From patchwork Thu Dec 21 13:40:57 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: James Darnley X-Patchwork-Id: 6889 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.2.79.195 with SMTP id r64csp939078jad; Thu, 21 Dec 2017 05:49:20 -0800 (PST) X-Google-Smtp-Source: ACJfBovRu6q12seT33kC3Vprt+KIRoqW1LC8W+MocQgxw2y6j0nIdCh+exoWZ8I9n0PRGA6gBIv1 X-Received: by 10.28.101.11 with SMTP id z11mr8918691wmb.110.1513864160246; Thu, 21 Dec 2017 05:49:20 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1513864160; cv=none; d=google.com; s=arc-20160816; b=PRdvhuR/EKR2b/92wvDo5CEjZYet2EBgoXRHF2jfCrpADcKRLL8F7dcdmHLRAEXSsj +XjHY0TN9IowJpdJOGaPxcPVSkGbaw40694l8jgF7eaB029Tk3vnCGgGkP0YFFhI6ZzM rYV4Po6YABOkGWQvNbT7G4sVrnE4Eur+GpdTZ86cC3iIXdeh3QefJSKC+jcjnY87fwFq CODBU5PVDyVclBanVzDB2jzO8GDHG4g/q0D0N/HLYpmpMuGUysC8o+nKGaySOazaWtH7 3kFrSXQnI9L9eSmK33UVrNmdF37aE2pkPptID0NkpErYib9Rb+oI18/KMiQfg4z/luXG k1gg== 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=ub8eGN5BWuV+MlNIp5GlXHgOxzdagKZ2mmT6UOX8jo4=; b=DI5LyVh9F+xf8Ys1Kt8mS1rUkyLalb6SXAxjZyK6vLH6ByUMJ50sPXoTqK6zph6koR 9Ccl0gIM/mjwLaYW1zSguuFluWE7YeMky47wAw/wCKzFFyZ17yMn2IUe2EPjILFNBnyM sYsHnnDgOJQyuuNkvVB71fXr0ywRkoc+ytFahZaUPDj9aThld1G/HvFOEDRBZZKbf7p5 uw1MjqADElDIad5Is+78MbC78qaflItJR1hofOKyHWGU58o0hqSOxWjeY0q0F1tNaX14 x3+lK7ld5KwSvZMP+dW0hDAlYmtBMNRZiU7o153vkeUNtebgbsk+qLZFoQp5oCq8qLiR rC1w== ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@ob-encoder-com.20150623.gappssmtp.com header.s=20150623 header.b=A9O3803I; 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 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id g28si4866227wmi.214.2017.12.21.05.49.19; Thu, 21 Dec 2017 05:49:20 -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=@ob-encoder-com.20150623.gappssmtp.com header.s=20150623 header.b=A9O3803I; 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 Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 0B5A968834E; Thu, 21 Dec 2017 15:49:02 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-wm0-f67.google.com (mail-wm0-f67.google.com [74.125.82.67]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 44D8E688297 for ; Thu, 21 Dec 2017 15:48:55 +0200 (EET) Received: by mail-wm0-f67.google.com with SMTP id 64so15885039wme.3 for ; Thu, 21 Dec 2017 05:49:06 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ob-encoder-com.20150623.gappssmtp.com; s=20150623; h=sender:from:to:subject:date:message-id:in-reply-to:references; bh=5fNM7gqRbHQDdYblc0ke9evT/mGn9LTwmQ0nksyarlk=; b=A9O3803IXHmLgqeCmISOzdCSHsPoEl5DT1P5UpmW2yYR+Kq6YvCLAROYBeB1DF/6D7 RzcQ4KWySjL4tuAzVTS3vFH6o06C8tb4/p/bIW0Jzu6Xe37jARrx/lAvh0mBOZjOlFmj jRuRqfuAj+YsRmMVWl2zc+oWBYznYB5L9z7miDTR//z2C3uLZHvTyrOroUB1n4aSC16f ZpAFf+HUJz3/3m+IJ9V0E9b/9VGpBdKCn8RmwxnDI05cC9O8CU7Lzd27+EJqPETEre40 +3Z6lPf+xDt3j6m1o6YlfrnFkkwJwd6rKekNWQlKJ0cBH6jeUaDFZHj9SGM1aff8Ooq6 n9vA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:from:to:subject:date:message-id :in-reply-to:references; bh=5fNM7gqRbHQDdYblc0ke9evT/mGn9LTwmQ0nksyarlk=; b=QwOJyVJOyBZQTvjpERhF2qyw6B+afWwoH7T6mATr1YdC6H6aWyOewmYnmm9oV4thU8 qtzVQEc73LLNuNlwtzPwMu4/YegQB/79kOZ4HOQbvExOZlRk95H2of+1fuo0zOKncxJq