Date: Thu, 03 May 2012 14:48:15 +0200 From: Gabor Kovesdan <gabor@FreeBSD.org> To: Steven Atreju <snatreju@googlemail.com> Cc: net@freebsd.org, Luigi Rizzo <rizzo@iet.unipi.it>, "K. Macy" <kmacy@freebsd.org>, current@freebsd.org Subject: Re: fast bcopy... Message-ID: <4FA27E8F.2040402@FreeBSD.org> In-Reply-To: <20120503102844.GU633@sherwood.local> References: <20120502182557.GA93838@onelab2.iet.unipi.it> <20120502215249.GT633@sherwood.local> <CAHM0Q_NNoMrtwcz-xoQ34oVmgJSyjeb_7O6qBHCe16eFeTot_w@mail.gmail.com> <20120503102844.GU633@sherwood.local>
next in thread | previous in thread | raw e-mail | index | archive | help
Em 03-05-2012 12:28, Steven Atreju escreveu: > Yes, of course. > Though i was kinda, even shocked, once i've seen this first: > > http://marc.info/?l=dragonfly-commits&m=132241713812022&w=2 I also experimented a bit with some trivial libc functions when testing a change for memcpy (still in queue, will send it out for review once I have some more detailed benchamrks) and I also noticed that sometimes the trivial C version performed just like the assembly code. It is definitely something that needs some cleanup and I'm interested in working on it but cannot afford too much time at the moment. Gabor
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4FA27E8F.2040402>