Date: Sun, 6 Feb 2005 01:50:56 +0100 (CET) From: Sten Spans <sten@blinkenlights.nl> To: freebsd-amd64@freebsd.org Subject: Re: Would this system work correctly with FreeBSD 5.3 ? Message-ID: <Pine.SOC.4.61.0502060145280.14350@tea.blinkenlights.nl> In-Reply-To: <20050206003545.GK9350@dragon.nuxi.com> References: <20050122141741.9690.qmail@web26804.mail.ukl.yahoo.com> <41F31836.2010403@freebsd.org> <20050206003545.GK9350@dragon.nuxi.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, 5 Feb 2005, David O'Brien wrote: > > There are no heat issues, and the pin-out is identical to single-core > Opteron CPU's -- 940-pin. Dual-core CPU's work just fine in AMD's Quad > reference machine. That's good news. > > >>> - Quad motherboards: >>> It's a shame that tyan connects all >>> the pci interfaces on their quad motherboard >>> to one cpu. The hp/compaq quad proliant has >>> seperate buses to two cpu's for extra bandwith. > .. >> Also, I don't believe that PCI buses are connected to CPUs >> at all. They are connected via HT-PCI bridges that act as >> normal HT peers. Only memory is connected directly to the CPU. > > What he is saying is that Tyan put all the PCI-X & PCI controllers on a > single HT "chain" off of the BSP. A better design, such as the HP DL585, > connects its PCI-X controllers spread out over two CPU's (using HT > links). > The new tyan k8we looks pretty good, with all 3 of the motherboard support chips connected to different hypertransport links 2200 - pci-e x16, 32bits pci, gigabit, sata 2050 - pci-e x16, gigabit eth amd 8131 - pci-x, scsi Let's hope this won't be as troublesome as the nforce3 stuff :) -- Sten Spans "There is a crack in everything, that's how the light gets in." Leonard Cohen - Anthem
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SOC.4.61.0502060145280.14350>