical RKAlgo1 E a +Horizontal RKAlgo1 a +Vertical X1# a E +Horizontal X1# a E +LinIpolDeinterlace e E +CubicIpolDeinterlace a e +LinBlendDeinterlace e E MedianDeinterlace# E Ec Ec -TempDeNoiser# E e e Ec +TempDeNoiser# E e Ec -* I do not have a 3DNow! CPU -> it is untested, but no one said it does not work so it seems to work # more or less selfinvented filters so the exactness is not too meaningful E = Exact implementation e = almost exact implementation (slightly different rounding,...) @@ -83,7 +82,6 @@ try to unroll inner for(x=0 ... loop to avoid these damn if(x ... checks #include #include //#undef HAVE_MMXEXT_INLINE -//#define HAVE_AMD3DNOW_INLINE //#undef HAVE_MMX_INLINE //#undef ARCH_X86 //#define DEBUG_BRIGHTNESS @@ -494,7 +492,7 @@ static av_always_inline void do_a_deblock_C(uint8_t *src, int step, } } -//Note: we have C, MMX, MMX2, 3DNOW version there is no 3DNOW+MMX2 one +//Note: we have C and SSE2 version (which uses MMX(EXT) when advantageous) //Plain C versions //we always compile C for testing which needs bitexactness #define TEMPLATE_PP_C 1 @@ -508,27 +506,12 @@ static av_always_inline void do_a_deblock_C(uint8_t *src, int step, #if ARCH_X86 && HAVE_INLINE_ASM # if CONFIG_RUNTIME_CPUDETECT -# define TEMPLATE_PP_MMX 1 -# include "postprocess_template.c" -# define TEMPLATE_PP_MMXEXT 1 -# include "postprocess_template.c" -# define TEMPLATE_PP_3DNOW 1 -# include "postprocess_template.c" # define TEMPLATE_PP_SSE2 1 # include "postprocess_template.c" # else # if HAVE_SSE2_INLINE # define TEMPLATE_PP_SSE2 1 # include "postprocess_template.c" -# elif HAVE_MMXEXT_INLINE -# define TEMPLATE_PP_MMXEXT 1 -# include "postprocess_template.c" -# elif HAVE_AMD3DNOW_INLINE -# define TEMPLATE_PP_3DNOW 1 -# include "postprocess_template.c" -# elif HAVE_MMX_INLINE -# define TEMPLATE_PP_MMX 1 -# include "postprocess_template.c" # endif # endif #endif @@ -549,21 +532,12 @@ static inline void postProcess(const uint8_t src[], int srcStride, uint8_t dst[] #if ARCH_X86 && HAVE_INLINE_ASM // ordered per speed fastest first if (c->cpuCaps & AV_CPU_FLAG_SSE2) pp = postProcess_SSE2; - else if (c->cpuCaps & AV_CPU_FLAG_MMXEXT) pp = postProcess_MMX2; - else if (c->cpuCaps & AV_CPU_FLAG_3DNOW) pp = postProcess_3DNow; - else if (c->cpuCaps & AV_CPU_FLAG_MMX) pp = postProcess_MMX; #elif HAVE_ALTIVEC if (c->cpuCaps & AV_CPU_FLAG_ALTIVEC) pp = postProcess_altivec; #endif #else /* CONFIG_RUNTIME_CPUDETECT */ #if HAVE_SSE2_INLINE pp = postProcess_SSE2; -#elif HAVE_MMXEXT_INLINE - pp = postProcess_MMX2; -#elif HAVE_AMD3DNOW_INLINE - pp = postProcess_3DNow; -#elif HAVE_MMX_INLINE - pp = postProcess_MMX; #elif HAVE_ALTIVEC pp = postProcess_altivec; #endif @@ -877,9 +851,6 @@ av_cold pp_context *pp_get_context(int width, int height, int cpuCaps){ c->cpuCaps = av_get_cpu_flags(); } else { c->cpuCaps = 0; - if (cpuCaps & PP_CPU_CAPS_MMX) c->cpuCaps |= AV_CPU_FLAG_MMX; - if (cpuCaps & PP_CPU_CAPS_MMX2) c->cpuCaps |= AV_CPU_FLAG_MMXEXT; - if (cpuCaps & PP_CPU_CAPS_3DNOW) c->cpuCaps |= AV_CPU_FLAG_3DNOW; if (cpuCaps & PP_CPU_CAPS_ALTIVEC) c->cpuCaps |= AV_CPU_FLAG_ALTIVEC; } diff --git a/libpostproc/postprocess_template.c b/libpostproc/postprocess_template.c index 9f76b7c587..bcf7bdad66 100644 --- a/libpostproc/postprocess_template.c +++ b/libpostproc/postprocess_template.c @@ -20,7 +20,7 @@ /** * @file - * mmx/mmx2/3dnow postprocess code. + * mmx/mmx2/sse2 postprocess code. */ #include "libavutil/mem_internal.h" @@ -57,14 +57,6 @@ # define TEMPLATE_PP_MMXEXT 0 #endif -#ifdef TEMPLATE_PP_3DNOW -# undef TEMPLATE_PP_MMX -# define TEMPLATE_PP_MMX 1 -# define RENAME(a) a ## _3DNow -#else -# define TEMPLATE_PP_3DNOW 0 -#endif - #ifdef TEMPLATE_PP_SSE2 # undef TEMPLATE_PP_MMX # define TEMPLATE_PP_MMX 1 @@ -82,30 +74,19 @@ #if TEMPLATE_PP_MMXEXT #define REAL_PAVGB(a,b) "pavgb " #a ", " #b " \n\t" -#elif TEMPLATE_PP_3DNOW -#define