From patchwork Sun Nov 19 03:39:37 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Almer X-Patchwork-Id: 6189 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.2.161.94 with SMTP id m30csp2410279jah; Sat, 18 Nov 2017 19:40:28 -0800 (PST) X-Google-Smtp-Source: AGs4zMaPcJ3lHUFFTIZ1NnIa5Vm/3qa2Ax0OubDRB6o548J31fFTwTlfiqjvL3KD14CF/atePi5m X-Received: by 10.28.19.73 with SMTP id 70mr7178124wmt.87.1511062828187; Sat, 18 Nov 2017 19:40:28 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1511062828; cv=none; d=google.com; s=arc-20160816; b=DJPrBedmRW7KbAC/ZtdQMIroPJv7hMvdCsDQIs1PD/KgXJ5a4PGW4UsCNHoWBl5QB3 MCpCZ7S2Sqg/7twMDgsF376DlMvyr2ixTpUTBROPgSR4wR2hSCW8yxi+tNPGaz9ajIDz iI4pKg6sjtzFm6ggyafEgjQNVcMoxbSZ+gm8yRaqPEMczTFvRvavp/vUKKAB/tHIqwxe riSbrVGV0HYWyl0b/zUExaqSkGXvoz9BIbhGDhtOAnTdf7lKff1x8+NqUOHkABIy0D6p Rt++uGXNRsnAZb5DIRd7j11PMN6pCHOgy/gUCO7usXFJkF1USZHbEsA17aJD3nbfFjOR T7HQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:references:in-reply-to:message-id:date :to:from:dkim-signature:delivered-to:arc-authentication-results; bh=psRHKAFIwil97YcZhgj2gdx4Ls9t9o6Y3yxEtGUdKq0=; b=EyyI8XR1XpJgG8u+DGZqZdra6Oa9SXzCwOQeJMTzg4ETJIQDzacAbHhShYsnA7Yiqm 6PCO7/yrotgZT0IDSi1l5itbSJofuyPVRkWyhA0ttumTjX+p9yyZqUx0TrBDdZKBdoZ3 Q6swYygQBDBhNEtCfSH8wjUE4T8VwRpixU4vjARuaveh+YxKo2Ou3oxd2IR/ru7SdZeO iCmoo7bdBbY/ymb7KN/fN2igx6t2z4Yd8bmTCXKbp5rNuWQmNiOI2MYWSlaSmxH/V1sf kI0VmQDAif1jQqhTgRbXoat8F5X+jDrWGmbV82KkZA4g1WdZ+1838GCwWXQl/cX9jKHr hUUw== ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@gmail.com header.s=20161025 header.b=t/WQgqPn; 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=NONE 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 o75si4586193wmd.200.2017.11.18.19.40.27; Sat, 18 Nov 2017 19:40:28 -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=@gmail.com header.s=20161025 header.b=t/WQgqPn; 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=NONE 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 0992168A19F; Sun, 19 Nov 2017 05:39:55 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-qt0-f195.google.com (mail-qt0-f195.google.com [209.85.216.195]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 0120968A124 for ; Sun, 19 Nov 2017 05:39:49 +0200 (EET) Received: by mail-qt0-f195.google.com with SMTP id u42so11241529qte.7 for ; Sat, 18 Nov 2017 19:40:05 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:subject:date:message-id:in-reply-to:references; bh=M5EJBL0d/1NCy0fd9vgVVq1Xp3xGerGNjj0axdK6m/k=; b=t/WQgqPn+PLAIt3QBskYOJwiyclqJScVtwh36yRf7BPkWzjgepnkQ1rPQ6T8oRncdF J0PzzOuwtfqi3uTF9QI6ufR6LwZ2gJ2klb5BYKu4i6+nuCiANi+VcFQZexA/WM4q6lSI 6jiunowDWX2V65ICbbOuNt4NZhav9lakJQ9W9F0ogUD/nOCrwNkNft+3246W04S9VRQJ QTXRs26bFnOSVYPoMiE8aHwPwjxgtEgOjjTaZ5GudOYTECwVdZ1e/NUsAW1oOnp/hbfa mcS7rIokLc0M/r9lr/88V/Qpfgh4wBd/k3hDtFRdhRP/QaP6ljwyf7hZSE28hZTghx1L PJXQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=M5EJBL0d/1NCy0fd9vgVVq1Xp3xGerGNjj0axdK6m/k=; b=qI4iwfdc6TkDzQL/WLW/iSDM4PG2WUjnuke04BOsUozdBpBLcX3LbO+s6efWSs8gyO cHVZK1syBQZnn68D4eMXsf3d+NzSrOOr0eTqN/cxrxgmE/BRmqdpRpuYDdb8t3D67r90 06fYVhYc7sPVA8XTagVWxJN9pJZqO+eJrW1NBGX1zm8rcPNhjtLhaW4AJQnStyZj6s/p bL9nnRsfZj0pItd78+68itW2L92ZPQGs4Zk74zGOBgCzSOuQr7I/i0xb/Angkzda8ess qmLoAnsxzt4FgEPA0yWQITf5o6efun2bDbN6CQJ8DXq7KV9v+H1DZ1pPhhYOatkQAAf1 iV0A== X-Gm-Message-State: AJaThX52HfLxY7YDDSdzoYIa1Cn1WIXONteee2mlJ3zlC7wvINibMC4+ TUVQ1NCir4SZPULBhEzLLtADqg== X-Received: by 10.200.15.24 with SMTP id e24mr16092076qtk.100.1511062804735; Sat, 18 Nov 2017 19:40:04 -0800 (PST) Received: from localhost.localdomain ([181.231.59.220]) by smtp.gmail.com with ESMTPSA id g47sm5059767qtc.69.2017.11.18.19.40.03 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Sat, 18 Nov 2017 19:40:04 -0800 (PST) From: James Almer To: ffmpeg-devel@ffmpeg.org Date: Sun, 19 Nov 2017 00:39:37 -0300 Message-Id: <20171119033937.9660-3-jamrial@gmail.com> X-Mailer: git-send-email 2.14.2 In-Reply-To: <20171119033937.9660-1-jamrial@gmail.com> References: <20171119033937.9660-1-jamrial@gmail.com> Subject: [FFmpeg-devel] [PATCH 3/3] x86/jpeg2000dsp: add ff_ict_float_{fma3, fma4} X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.20 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 MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" jpeg2000_ict_float_c: 2296.0 jpeg2000_ict_float_sse: 628.0 jpeg2000_ict_float_avx: 317.0 jpeg2000_ict_float_fma3: 262.0 Signed-off-by: James Almer --- libavcodec/x86/jpeg2000dsp.asm | 20 ++++++++++++++++++++ libavcodec/x86/jpeg2000dsp_init.c | 10 ++++++++++ 2 files changed, 30 insertions(+) diff --git a/libavcodec/x86/jpeg2000dsp.asm b/libavcodec/x86/jpeg2000dsp.asm index 56b5fbd606..61dfdd4f71 100644 --- a/libavcodec/x86/jpeg2000dsp.asm +++ b/libavcodec/x86/jpeg2000dsp.asm @@ -74,6 +74,19 @@ align 16 movaps m1, [src1q+csizeq] movaps m2, [src2q+csizeq] +%if cpuflag(fma4) || cpuflag(fma3) +%if cpuflag(fma4) + fnmaddps m5, m1, ICT1, m0 + fmaddps m4, m2, ICT0, m0 +%else ; fma3 + movaps m5, m1 + movaps m4, m2 + fnmaddps m5, m5, ICT1, m0 + fmaddps m4, m4, ICT0, m0 +%endif + fmaddps m0, m1, ICT3, m0 + fnmaddps m5, m2, ICT2, m5 +%else ; non FMA %if cpuflag(avx) mulps m5, m1, ICT1 mulps m4, m2, ICT0 @@ -93,6 +106,7 @@ align 16 addps m4, m4, m0 addps m0, m0, m1 subps m5, m5, m2 +%endif movaps [src0q+csizeq], m4 movaps [src2q+csizeq], m0 @@ -106,6 +120,12 @@ INIT_XMM sse ICT_FLOAT 10 INIT_YMM avx ICT_FLOAT 9 +%if HAVE_FMA4_EXTERNAL +INIT_XMM fma4 +ICT_FLOAT 9 +%endif +INIT_YMM fma3 +ICT_FLOAT 9 ;*************************************************************************** ; ff_rct_int_(int32_t *src0, int32_t *src1, int32_t *src2, int csize) diff --git a/libavcodec/x86/jpeg2000dsp_init.c b/libavcodec/x86/jpeg2000dsp_init.c index baa81383ea..7310a1d0e1 100644 --- a/libavcodec/x86/jpeg2000dsp_init.c +++ b/libavcodec/x86/jpeg2000dsp_init.c @@ -26,6 +26,8 @@ void ff_ict_float_sse(void *src0, void *src1, void *src2, int csize); void ff_ict_float_avx(void *src0, void *src1, void *src2, int csize); +void ff_ict_float_fma3(void *src0, void *src1, void *src2, int csize); +void ff_ict_float_fma4(void *src0, void *src1, void *src2, int csize); void ff_rct_int_sse2 (void *src0, void *src1, void *src2, int csize); void ff_rct_int_avx2 (void *src0, void *src1, void *src2, int csize); @@ -44,6 +46,14 @@ av_cold void ff_jpeg2000dsp_init_x86(Jpeg2000DSPContext *c) c->mct_decode[FF_DWT97] = ff_ict_float_avx; } + if (EXTERNAL_FMA4(cpu_flags)) { + c->mct_decode[FF_DWT97] = ff_ict_float_fma4; + } + + if (EXTERNAL_FMA3_FAST(cpu_flags)) { + c->mct_decode[FF_DWT97] = ff_ict_float_fma3; + } + if (EXTERNAL_AVX2_FAST(cpu_flags)) { c->mct_decode[FF_DWT53] = ff_rct_int_avx2; }