Date: Tue, 6 Dec 2005 12:01:13 -0800 From: "David O'Brien" <obrien@freebsd.org> To: "O. Hartmann" <ohartman@mail.uni-mainz.de> Cc: freebsd-amd64@freebsd.org Subject: Re: 64bit FreeBSD performance Message-ID: <20051206200113.GF76476@dragon.NUXI.org> In-Reply-To: <43949054.7080404@mail.uni-mainz.de> References: <200511292057.13225.dantavious@comcast.net> <20051205174815.GB76476@dragon.NUXI.org> <43949054.7080404@mail.uni-mainz.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Dec 05, 2005 at 08:09:08PM +0100, O. Hartmann wrote: > David O'Brien wrote: > >Your statement is hard to parse - to figure out what you're really > >saying. VMware 5.5 runs fine on AMD Athlon64 3700 (754-pin) systems if > >you are running a 32-bit host and want to run 64-bit guests. If you want > >to run a 64-bit guest you need a revision D or later Athlon64. 64-bit > >754-pin Semprons qualify. It isn't an issue of the number of pins the > >CPU has. You cannot run a 64-bit guest on a 939-pin rev.CG Athlon64. > > Just for my information: what is the difference between those 'older' > socket 939-athlon64 and newer CPUs that they aren't capable of running a > 64-bit guest system? Opteron/Athlon64 rev.D added segment limits to long mode. > Well, I'm just only familiar with the so called 'market-names' of the > Athlon64 chip series, like 'Winchester' or 'Venice'. Those are the core code names - which not only include architecture changes, but metal layers and other fab things. I only care about the architecture database revisions. I.E. only the things that software can "see", vs. fab things the OC'ers care about. -- -- David (obrien@FreeBSD.org)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20051206200113.GF76476>