REAL_PAVGB(a,b) "pavgusb " #a ", " #b " \n\t" #endif #define PAVGB(a,b) REAL_PAVGB(a,b) #if TEMPLATE_PP_MMXEXT #define PMINUB(a,b,t) "pminub " #a ", " #b " \n\t" -#elif TEMPLATE_PP_MMX -#define PMINUB(b,a,t) \ - "movq " #a ", " #t " \n\t"\ - "psubusb " #b ", " #t " \n\t"\ - "psubb " #t ", " #a " \n\t" #endif #if TEMPLATE_PP_MMXEXT #define PMAXUB(a,b) "pmaxub " #a ", " #b " \n\t" -#elif TEMPLATE_PP_MMX -#define PMAXUB(a,b) \ - "psubusb " #a ", " #b " \n\t"\ - "paddb " #a ", " #b " \n\t" #endif //FIXME? |255-0| = 1 (should not be a problem ...) -#if TEMPLATE_PP_MMX +#if TEMPLATE_PP_MMXEXT /** * Check if the middle 8x8 Block in the given 8x16 block is flat */ @@ -185,20 +166,8 @@ static inline int RENAME(vertClassify)(const uint8_t src[], int stride, PPContex "psubusb %%mm3, %%mm4 \n\t" " \n\t" -#if TEMPLATE_PP_MMXEXT "pxor %%mm7, %%mm7 \n\t" "psadbw %%mm7, %%mm0 \n\t" -#else - "movq %%mm0, %%mm1 \n\t" - "psrlw $8, %%mm0 \n\t" - "paddb %%mm1, %%mm0 \n\t" - "movq %%mm0, %%mm1 \n\t" - "psrlq $16, %%mm0 \n\t" - "paddb %%mm1, %%mm0 \n\t" - "movq %%mm0, %%mm1 \n\t" - "psrlq $32, %%mm0 \n\t" - "paddb %%mm1, %%mm0 \n\t" -#endif "movq %4, %%mm7 \n\t" // QP,..., QP "paddusb %%mm7, %%mm7 \n\t" // 2QP ... 2QP "psubusb %%mm7, %%mm4 \n\t" // Diff <= 2QP -> 0 @@ -219,7 +188,7 @@ static inline int RENAME(vertClassify)(const uint8_t src[], int stride, PPContex return 2; } } -#endif //TEMPLATE_PP_MMX +#endif //TEMPLATE_PP_MMXEXT /** * Do a vertical low pass filter on the 8x16 block (only write to the 8x8 block in the middle) @@ -228,7 +197,7 @@ static inline int RENAME(vertClassify)(const uint8_t src[], int stride, PPContex #if !TEMPLATE_PP_ALTIVEC static inline void RENAME(doVertLowPass)(uint8_t *src, int stride, PPContext *c) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT src+= stride*3; __asm__ volatile( //"movv %0 %1 %2\n\t" "movq %2, %%mm0 \n\t" // QP,..., QP @@ -355,7 +324,7 @@ static inline void RENAME(doVertLowPass)(uint8_t *src, int stride, PPContext *c) : "r" (src), "r" ((x86_reg)stride), "m" (c->pQPb) : "%"FF_REG_a, "%"FF_REG_c ); -#else //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_MMXEXT const int l1= stride; const int l2= stride + l1; const int l3= stride + l2; @@ -394,7 +363,7 @@ static inline void RENAME(doVertLowPass)(uint8_t *src, int stride, PPContext *c) src++; } -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } #endif //TEMPLATE_PP_ALTIVEC @@ -407,7 +376,7 @@ static inline void RENAME(doVertLowPass)(uint8_t *src, int stride, PPContext *c) */ static inline void RENAME(vertX1Filter)(uint8_t *src, int stride, PPContext *co) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT src+= stride*3; __asm__ volatile( @@ -494,7 +463,7 @@ static inline void RENAME(vertX1Filter)(uint8_t *src, int stride, PPContext *co) NAMED_CONSTRAINTS_ADD(b01) : "%"FF_REG_a, "%"FF_REG_c ); -#else //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_MMXEXT const int l1= stride; const int l2= stride + l1; @@ -528,13 +497,13 @@ static inline void RENAME(vertX1Filter)(uint8_t *src, int stride, PPContext *co) } src++; } -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } #if !TEMPLATE_PP_ALTIVEC static inline void RENAME(doVertDefFilter)(uint8_t src[], int stride, PPContext *c) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT /* uint8_t tmp[16]; const int l1= stride; @@ -816,239 +785,7 @@ static inline void RENAME(doVertDefFilter)(uint8_t src[], int stride, PPContext } } */ -#elif TEMPLATE_PP_MMX - DECLARE_ALIGNED(8, uint64_t, tmp)[4]; // make space for 4 8-byte vars - src+= stride*4; - __asm__ volatile( - "pxor %%mm7, %%mm7 \n\t" -// 0 1 2 3 4 5 6 7 -// %0 %0+%1 %0+2%1 eax+2%1 %0+4%1 eax+4%1 edx+%1 edx+2%1 -// %0 eax eax+%1 eax+2%1 %0+4%1 edx edx+%1 edx+2%1 - - "movq (%0), %%mm0 \n\t" - "movq %%mm0, %%mm1 \n\t" - "punpcklbw %%mm7, %%mm0 \n\t" // low part of line 0 - "punpckhbw %%mm7, %%mm1 \n\t" // high part of line 0 - - "movq (%0, %1), %%mm2 \n\t" - "lea (%0, %1, 2), %%"FF_REG_a" \n\t" - "movq %%mm2, %%mm3 \n\t" - "punpcklbw %%mm7, %%mm2 \n\t" // low part of line 1 - "punpckhbw %%mm7, %%mm3 \n\t" // high part of line 1 - - "movq (%%"FF_REG_a"), %%mm4 \n\t" - "movq %%mm4, %%mm5 \n\t" - "punpcklbw %%mm7, %%mm4 \n\t" // low part of line 2 - "punpckhbw %%mm7, %%mm5 \n\t" // high part of line 2 - - "paddw %%mm0, %%mm0 \n\t" // 2L0 - "paddw %%mm1, %%mm1 \n\t" // 2H0 - "psubw %%mm4, %%mm2 \n\t" // L1 - L2 - "psubw %%mm5, %%mm3 \n\t" // H1 - H2 - "psubw %%mm2, %%mm0 \n\t" // 2L0 - L1 + L2 - "psubw %%mm3, %%mm1 \n\t" // 2H0 - H1 + H2 - - "psllw $2, %%mm2 \n\t" // 4L1 - 4L2 - "psllw $2, %%mm3 \n\t" // 4H1 - 4H2 - "psubw %%mm2, %%mm0 \n\t" // 2L0 - 5L1 + 5L2 - "psubw %%mm3, %%mm1 \n\t" // 2H0 - 5H1 + 5H2 - - "movq (%%"FF_REG_a", %1), %%mm2 \n\t" - "movq %%mm2, %%mm3 \n\t" - "punpcklbw %%mm7, %%mm2 \n\t" // L3 - "punpckhbw %%mm7, %%mm3 \n\t" // H3 - - "psubw %%mm2, %%mm0 \n\t" // 2L0 - 5L1 + 5L2 - L3 - "psubw %%mm3, %%mm1 \n\t" // 2H0 - 5H1 + 5H2 - H3 - "psubw %%mm2, %%mm0 \n\t" // 2L0 - 5L1 + 5L2 - 2L3 - "psubw %%mm3, %%mm1 \n\t" // 2H0 - 5H1 + 5H2 - 2H3 - "movq %%mm0, (%3) \n\t" // 2L0 - 5L1 + 5L2 - 2L3 - "movq %%mm1, 8(%3) \n\t" // 2H0 - 5H1 + 5H2 - 2H3 - - "movq (%%"FF_REG_a", %1, 2), %%mm0 \n\t" - "movq %%mm0, %%mm1 \n\t" - "punpcklbw %%mm7, %%mm0 \n\t" // L4 - "punpckhbw %%mm7, %%mm1 \n\t" // H4 - - "psubw %%mm0, %%mm2 \n\t" // L3 - L4 - "psubw %%mm1, %%mm3 \n\t" // H3 - H4 - "movq %%mm2, 16(%3) \n\t" // L3 - L4 - "movq %%mm3, 24(%3) \n\t" // H3 - H4 - "paddw %%mm4, %%mm4 \n\t" // 2L2 - "paddw %%mm5, %%mm5 \n\t" // 2H2 - "psubw %%mm2, %%mm4 \n\t" // 2L2 - L3 + L4 - "psubw %%mm3, %%mm5 \n\t" // 2H2 - H3 + H4 - - "lea (%%"FF_REG_a", %1), %0 \n\t" - "psllw $2, %%mm2 \n\t" // 4L3 - 4L4 - "psllw $2, %%mm3 \n\t" // 4H3 - 4H4 - "psubw %%mm2, %%mm4 \n\t" // 2L2 - 5L3 + 5L4 - "psubw %%mm3, %%mm5 \n\t" // 2H2 - 5H3 + 5H4 -//50 opcodes so far - "movq (%0, %1, 2), %%mm2 \n\t" - "movq %%mm2, %%mm3 \n\t" - "punpcklbw %%mm7, %%mm2 \n\t" // L5 - "punpckhbw %%mm7, %%mm3 \n\t" // H5 - "psubw %%mm2, %%mm4 \n\t" // 2L2 - 5L3 + 5L4 - L5 - "psubw %%mm3, %%mm5 \n\t" // 2H2 - 5H3 + 5H4 - H5 - "psubw %%mm2, %%mm4 \n\t" // 2L2 - 5L3 + 5L4 - 2L5 - "psubw %%mm3, %%mm5 \n\t" // 2H2 - 5H3 + 5H4 - 2H5 - - "movq (%%"FF_REG_a", %1, 4), %%mm6 \n\t" - "punpcklbw %%mm7, %%mm6 \n\t" // L6 - "psubw %%mm6, %%mm2 \n\t" // L5 - L6 - "movq (%%"FF_REG_a", %1, 4), %%mm6 \n\t" - "punpckhbw %%mm7, %%mm6 \n\t" // H6 - "psubw %%mm6, %%mm3 \n\t" // H5 - H6 - - "paddw %%mm0, %%mm0 \n\t" // 2L4 - "paddw %%mm1, %%mm1 \n\t" // 2H4 - "psubw %%mm2, %%mm0 \n\t" // 2L4 - L5 + L6 - "psubw %%mm3, %%mm1 \n\t" // 2H4 - H5 + H6 - - "psllw $2, %%mm2 \n\t" // 4L5 - 4L6 - "psllw $2, %%mm3 \n\t" // 4H5 - 4H6 - "psubw %%mm2, %%mm0 \n\t" // 2L4 - 5L5 + 5L6 - "psubw %%mm3, %%mm1 \n\t" // 2H4 - 5H5 + 5H6 - - "movq (%0, %1, 4), %%mm2 \n\t" - "movq %%mm2, %%mm3 \n\t" - "punpcklbw %%mm7, %%mm2 \n\t" // L7 - "punpckhbw %%mm7, %%mm3 \n\t" // H7 - - "paddw %%mm2, %%mm2 \n\t" // 2L7 - "paddw %%mm3, %%mm3 \n\t" // 2H7 - "psubw %%mm2, %%mm0 \n\t" // 2L4 - 5L5 + 5L6 - 2L7 - "psubw %%mm3, %%mm1 \n\t" // 2H4 - 5H5 + 5H6 - 2H7 - - "movq (%3), %%mm2 \n\t" // 2L0 - 5L1 + 5L2 - 2L3 - "movq 8(%3), %%mm3 \n\t" // 2H0 - 5H1 + 5H2 - 2H3 - -#if TEMPLATE_PP_MMXEXT - "movq %%mm7, %%mm6 \n\t" // 0 - "psubw %%mm0, %%mm6 \n\t" - "pmaxsw %%mm6, %%mm0 \n\t" // |2L4 - 5L5 + 5L6 - 2L7| - "movq %%mm7, %%mm6 \n\t" // 0 - "psubw %%mm1, %%mm6 \n\t" - "pmaxsw %%mm6, %%mm1 \n\t" // |2H4 - 5H5 + 5H6 - 2H7| - "movq %%mm7, %%mm6 \n\t" // 0 - "psubw %%mm2, %%mm6 \n\t" - "pmaxsw %%mm6, %%mm2 \n\t" // |2L0 - 5L1 + 5L2 - 2L3| - "movq %%mm7, %%mm6 \n\t" // 0 - "psubw %%mm3, %%mm6 \n\t" - "pmaxsw %%mm6, %%mm3 \n\t" // |2H0 - 5H1 + 5H2 - 2H3| -#else - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm0, %%mm6 \n\t" - "pxor %%mm6, %%mm0 \n\t" - "psubw %%mm6, %%mm0 \n\t" // |2L4 - 5L5 + 5L6 - 2L7| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm1, %%mm6 \n\t" - "pxor %%mm6, %%mm1 \n\t" - "psubw %%mm6, %%mm1 \n\t" // |2H4 - 5H5 + 5H6 - 2H7| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm2, %%mm6 \n\t" - "pxor %%mm6, %%mm2 \n\t" - "psubw %%mm6, %%mm2 \n\t" // |2L0 - 5L1 + 5L2 - 2L3| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm3, %%mm6 \n\t" - "pxor %%mm6, %%mm3 \n\t" - "psubw %%mm6, %%mm3 \n\t" // |2H0 - 5H1 + 5H2 - 2H3| -#endif - -#if TEMPLATE_PP_MMXEXT - "pminsw %%mm2, %%mm0 \n\t" - "pminsw %%mm3, %%mm1 \n\t" -#else - "movq %%mm0, %%mm6 \n\t" - "psubusw %%mm2, %%mm6 \n\t" - "psubw %%mm6, %%mm0 \n\t" - "movq %%mm1, %%mm6 \n\t" - "psubusw %%mm3, %%mm6 \n\t" - "psubw %%mm6, %%mm1 \n\t" -#endif - - "movd %2, %%mm2 \n\t" // QP - "punpcklbw %%mm7, %%mm2 \n\t" - - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm4, %%mm6 \n\t" // sign(2L2 - 5L3 + 5L4 - 2L5) - "pxor %%mm6, %%mm4 \n\t" - "psubw %%mm6, %%mm4 \n\t" // |2L2 - 5L3 + 5L4 - 2L5| - "pcmpgtw %%mm5, %%mm7 \n\t" // sign(2H2 - 5H3 + 5H4 - 2H5) - "pxor %%mm7, %%mm5 \n\t" - "psubw %%mm7, %%mm5 \n\t" // |2H2 - 5H3 + 5H4 - 2H5| -// 100 opcodes - "psllw $3, %%mm2 \n\t" // 8QP - "movq %%mm2, %%mm3 \n\t" // 8QP - "pcmpgtw %%mm4, %%mm2 \n\t" - "pcmpgtw %%mm5, %%mm3 \n\t" - "pand %%mm2, %%mm4 \n\t" - "pand %%mm3, %%mm5 \n\t" - - - "psubusw %%mm0, %%mm4 \n\t" // hd - "psubusw %%mm1, %%mm5 \n\t" // ld - - - "movq "MANGLE(w05)", %%mm2 \n\t" // 5 - "pmullw %%mm2, %%mm4 \n\t" - "pmullw %%mm2, %%mm5 \n\t" - "movq "MANGLE(w20)", %%mm2 \n\t" // 32 - "paddw %%mm2, %%mm4 \n\t" - "paddw %%mm2, %%mm5 \n\t" - "psrlw $6, %%mm4 \n\t" - "psrlw $6, %%mm5 \n\t" - - "movq 16(%3), %%mm0 \n\t" // L3 - L4 - "movq 24(%3), %%mm1 \n\t" // H3 - H4 - - "pxor %%mm2, %%mm2 \n\t" - "pxor %%mm3, %%mm3 \n\t" - - "pcmpgtw %%mm0, %%mm2 \n\t" // sign (L3-L4) - "pcmpgtw %%mm1, %%mm3 \n\t" // sign (H3-H4) - "pxor %%mm2, %%mm0 \n\t" - "pxor %%mm3, %%mm1 \n\t" - "psubw %%mm2, %%mm0 \n\t" // |L3-L4| - "psubw %%mm3, %%mm1 \n\t" // |H3-H4| - "psrlw $1, %%mm0 \n\t" // |L3 - L4|/2 - "psrlw $1, %%mm1 \n\t" // |H3 - H4|/2 - - "pxor %%mm6, %%mm2 \n\t" - "pxor %%mm7, %%mm3 \n\t" - "pand %%mm2, %%mm4 \n\t" - "pand %%mm3, %%mm5 \n\t" - -#if TEMPLATE_PP_MMXEXT - "pminsw %%mm0, %%mm4 \n\t" - "pminsw %%mm1, %%mm5 \n\t" -#else - "movq %%mm4, %%mm2 \n\t" - "psubusw %%mm0, %%mm2 \n\t" - "psubw %%mm2, %%mm4 \n\t" - "movq %%mm5, %%mm2 \n\t" - "psubusw %%mm1, %%mm2 \n\t" - "psubw %%mm2, %%mm5 \n\t" -#endif - "pxor %%mm6, %%mm4 \n\t" - "pxor %%mm7, %%mm5 \n\t" - "psubw %%mm6, %%mm4 \n\t" - "psubw %%mm7, %%mm5 \n\t" - "packsswb %%mm5, %%mm4 \n\t" - "movq (%0), %%mm0 \n\t" - "paddb %%mm4, %%mm0 \n\t" - "movq %%mm0, (%0) \n\t" - "movq (%0, %1), %%mm0 \n\t" - "psubb %%mm4, %%mm0 \n\t" - "movq %%mm0, (%0, %1) \n\t" - - : "+r" (src) - : "r" ((x86_reg)stride), "m" (c->pQPb), "r"(tmp) - NAMED_CONSTRAINTS_ADD(w05,w20) - : "%"FF_REG_a - ); -#else //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_MMXEXT const int l1= stride; const int l2= stride + l1; const int l3= stride + l2; @@ -1086,14 +823,14 @@ static inline void RENAME(doVertDefFilter)(uint8_t src[], int stride, PPContext } src++; } -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } #endif //TEMPLATE_PP_ALTIVEC #if !TEMPLATE_PP_ALTIVEC static inline void RENAME(dering)(uint8_t src[], int stride, PPContext *c) { -#if HAVE_7REGS && (TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) +#if HAVE_7REGS && TEMPLATE_PP_MMXEXT DECLARE_ALIGNED(8, uint64_t, tmp)[3]; __asm__ volatile( "pxor %%mm6, %%mm6 \n\t" @@ -1113,20 +850,10 @@ static inline void RENAME(dering)(uint8_t src[], int stride, PPContext *c) #undef REAL_FIND_MIN_MAX #undef FIND_MIN_MAX -#if TEMPLATE_PP_MMXEXT #define REAL_FIND_MIN_MAX(addr)\ "movq " #addr ", %%mm0 \n\t"\ "pminub %%mm0, %%mm7 \n\t"\ "pmaxub %%mm0, %%mm6 \n\t" -#else -#define REAL_FIND_MIN_MAX(addr)\ - "movq " #addr ", %%mm0 \n\t"\ - "movq %%mm7, %%mm1 \n\t"\ - "psubusb %%mm0, %%mm6 \n\t"\ - "paddb %%mm0, %%mm6 \n\t"\ - "psubusb %%mm0, %%mm1 \n\t"\ - "psubb %%mm1, %%mm7 \n\t" -#endif #define FIND_MIN_MAX(addr) REAL_FIND_MIN_MAX(addr) FIND_MIN_MAX((%%FF_REGa)) @@ -1140,49 +867,20 @@ FIND_MIN_MAX((%0, %1, 8)) "movq %%mm7, %%mm4 \n\t" "psrlq $8, %%mm7 \n\t" -#if TEMPLATE_PP_MMXEXT "pminub %%mm4, %%mm7 \n\t" // min of pixels "pshufw $0xF9, %%mm7, %%mm4 \n\t" "pminub %%mm4, %%mm7 \n\t" // min of pixels "pshufw $0xFE, %%mm7, %%mm4 \n\t" "pminub %%mm4, %%mm7 \n\t" -#else - "movq %%mm7, %%mm1 \n\t" - "psubusb %%mm4, %%mm1 \n\t" - "psubb %%mm1, %%mm7 \n\t" - "movq %%mm7, %%mm4 \n\t" - "psrlq $16, %%mm7 \n\t" - "movq %%mm7, %%mm1 \n\t" - "psubusb %%mm4, %%mm1 \n\t" - "psubb %%mm1, %%mm7 \n\t" - "movq %%mm7, %%mm4 \n\t" - "psrlq $32, %%mm7 \n\t" - "movq %%mm7, %%mm1 \n\t" - "psubusb %%mm4, %%mm1 \n\t" - "psubb %%mm1, %%mm7 \n\t" -#endif "movq %%mm6, %%mm4 \n\t" "psrlq $8, %%mm6 \n\t" -#if TEMPLATE_PP_MMXEXT "pmaxub %%mm4, %%mm6 \n\t" // max of pixels "pshufw $0xF9, %%mm6, %%mm4 \n\t" "pmaxub %%mm4, %%mm6 \n\t" "pshufw $0xFE, %%mm6, %%mm4 \n\t" "pmaxub %%mm4, %%mm6 \n\t" -#else - "psubusb %%mm4, %%mm6 \n\t" - "paddb %%mm4, %%mm6 \n\t" - "movq %%mm6, %%mm4 \n\t" - "psrlq $16, %%mm6 \n\t" - "psubusb %%mm4, %%mm6 \n\t" - "paddb %%mm4, %%mm6 \n\t" - "movq %%mm6, %%mm4 \n\t" - "psrlq $32, %%mm6 \n\t" - "psubusb %%mm4, %%mm6 \n\t" - "paddb %%mm4, %%mm6 \n\t" -#endif "movq %%mm6, %%mm0 \n\t" // max "psubb %%mm7, %%mm6 \n\t" // max - min "push %%"FF_REG_a" \n\t" @@ -1320,7 +1018,7 @@ DERING_CORE((%0, %1, 8) ,(%%FF_REGd, %1, 4),%%mm2,%%mm4,%%mm0,%%mm3,%%mm5, NAMED_CONSTRAINTS_ADD(deringThreshold,b00,b02,b08) : "%"FF_REG_a, "%"FF_REG_d ); -#else // HAVE_7REGS && (TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) +#else // HAVE_7REGS && TEMPLATE_PP_MMXEXT int y; int min=255; int max=0; @@ -1438,7 +1136,7 @@ DERING_CORE((%0, %1, 8) ,(%%FF_REGd, %1, 4),%%mm2,%%mm4,%%mm0,%%mm3,%%mm5, // src[0] = src[7]=src[stride*7]=src[stride*7 + 7]=255; } #endif -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } #endif //TEMPLATE_PP_ALTIVEC @@ -1450,7 +1148,7 @@ DERING_CORE((%0, %1, 8) ,(%%FF_REGd, %1, 4),%%mm2,%%mm4,%%mm0,%%mm3,%%mm5, */ static inline void RENAME(deInterlaceInterpolateLinear)(uint8_t src[], int stride) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT src+= 4*stride; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" @@ -1503,14 +1201,13 @@ static inline void RENAME(deInterlaceInterpolateLinear)(uint8_t src[], int strid */ static inline void RENAME(deInterlaceInterpolateCubic)(uint8_t src[], int stride) { -#if TEMPLATE_PP_SSE2 || TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_SSE2 src+= stride*3; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" "lea (%%"FF_REG_a", %1, 4), %%"FF_REG_d"\n\t" "lea (%%"FF_REG_d", %1, 4), %%"FF_REG_c"\n\t" "add %1, %%"FF_REG_c" \n\t" -#if TEMPLATE_PP_SSE2 "pxor %%xmm7, %%xmm7 \n\t" #define REAL_DEINT_CUBIC(a,b,c,d,e)\ "movq " #a ", %%xmm0 \n\t"\ @@ -1526,33 +1223,6 @@ static inline void RENAME(deInterlaceInterpolateCubic)(uint8_t src[], int stride "psubw %%xmm0, %%xmm1 \n\t"\ "packuswb %%xmm1, %%xmm1 \n\t"\ "movlps %%xmm1, " #c " \n\t" -#else //TEMPLATE_PP_SSE2 - "pxor %%mm7, %%mm7 \n\t" -// 0 1 2 3 4 5 6 7 8 9 10 -// %0 eax eax+%1 eax+2%1 %0+4%1 edx edx+%1 edx+2%1 %0+8%1 edx+4%1 ecx - -#define REAL_DEINT_CUBIC(a,b,c,d,e)\ - "movq " #a ", %%mm0 \n\t"\ - "movq " #b ", %%mm1 \n\t"\ - "movq " #d ", %%mm2 \n\t"\ - "movq " #e ", %%mm3 \n\t"\ - PAVGB(%%mm2, %%mm1) /* (b+d) /2 */\ - PAVGB(%%mm3, %%mm0) /* (a+e) /2 */\ - "movq %%mm0, %%mm2 \n\t"\ - "punpcklbw %%mm7, %%mm0 \n\t"\ - "punpckhbw %%mm7, %%mm2 \n\t"\ - "movq %%mm1, %%mm3 \n\t"\ - "punpcklbw %%mm7, %%mm1 \n\t"\ - "punpckhbw %%mm7, %%mm3 \n\t"\ - "psubw %%mm1, %%mm0 \n\t" /* L(a+e - (b+d))/2 */\ - "psubw %%mm3, %%mm2 \n\t" /* H(a+e - (b+d))/2 */\ - "psraw $3, %%mm0 \n\t" /* L(a+e - (b+d))/16 */\ - "psraw $3, %%mm2 \n\t" /* H(a+e - (b+d))/16 */\ - "psubw %%mm0, %%mm1 \n\t" /* L(9b + 9d - a - e)/16 */\ - "psubw %%mm2, %%mm3 \n\t" /* H(9b + 9d - a - e)/16 */\ - "packuswb %%mm3, %%mm1 \n\t"\ - "movq %%mm1, " #c " \n\t" -#endif //TEMPLATE_PP_SSE2 #define DEINT_CUBIC(a,b,c,d,e) REAL_DEINT_CUBIC(a,b,c,d,e) DEINT_CUBIC((%0) , (%%FF_REGa, %1), (%%FF_REGa, %1, 2), (%0, %1, 4) , (%%FF_REGd, %1)) @@ -1562,13 +1232,11 @@ DEINT_CUBIC((%%FF_REGd, %1), (%0, %1, 8) , (%%FF_REGd, %1, 4), (%%FF_REGc) : : "r" (src), "r" ((x86_reg)stride) : -#if TEMPLATE_PP_SSE2 XMM_CLOBBERS("%xmm0", "%xmm1", "%xmm2", "%xmm3", "%xmm7",) -#endif "%"FF_REG_a, "%"FF_REG_d, "%"FF_REG_c ); #undef REAL_DEINT_CUBIC -#else //TEMPLATE_PP_SSE2 || TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_SSE2 int x; src+= stride*3; for(x=0; x<8; x++){ @@ -1578,7 +1246,7 @@ DEINT_CUBIC((%%FF_REGd, %1), (%0, %1, 8) , (%%FF_REGd, %1, 4), (%%FF_REGc) src[stride*9] = av_clip_uint8((-src[stride*6] + 9*src[stride*8] + 9*src[stride*10] - src[stride*12])>>4); src++; } -#endif //TEMPLATE_PP_SSE2 || TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_SSE2 } /** @@ -1590,7 +1258,7 @@ DEINT_CUBIC((%%FF_REGd, %1), (%0, %1, 8) , (%%FF_REGd, %1, 4), (%%FF_REGc) */ static inline void RENAME(deInterlaceFF)(uint8_t src[], int stride, uint8_t *tmp) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT src+= stride*4; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" @@ -1639,7 +1307,7 @@ DEINT_FF((%%FF_REGd, %1), (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 : : "r" (src), "r" ((x86_reg)stride), "r"(tmp) : "%"FF_REG_a, "%"FF_REG_d ); -#else //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_MMXEXT int x; src+= stride*4; for(x=0; x<8; x++){ @@ -1657,7 +1325,7 @@ DEINT_FF((%%FF_REGd, %1), (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 src++; } -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } /** @@ -1669,7 +1337,7 @@ DEINT_FF((%%FF_REGd, %1), (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 */ static inline void RENAME(deInterlaceL5)(uint8_t src[], int stride, uint8_t *tmp, uint8_t *tmp2) { -#if (TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#if TEMPLATE_PP_MMXEXT && HAVE_6REGS src+= stride*4; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" @@ -1729,7 +1397,7 @@ DEINT_L5(%%mm1, %%mm0, (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 : : "r" (src), "r" ((x86_reg)stride), "r"(tmp), "r"(tmp2) : "%"FF_REG_a, "%"FF_REG_d ); -#else //(TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#else //TEMPLATE_PP_MMXEXT && HAVE_6REGS int x; src+= stride*4; for(x=0; x<8; x++){ @@ -1758,7 +1426,7 @@ DEINT_L5(%%mm1, %%mm0, (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 src++; } -#endif //(TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#endif // TEMPLATE_PP_MMXEXT && HAVE_6REGS } /** @@ -1770,7 +1438,7 @@ DEINT_L5(%%mm1, %%mm0, (%%FF_REGd, %1, 2), (%0, %1, 8) , (%%FF_REGd, %1, 4 */ static inline void RENAME(deInterlaceBlendLinear)(uint8_t src[], int stride, uint8_t *tmp) { -#if TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#if TEMPLATE_PP_MMXEXT src+= 4*stride; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" @@ -1817,7 +1485,7 @@ static inline void RENAME(deInterlaceBlendLinear)(uint8_t src[], int stride, uin : : "r" (src), "r" ((x86_reg)stride), "r" (tmp) : "%"FF_REG_a, "%"FF_REG_d ); -#else //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#else //TEMPLATE_PP_MMXEXT int a, b, c, x; src+= 4*stride; @@ -1860,7 +1528,7 @@ static inline void RENAME(deInterlaceBlendLinear)(uint8_t src[], int stride, uin src += 4; tmp += 4; } -#endif //TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW +#endif //TEMPLATE_PP_MMXEXT } /** @@ -1871,9 +1539,8 @@ static inline void RENAME(deInterlaceBlendLinear)(uint8_t src[], int stride, uin */ static inline void RENAME(deInterlaceMedian)(uint8_t src[], int stride) { -#if TEMPLATE_PP_MMX - src+= 4*stride; #if TEMPLATE_PP_MMXEXT + src+= 4*stride; __asm__ volatile( "lea (%0, %1), %%"FF_REG_a" \n\t" "lea (%%"FF_REG_a", %1, 4), %%"FF_REG_d"\n\t" @@ -1922,48 +1589,6 @@ static inline void RENAME(deInterlaceMedian)(uint8_t src[], int stride) : "%"FF_REG_a, "%"FF_REG_d ); -#else // MMX without MMX2 - __asm__ volatile( - "lea (%0, %1), %%"FF_REG_a" \n\t" - "lea (%%"FF_REG_a", %1, 4), %%"FF_REG_d"\n\t" -// 0 1 2 3 4 5 6 7 8 9 -// %0 eax eax+%1 eax+2%1 %0+4%1 edx edx+%1 edx+2%1 %0+8%1 edx+4%1 - "pxor %%mm7, %%mm7 \n\t" - -#define REAL_MEDIAN(a,b,c)\ - "movq " #a ", %%mm0 \n\t"\ - "movq " #b ", %%mm2 \n\t"\ - "movq " #c ", %%mm1 \n\t"\ - "movq %%mm0, %%mm3 \n\t"\ - "movq %%mm1, %%mm4 \n\t"\ - "movq %%mm2, %%mm5 \n\t"\ - "psubusb %%mm1, %%mm3 \n\t"\ - "psubusb %%mm2, %%mm4 \n\t"\ - "psubusb %%mm0, %%mm5 \n\t"\ - "pcmpeqb %%mm7, %%mm3 \n\t"\ - "pcmpeqb %%mm7, %%mm4 \n\t"\ - "pcmpeqb %%mm7, %%mm5 \n\t"\ - "movq %%mm3, %%mm6 \n\t"\ - "pxor %%mm4, %%mm3 \n\t"\ - "pxor %%mm5, %%mm4 \n\t"\ - "pxor %%mm6, %%mm5 \n\t"\ - "por %%mm3, %%mm1 \n\t"\ - "por %%mm4, %%mm2 \n\t"\ - "por %%mm5, %%mm0 \n\t"\ - "pand %%mm2, %%mm0 \n\t"\ - "pand %%mm1, %%mm0 \n\t"\ - "movq %%mm0, " #b " \n\t" -#define MEDIAN(a,b,c) REAL_MEDIAN(a,b,c) - -MEDIAN((%0) , (%%FF_REGa) , (%%FF_REGa, %1)) -MEDIAN((%%FF_REGa, %1), (%%FF_REGa, %1, 2), (%0, %1, 4)) -MEDIAN((%0, %1, 4) , (%%FF_REGd) , (%%FF_REGd, %1)) -MEDIAN((%%FF_REGd, %1), (%%FF_REGd, %1, 2), (%0, %1, 8)) - - : : "r" (src), "r" ((x86_reg)stride) - : "%"FF_REG_a, "%"FF_REG_d - ); -#endif //TEMPLATE_PP_MMXEXT #else //TEMPLATE_PP_MMX int x, y; src+= 4*stride; @@ -2165,7 +1790,7 @@ static inline void RENAME(tempNoiseReducer)(uint8_t *src, int stride, #define FAST_L2_DIFF //#define L1_DIFF //u should change the thresholds too if u try that one -#if (TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#if TEMPLATE_PP_MMXEXT && HAVE_6REGS __asm__ volatile( "lea (%2, %2, 2), %%"FF_REG_a" \n\t" // 3*stride "lea (%2, %2, 4), %%"FF_REG_d" \n\t" // 5*stride @@ -2454,7 +2079,7 @@ L2_DIFF_CORE((%0, %%FF_REGc) , (%1, %%FF_REGc)) NAMED_CONSTRAINTS_ADD(b80) : "%"FF_REG_a, "%"FF_REG_d, "%"FF_REG_c, "memory" ); -#else //(TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#else //TEMPLATE_PP_MMXEXT && HAVE_6REGS { int y; int d=0; @@ -2537,11 +2162,11 @@ Switch between } } } -#endif //(TEMPLATE_PP_MMXEXT || TEMPLATE_PP_3DNOW) && HAVE_6REGS +#endif //TEMPLATE_PP_MMXEXT && HAVE_6REGS } #endif //TEMPLATE_PP_ALTIVEC -#if TEMPLATE_PP_MMX +#if TEMPLATE_PP_MMXEXT /** * accurate deblock filter */ @@ -2945,7 +2570,6 @@ static av_always_inline void RENAME(do_a_deblock)(uint8_t *src, int step, int st "movq (%4), %%mm2 \n\t" // 2L0 - 5L1 + 5L2 - 2L3 "movq 8(%4), %%mm3 \n\t" // 2H0 - 5H1 + 5H2 - 2H3 -#if TEMPLATE_PP_MMXEXT "movq %%mm7, %%mm6 \n\t" // 0 "psubw %%mm0, %%mm6 \n\t" "pmaxsw %%mm6, %%mm0 \n\t" // |2L4 - 5L5 + 5L6 - 2L7| @@ -2958,36 +2582,9 @@ static av_always_inline void RENAME(do_a_deblock)(uint8_t *src, int step, int st "movq %%mm7, %%mm6 \n\t" // 0 "psubw %%mm3, %%mm6 \n\t" "pmaxsw %%mm6, %%mm3 \n\t" // |2H0 - 5H1 + 5H2 - 2H3| -#else - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm0, %%mm6 \n\t" - "pxor %%mm6, %%mm0 \n\t" - "psubw %%mm6, %%mm0 \n\t" // |2L4 - 5L5 + 5L6 - 2L7| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm1, %%mm6 \n\t" - "pxor %%mm6, %%mm1 \n\t" - "psubw %%mm6, %%mm1 \n\t" // |2H4 - 5H5 + 5H6 - 2H7| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm2, %%mm6 \n\t" - "pxor %%mm6, %%mm2 \n\t" - "psubw %%mm6, %%mm2 \n\t" // |2L0 - 5L1 + 5L2 - 2L3| - "movq %%mm7, %%mm6 \n\t" // 0 - "pcmpgtw %%mm3, %%mm6 \n\t" - "pxor %%mm6, %%mm3 \n\t" - "psubw %%mm6, %%mm3 \n\t" // |2H0 - 5H1 + 5H2 - 2H3| -#endif -#if TEMPLATE_PP_MMXEXT "pminsw %%mm2, %%mm0 \n\t" "pminsw %%mm3, %%mm1 \n\t" -#else - "movq %%mm0, %%mm6 \n\t" - "psubusw %%mm2, %%mm6 \n\t" - "psubw %%mm6, %%mm0 \n\t" - "movq %%mm1, %%mm6 \n\t" - "psubusw %%mm3, %%mm6 \n\t" - "psubw %%mm6, %%mm1 \n\t" -#endif "movd %2, %%mm2 \n\t" // QP "punpcklbw %%mm7, %%mm2 \n\t" @@ -3041,17 +2638,8 @@ static av_always_inline void RENAME(do_a_deblock)(uint8_t *src, int step, int st "pand %%mm2, %%mm4 \n\t" "pand %%mm3, %%mm5 \n\t" -#if TEMPLATE_PP_MMXEXT "pminsw %%mm0, %%mm4 \n\t" "pminsw %%mm1, %%mm5 \n\t" -#else - "movq %%mm4, %%mm2 \n\t" - "psubusw %%mm0, %%mm2 \n\t" - "psubw %%mm2, %%mm4 \n\t" - "movq %%mm5, %%mm2 \n\t" - "psubusw %%mm1, %%mm2 \n\t" - "psubw %%mm2, %%mm5 \n\t" -#endif "pxor %%mm6, %%mm4 \n\t" "pxor %%mm7, %%mm5 \n\t" "psubw %%mm6, %%mm4 \n\t" @@ -3088,18 +2676,14 @@ static void RENAME(postProcess)(const uint8_t src[], int srcStride, uint8_t dst[ static inline void RENAME(blockCopy)(uint8_t dst[], int dstStride, const uint8_t src[], int srcStride, int levelFix, int64_t *packedOffsetAndScale) { -#if !TEMPLATE_PP_MMX || !HAVE_6REGS - int i; -#endif if(levelFix){ -#if TEMPLATE_PP_MMX && HAVE_6REGS +#if TEMPLATE_PP_MMXEXT && HAVE_6REGS __asm__ volatile( "movq (%%"FF_REG_a"), %%mm2 \n\t" // packedYOffset "movq 8(%%"FF_REG_a"), %%mm3 \n\t" // packedYScale "lea (%2,%4), %%"FF_REG_a" \n\t" "lea (%3,%5), %%"FF_REG_d" \n\t" "pxor %%mm4, %%mm4 \n\t" -#if TEMPLATE_PP_MMXEXT #define REAL_SCALED_CPY(src1, src2, dst1, dst2) \ "movq " #src1 ", %%mm0 \n\t"\ "movq " #src1 ", %%mm5 \n\t"\ @@ -3122,34 +2706,6 @@ static inline void RENAME(blockCopy)(uint8_t dst[], int dstStride, const uint8_t "movq %%mm0, " #dst1 " \n\t"\ "movq %%mm1, " #dst2 " \n\t"\ -#else //TEMPLATE_PP_MMXEXT -#define REAL_SCALED_CPY(src1, src2, dst1, dst2) \ - "movq " #src1 ", %%mm0 \n\t"\ - "movq " #src1 ", %%mm5 \n\t"\ - "punpcklbw %%mm4, %%mm0 \n\t"\ - "punpckhbw %%mm4, %%mm5 \n\t"\ - "psubw %%mm2, %%mm0 \n\t"\ - "psubw %%mm2, %%mm5 \n\t"\ - "movq " #src2 ", %%mm1 \n\t"\ - "psllw $6, %%mm0 \n\t"\ - "psllw $6, %%mm5 \n\t"\ - "pmulhw %%mm3, %%mm0 \n\t"\ - "movq " #src2 ", %%mm6 \n\t"\ - "pmulhw %%mm3, %%mm5 \n\t"\ - "punpcklbw %%mm4, %%mm1 \n\t"\ - "punpckhbw %%mm4, %%mm6 \n\t"\ - "psubw %%mm2, %%mm1 \n\t"\ - "psubw %%mm2, %%mm6 \n\t"\ - "psllw $6, %%mm1 \n\t"\ - "psllw $6, %%mm6 \n\t"\ - "pmulhw %%mm3, %%mm1 \n\t"\ - "pmulhw %%mm3, %%mm6 \n\t"\ - "packuswb %%mm5, %%mm0 \n\t"\ - "packuswb %%mm6, %%mm1 \n\t"\ - "movq %%mm0, " #dst1 " \n\t"\ - "movq %%mm1, " #dst2 " \n\t"\ - -#endif //TEMPLATE_PP_MMXEXT #define SCALED_CPY(src1, src2, dst1, dst2)\ REAL_SCALED_CPY(src1, src2, dst1, dst2) @@ -3170,7 +2726,7 @@ SCALED_CPY((%%FF_REGa, %4), (%%FF_REGa, %4, 2), (%%FF_REGd, %5), (%%FF_REGd, %5, : "%"FF_REG_d ); #else //TEMPLATE_PP_MMX && HAVE_6REGS - for(i=0; i<8; i++) + for (int i = 0; i < 8; i++) memcpy( &(dst[dstStride*i]), &(src[srcStride*i]), BLOCK_SIZE); #endif //TEMPLATE_PP_MMX && HAVE_6REGS @@ -3203,7 +2759,7 @@ SIMPLE_CPY((%%FF_REGa, %2), (%%FF_REGa, %2, 2), (%%FF_REGd, %3), (%%FF_REGd, %3, : "%"FF_REG_a, "%"FF_REG_d ); #else //TEMPLATE_PP_MMX && HAVE_6REGS - for(i=0; i<8; i++) + for (int i = 0; i < 8; i++) memcpy( &(dst[dstStride*i]), &(src[srcStride*i]), BLOCK_SIZE); #endif //TEMPLATE_PP_MMX && HAVE_6REGS @@ -3696,9 +3252,7 @@ static void RENAME(postProcess)(const uint8_t src[], int srcStride, uint8_t dst[ } } } -#if TEMPLATE_PP_3DNOW - __asm__ volatile("femms"); -#elif TEMPLATE_PP_MMX +#if TEMPLATE_PP_MMX __asm__ volatile("emms"); #endif @@ -3734,5 +3288,4 @@ static void RENAME(postProcess)(const uint8_t src[], int srcStride, uint8_t dst[ #undef TEMPLATE_PP_ALTIVEC #undef TEMPLATE_PP_MMX #undef TEMPLATE_PP_MMXEXT -#undef TEMPLATE_PP_3DNOW #undef TEMPLATE_PP_SSE2