From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/2879 Path: news.gmane.org!not-for-mail From: Rob Landley Newsgroups: gmane.linux.lib.musl.general Subject: Re: ARM optimisations Date: Mon, 04 Mar 2013 12:55:01 -0600 Message-ID: <1362423301.29250.16@driftwood> References: <20130302062102.GP20323@brightrain.aerifal.cx> Reply-To: musl@lists.openwall.com NNTP-Posting-Host: plane.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; DelSp=Yes; Format=Flowed Content-Transfer-Encoding: quoted-printable X-Trace: ger.gmane.org 1362423319 16640 80.91.229.3 (4 Mar 2013 18:55:19 GMT) X-Complaints-To: usenet@ger.gmane.org NNTP-Posting-Date: Mon, 4 Mar 2013 18:55:19 +0000 (UTC) Cc: musl@lists.openwall.com To: musl@lists.openwall.com Original-X-From: musl-return-2880-gllmg-musl=m.gmane.org@lists.openwall.com Mon Mar 04 19:55:39 2013 Return-path: Envelope-to: gllmg-musl@plane.gmane.org Original-Received: from mother.openwall.net ([195.42.179.200]) by plane.gmane.org with smtp (Exim 4.69) (envelope-from ) id 1UCaXz-0000Zg-Gs for gllmg-musl@plane.gmane.org; Mon, 04 Mar 2013 19:55:39 +0100 Original-Received: (qmail 26545 invoked by uid 550); 4 Mar 2013 18:55:17 -0000 Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: Original-Received: (qmail 26537 invoked from network); 4 Mar 2013 18:55:17 -0000 X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=x-received:date:from:subject:to:cc:in-reply-to:x-mailer:message-id :mime-version:content-type:content-disposition :content-transfer-encoding:x-gm-message-state; bh=5JOf74EdrWKgSdYy6JCLiAvNXVhZBp0mZlNpS40iH8o=; b=WlI3svH0ZzvZGY0XrX0ffzB9fPqDX024HyJaDaph09pkceYvLkmRnwjAugfwLAxiIn 1vxTzd0Pf9rmpEB6JQei0g8jfRUbFoplI05Yw4TM/jFhrdOf6FYDyMjlsPbcqtlTqIsp JfOa+N6u7LRZkOeKDsPNo3Qnq3xWe4usmgFiPAZuRAATMdXlAqU1i8aoW0tMqd8nBxzM fvfv3NJLArGiPTBGMwcdGSHJjvVkJXMgLjNuXnU+zdMD2DkLInOQUrfPrrcwnpj8DY5l jUNrrz4hRVuwPs3AgvoUYr7+zXhm/ynFxuUIWYpYkiKJDtMTWvbQFj3HYPLQ4G/c94Y5 bgIg== X-Received: by 10.50.208.40 with SMTP id mb8mr3363863igc.91.1362423304971; Mon, 04 Mar 2013 10:55:04 -0800 (PST) In-Reply-To: <20130302062102.GP20323@brightrain.aerifal.cx> (from dalias@aerifal.cx on Sat Mar 2 00:21:02 2013) X-Mailer: Balsa 2.4.11 Content-Disposition: inline X-Gm-Message-State: ALoCoQnUPVrmiKkOO4r6/WNqomZzb7QJkuD8z+m4TQhH5YXoRKpzRyRR2ZJlDD06ESpRgiFzEA7D Xref: news.gmane.org gmane.linux.lib.musl.general:2879 Archived-At: On 03/02/2013 12:21:02 AM, Rich Felker wrote: > > systems aren't that common. (They existed, the tin can tools nail > > board used one, but the generic C code works for them. Point is I'm > > not sure they're worth _optimizing_ for if it costs the vast > > majority of systems a 25% performance hit and we don't want to > > maintain multiple versions. If you _have_ an armv5 version, the > > armv4 one won't/shouldn't get much testing.) >=20 > Can you explain why you think a version that's v4 compatible will be > that much slower? If so, v5 code can be used as long as it checks > __hwcap and falls back to a simple working version... Alas, I do not have recent benchmarks. The timesys guys benched various =20 stuff in 2006 and that's where I grabbed the 25% figure. I mostly test =20 under qemu, where benchmarks are meaningless for real hardware. If I'm in error, ignore me. Rob=