xUbWXzVMAzL0/MskGwojKC36JlIWyI1qV0iBrpqUAqVf+RP+BrfI57UkXErTpg2rEYrd X1wZaaC7/YdemEwInC7ptMT3hoyne42oyz9Kqvgl4O0+hel1pduFVajZ5zSg2ulS6L/x bM4CKk+wnCTODmJyNDeBEtFz/OWPGenXkr/gWWhFMJf3gZpxX1uQqSsapYzRalpsTdII UcUQ== X-Gm-Message-State: AKGB3mLWi2zLo5Nl4x36ndrtgZxd7RakBNFA47HcXxQyC9V4nxPcaOH6 R0YqSrUgcWAAeH378DD7/nZZEKCg X-Received: by 10.80.146.81 with SMTP id j17mr10111011eda.159.1513863677593; Thu, 21 Dec 2017 05:41:17 -0800 (PST) Received: from Highwind.systemlords.lan (d51a44418.access.telenet.be. [81.164.68.24]) by smtp.gmail.com with ESMTPSA id h56sm16517188ede.45.2017.12.21.05.41.16 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 21 Dec 2017 05:41:17 -0800 (PST) From: James Darnley To: ffmpeg-devel@ffmpeg.org Date: Thu, 21 Dec 2017 14:40:57 +0100 Message-Id: <20171221134102.3959-3-jdarnley@obe.tv> X-Mailer: git-send-email 2.15.1 In-Reply-To: <20171221134102.3959-1-jdarnley@obe.tv> References: <20171221134102.3959-1-jdarnley@obe.tv> Subject: [FFmpeg-devel] [PATCH 2/7] avutil: add AVX-512 flags 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" --- Changelog | 1 + doc/APIchanges | 3 +++ libavutil/cpu.c | 6 +++++- libavutil/cpu.h | 1 + libavutil/tests/cpu.c | 1 + libavutil/version.h | 2 +- libavutil/x86/cpu.h | 2 ++ 7 files changed, 14 insertions(+), 2 deletions(-) diff --git a/Changelog b/Changelog index ee48876128..f44cec679f 100644 --- a/Changelog +++ b/Changelog @@ -27,6 +27,7 @@ version : - video setrange filter - nsp demuxer - support LibreSSL (via libtls) +- AVX-512/ZMM support added version 3.4: diff --git a/doc/APIchanges b/doc/APIchanges index da444ffb7c..df79758e86 100644 --- a/doc/APIchanges +++ b/doc/APIchanges @@ -15,6 +15,9 @@ libavutil: 2017-10-21 API changes, most recent first: +2017-12-xx - xxxxxxx - lavu 56.7.100 - cpu.h + AVX-512 flags added. + 2017-xx-xx - xxxxxxx - lavc 58.8.100 - avcodec.h The MediaCodec decoders now support AVCodecContext.hw_device_ctx. diff --git a/libavutil/cpu.c b/libavutil/cpu.c index c8401b8258..6548cc3042 100644 --- a/libavutil/cpu.c +++ b/libavutil/cpu.c @@ -80,7 +80,8 @@ void av_force_cpu_flags(int arg){ AV_CPU_FLAG_XOP | AV_CPU_FLAG_FMA3 | AV_CPU_FLAG_FMA4 | - AV_CPU_FLAG_AVX2 )) + AV_CPU_FLAG_AVX2 | + AV_CPU_FLAG_AVX512 )) && !(arg & AV_CPU_FLAG_MMX)) { av_log(NULL, AV_LOG_WARNING, "MMX implied by specified flags\n"); arg |= AV_CPU_FLAG_MMX; @@ -126,6 +127,7 @@ int av_parse_cpu_flags(const char *s) #define CPUFLAG_AVX2 (AV_CPU_FLAG_AVX2 | CPUFLAG_AVX) #define CPUFLAG_BMI2 (AV_CPU_FLAG_BMI2 | AV_CPU_FLAG_BMI1) #define CPUFLAG_AESNI (AV_CPU_FLAG_AESNI | CPUFLAG_SSE42) +#define CPUFLAG_AVX512 (AV_CPU_FLAG_AVX512 | CPUFLAG_AVX2) static const AVOption cpuflags_opts[] = { { "flags" , NULL, 0, AV_OPT_TYPE_FLAGS, { .i64 = 0 }, INT64_MIN, INT64_MAX, .unit = "flags" }, #if ARCH_PPC @@ -154,6 +156,7 @@ int av_parse_cpu_flags(const char *s) { "3dnowext", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = CPUFLAG_3DNOWEXT }, .unit = "flags" }, { "cmov", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_CMOV }, .unit = "flags" }, { "aesni" , NULL, 0, AV_OPT_TYPE_CONST, { .i64 = CPUFLAG_AESNI }, .unit = "flags" }, + { "avx512" , NULL, 0, AV_OPT_TYPE_CONST, { .i64 = CPUFLAG_AVX512 }, .unit = "flags" }, #elif ARCH_ARM { "armv5te", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_ARMV5TE }, .unit = "flags" }, { "armv6", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_ARMV6 }, .unit = "flags" }, @@ -216,6 +219,7 @@ int av_parse_cpu_caps(unsigned *flags, const char *s) { "3dnowext", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_3DNOWEXT }, .unit = "flags" }, { "cmov", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_CMOV }, .unit = "flags" }, { "aesni", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_AESNI }, .unit = "flags" }, + { "avx512" , NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_AVX512 }, .unit = "flags" }, #define CPU_FLAG_P2 AV_CPU_FLAG_CMOV | AV_CPU_FLAG_MMX #define CPU_FLAG_P3 CPU_FLAG_P2 | AV_CPU_FLAG_MMX2 | AV_CPU_FLAG_SSE diff --git a/libavutil/cpu.h b/libavutil/cpu.h index 9e5d40affe..8bb9eb606b 100644 --- a/libavutil/cpu.h +++ b/libavutil/cpu.h @@ -55,6 +55,7 @@ #define AV_CPU_FLAG_FMA3 0x10000 ///< Haswell FMA3 functions #define AV_CPU_FLAG_BMI1 0x20000 ///< Bit Manipulation Instruction Set 1 #define AV_CPU_FLAG_BMI2 0x40000 ///< Bit Manipulation Instruction Set 2 +#define AV_CPU_FLAG_AVX512 0x100000 ///< AVX-512 functions: requires OS support even if YMM/ZMM registers aren't used #define AV_CPU_FLAG_ALTIVEC 0x0001 ///< standard #define AV_CPU_FLAG_VSX 0x0002 ///< ISA 2.06 diff --git a/libavutil/tests/cpu.c b/libavutil/tests/cpu.c index f02a54cbbb..ce45b715a0 100644 --- a/libavutil/tests/cpu.c +++ b/libavutil/tests/cpu.c @@ -73,6 +73,7 @@ static const struct { { AV_CPU_FLAG_BMI1, "bmi1" }, { AV_CPU_FLAG_BMI2, "bmi2" }, { AV_CPU_FLAG_AESNI, "aesni" }, + { AV_CPU_FLAG_AVX512, "avx512" }, #endif { 0 } }; diff --git a/libavutil/version.h b/libavutil/version.h index 9ae9768d4d..d81ec6fa7b 100644 --- a/libavutil/version.h +++ b/libavutil/version.h @@ -79,7 +79,7 @@ */ #define LIBAVUTIL_VERSION_MAJOR 56 -#define LIBAVUTIL_VERSION_MINOR 6 +#define LIBAVUTIL_VERSION_MINOR 7 #define LIBAVUTIL_VERSION_MICRO 100 #define LIBAVUTIL_VERSION_INT AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \ diff --git a/libavutil/x86/cpu.h b/libavutil/x86/cpu.h index 309b8e746c..7f4e5d08bb 100644 --- a/libavutil/x86/cpu.h +++ b/libavutil/x86/cpu.h @@ -50,6 +50,7 @@ #define X86_FMA4(flags) CPUEXT(flags, FMA4) #define X86_AVX2(flags) CPUEXT(flags, AVX2) #define X86_AESNI(flags) CPUEXT(flags, AESNI) +#define X86_AVX512(flags) CPUEXT(flags, AVX512) #define EXTERNAL_AMD3DNOW(flags) CPUEXT_SUFFIX(flags, _EXTERNAL, AMD3DNOW) #define EXTERNAL_AMD3DNOWEXT(flags) CPUEXT_SUFFIX(flags, _EXTERNAL, AMD3DNOWEXT) @@ -79,6 +80,7 @@ #define EXTERNAL_AVX2_FAST(flags) CPUEXT_SUFFIX_FAST2(flags, _EXTERNAL, AVX2, AVX) #define EXTERNAL_AVX2_SLOW(flags) CPUEXT_SUFFIX_SLOW2(flags, _EXTERNAL, AVX2, AVX) #define EXTERNAL_AESNI(flags) CPUEXT_SUFFIX(flags, _EXTERNAL, AESNI) +#define EXTERNAL_AVX512(flags) CPUEXT_SUFFIX(flags, _EXTERNAL, AVX512) #define INLINE_AMD3DNOW(flags) CPUEXT_SUFFIX(flags, _INLINE, AMD3DNOW) #define INLINE_AMD3DNOWEXT(flags) CPUEXT_SUFFIX(flags, _INLINE, AMD3DNOWEXT)