Date: Thu, 10 Jun 2004 12:14:30 -1000 From: juli mallett <jmallett@FreeBSD.org> To: Ralf Baechle <ralf@linux-mips.org> Cc: freebsd-mips@FreeBSD.org Subject: Re: Some MIPS status goodies. Message-ID: <20040610221430.GA26579@FreeBSD.org> In-Reply-To: <20040610160207.GB32315@linux-mips.org> References: <Pine.LNX.4.33.0406101040240.2858-100000@servww6.ww.uni-erlangen.de> <20040610090712.GA71925@FreeBSD.org> <20040610160207.GB32315@linux-mips.org>
next in thread | previous in thread | raw e-mail | index | archive | help
* Ralf Baechle <ralf@linux-mips.org> [ Date: 2004-06-10 ] [ w.r.t. Re: Some MIPS status goodies. ] > On Wed, Jun 09, 2004 at 11:07:12PM -1000, juli mallett wrote: > > > R10K and IP28 support are probably a ways away, but I'm interested > > in supporting these systems and more. Right now it's easiest to start > > with the, much simpler, R4400 Indigo2 I have here, and get a good base > > of this stuff, then move into supporting the more modern and complex > > CPUs and machines - but be assured I am taking them into account! > > R10000 in non-coherent systems (Indigo 2 R10000, O2) is a rather hard to > use processor due to unwanted behaviour of speculative execution that > leads to memory corruption. The workarounds are fairly complex; efficient > solutions involve compiler modifications. Yeah, I read about the compiler mods SGI had to make, with accessing the stack as a barrier... It sounded like that was only for the kernel though, yeah? > That said, the R10000's is resolving all hazards in hardware and does > almost the entire coherency in software so in a saner system such as > the Origin it's a breeze. Right. juli. -- juli mallett. jmallett@freebsd.org. adrift in the pacific.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040610221430.GA26579>