From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-f171.google.com (mail-pf0-f171.google.com [209.85.192.171]) by mail.openembedded.org (Postfix) with ESMTP id 807B16FEE0 for ; Mon, 11 Jan 2016 23:18:21 +0000 (UTC) Received: by mail-pf0-f171.google.com with SMTP id n128so51853396pfn.3 for ; Mon, 11 Jan 2016 15:18:22 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=subject:mime-version:content-type:from:in-reply-to:date:cc :message-id:references:to; bh=hf4IJvmeL86ZWOhkw7i151ndL843B5UWReZUlxb0T2Y=; b=fDeGQhYbdzRLYNHkTIM6zj6RFFQsgBrE2+CRmzwGDd/Q3p8B9vKanwUaJ90AxtWX2q MvlhBvosUhVV37M0Mv5eBupn8ySXpvAkuf2I2HZA528subQan6twbYoVIgmtSYAYnRex dUdyOalEk97LM6M8EfQBleXxePw3GYnlfA9ggHt+exkOxnilE2VR/AYx/Iq+gMCQTbEy UF2xAdTtzwJuDhHlJL26y0tLRGCJxZFkrzsHHeCgCWrk9UPTclmG/WK3R5cYQPRhtFh/ vjmodlfrR9KmvfeDOm2aJdYCnB2DV/DqFf2pJ3rpLXY/AXK6eM4FzcJEFlxazb+oOlVS 76QA== X-Received: by 10.98.15.213 with SMTP id 82mr30342538pfp.52.1452554301970; Mon, 11 Jan 2016 15:18:21 -0800 (PST) Received: from [192.168.0.4] (c-73-252-206-77.hsd1.ca.comcast.net. [73.252.206.77]) by smtp.gmail.com with ESMTPSA id xr8sm188067478pab.26.2016.01.11.15.18.21 (version=TLSv1/SSLv3 cipher=OTHER); Mon, 11 Jan 2016 15:18:21 -0800 (PST) Mime-Version: 1.0 (Mac OS X Mail 9.2 \(3112\)) X-Pgp-Agent: GPGMail 2.6b2 From: Khem Raj In-Reply-To: <1452553655.7598.206.camel@linuxfoundation.org> Date: Mon, 11 Jan 2016 15:18:17 -0800 Message-Id: <77011399-2719-4BA7-96B0-7040D169AA7E@gmail.com> References: <1452205752-6353-1-git-send-email-armccurdy@gmail.com> <1452205752-6353-4-git-send-email-armccurdy@gmail.com> <1452210004.2002.129.camel@pbcl.net> <4E2CA517-1339-416B-832B-AB2EFF04CEE6@gmail.com> <1452553655.7598.206.camel@linuxfoundation.org> To: Richard Purdie X-Mailer: Apple Mail (2.3112) Cc: openembedded-core@lists.openembedded.org Subject: Re: [PATCH v2 3/4] libav.inc: duplicate armv7a over-rides for armv7ve X-BeenThere: openembedded-core@lists.openembedded.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: Patches and discussions about the oe-core layer List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 11 Jan 2016 23:18:21 -0000 X-Groupsio-MsgNum: 75886 Content-Type: multipart/signed; boundary="Apple-Mail=_E34D398A-96FA-4493-8F65-D1516CA25A5A"; protocol="application/pgp-signature"; micalg=pgp-sha1 --Apple-Mail=_E34D398A-96FA-4493-8F65-D1516CA25A5A Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 > On Jan 11, 2016, at 3:07 PM, Richard Purdie = wrote: >=20 > On Mon, 2016-01-11 at 14:58 -0800, Khem Raj wrote: >>> On Jan 7, 2016, at 3:40 PM, Phil Blundell wrote: >>>=20 >>> On Thu, 2016-01-07 at 14:29 -0800, Andre McCurdy wrote: >>>> FULL_OPTIMIZATION_armv7a =3D "-fexpensive-optimizations -fomit >>>> -frame-pointer -O4 -ffast-math" >>>> +FULL_OPTIMIZATION_armv7ve =3D "-fexpensive-optimizations -fomit >>>> -frame-pointer -O4 -ffast-math" >>>=20 >>=20 >> O4 ? may be just replace this whole thing with -Ofast now a days >> -fexpensive-optimizations is enabled at -O2,-O3 anyway same for fomit >> -frame-pointer and -Ofast turns on >> feast-match on top of -O3 >>=20 >>> I wonder if this would be better as just FULL_OPTIMIZATION_arm. >>> That >>> said, the OPTIMIZATION variables are primarily distro knobs and >>> it's not >>> entirely clear that individual packages ought to be overriding them >>> at >>> all. >>>=20 >>> Does anybody know whether there is any actual science behind the >>> use of >>> those flags on armv7a specifically? >>=20 >> it came into ffmpeg circa 2008 and proliferated into related >> components primarily to support vectorization and neon >> which was quite nascent for ARM architecture in those days in gcc. >> Today if you were to configure libav with default options >> then it uses mainly -fomit-frame-pointer-O3 -fno-math-errno -fno >> -signed-zeros -fno-tree-vectorize >>=20 >> which is primarily -Ofast -fno-tree-vectorize >=20 > I have to admit that my personal instinct on these is simply to remove > them. I doubt they're buying much now and if people really want to = tune > specific recipes by hand they still can do so from their local/distro > config. Thats ok, however the most tested option combination seems to use -O3 = since thats configure=E2=80=99s default for libav If we start using -O2 .. as we use that for global optimizations in OE then we are odd man out. >=20 > Cheers, >=20 > Richard >=20 --Apple-Mail=_E34D398A-96FA-4493-8F65-D1516CA25A5A Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename=signature.asc Content-Type: application/pgp-signature; name=signature.asc Content-Description: Message signed with OpenPGP using GPGMail -----BEGIN PGP SIGNATURE----- Comment: GPGTools - https://gpgtools.org iEYEARECAAYFAlaUODwACgkQuwUzVZGdMxQdXgCfZZWxYkf9oOjCdTPVF5icmlhI FV4AnRPRnZK4etMwAfy63bTJZnZjj0ih =IF+C -----END PGP SIGNATURE----- --Apple-Mail=_E34D398A-96FA-4493-8F65-D1516CA25A5A--