From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/10450 Path: news.gmane.org!.POSTED!not-for-mail From: Rob Landley Newsgroups: gmane.linux.lib.musl.general Subject: Re: [J-core] Aligned copies and cacheline conflicts? Date: Wed, 14 Sep 2016 19:58:52 -0500 Message-ID: <8498eaa7-f263-efc8-a59c-d601e84af2db@landley.net> References: <0c256cb1-d0fa-9a5a-3976-b7ef545c1827@landley.net> <20160915003451.GC15995@brightrain.aerifal.cx> Reply-To: musl@lists.openwall.com NNTP-Posting-Host: blaine.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit X-Trace: blaine.gmane.org 1473901164 3211 195.159.176.226 (15 Sep 2016 00:59:24 GMT) X-Complaints-To: usenet@blaine.gmane.org NNTP-Posting-Date: Thu, 15 Sep 2016 00:59:24 +0000 (UTC) User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.2.0 Cc: "j-core@j-core.org" , musl@lists.openwall.com To: Rich Felker Original-X-From: musl-return-10463-gllmg-musl=m.gmane.org@lists.openwall.com Thu Sep 15 02:59:20 2016 Return-path: Envelope-to: gllmg-musl@m.gmane.org Original-Received: from mother.openwall.net ([195.42.179.200]) by blaine.gmane.org with smtp (Exim 4.84_2) (envelope-from ) id 1bkL1A-0007Uz-Sz for gllmg-musl@m.gmane.org; Thu, 15 Sep 2016 02:59:09 +0200 Original-Received: (qmail 13777 invoked by uid 550); 15 Sep 2016 00:59:08 -0000 Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-ID: Original-Received: (qmail 13742 invoked from network); 15 Sep 2016 00:59:07 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=landley-net.20150623.gappssmtp.com; s=20150623; h=subject:to:references:cc:from:message-id:date:user-agent :mime-version:in-reply-to:content-transfer-encoding; bh=yplyQ8eRdAemwlF/tbA5vAtn44vs/CQRykUvP9OE4mU=; b=Rj6BZB12PN4SibptrTh2G6EBFzld7Ao5GdKkeCp8xOCIkzDmWoUwg9UbSMBesY9C+Z RH0wKdm9yHRO1CEkSz32fIaoD4IsKuXnhObXE2GekWf5B/g84VUo9PaKGM6B81Wf2baX MB6cmu+s0UVlEVv1aKuwv2azH5m+tu/uTWKQGH6nIHm5gYoha65Lph4YiTaD401Et4em bWU1Yk6y6Gc890fkg6KLQGHqfNsgs7ioVLXL+6MRA/NeCwEcXzIL1NpoYNIsfbwEAiSZ dDlA+U5Wz5NO/RDePK12SgY+09/2VRDOmpVKsfpkAzE48zcPhylGaDXHdmapCR3rXV9/ kSgw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:subject:to:references:cc:from:message-id:date :user-agent:mime-version:in-reply-to:content-transfer-encoding; bh=yplyQ8eRdAemwlF/tbA5vAtn44vs/CQRykUvP9OE4mU=; b=ZulRQoTIzw8bXdi5vNHvhP7mwUzVy7c+D+lSkOE/DV373euik2PcmuZ8LOkSFiLkaE ek2o9VtULlNOjSEp4rUVCt3qA/xcU+DHDzyVpDqxvhLjTe8QWWek7s8qgYhW6U28xlMp Nq5Day2TrAd4faGbCr8CIoTZwGdQi18dbbfIHQ6pKcndddG0cK7Y77JL6i4t7rBYamVt dtr2kZzLUZO10q+DFwGbIXqBuJDQ/9Kx+/aYi6sXeZ+JQQjQN2evxBSsrnhk1NLecgMJ HHfdZUshzEACE+hXL2KBTMCqFSnfmAXtw42Zyj4twoHfMyVg6xShC/AZC7W8PZaT7A2X x2MA== X-Gm-Message-State: AE9vXwMyA/iVhrISrzYrL+c1DEK6mrA/W7gF2u1acu8zkGdIMYlIpvYgaF7OWmOgQFkUyQ== X-Received: by 10.157.57.130 with SMTP id y2mr4853961otb.73.1473901134828; Wed, 14 Sep 2016 17:58:54 -0700 (PDT) In-Reply-To: <20160915003451.GC15995@brightrain.aerifal.cx> Xref: news.gmane.org gmane.linux.lib.musl.general:10450 Archived-At: On 09/14/2016 07:34 PM, Rich Felker wrote: > I could put a fork of memcpy.c in sh/memcpy.c and work on it there and > only merge it back to the shared one if others test it on other archs > and find it beneficial (or at least not harmful). Both musl and the kernel need it. And yes at the moment it seems architecture-specific, but it's a _big_ performance difference... Rob