Date: Fri, 04 Sep 1998 20:46:50 -0700 From: Mike Smith <mike@smith.net.au> To: Steve Passe <smp@csn.net> Cc: smp@FreeBSD.ORG Subject: Re: Big new SMP challenge (4x Xeon, 450NX) Message-ID: <199809050346.UAA05745@dingo.cdrom.com> In-Reply-To: Your message of "Fri, 04 Sep 1998 21:31:36 MDT." <199809050331.VAA17025@Ilsa.StevesCafe.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> Mike, > > > > I want one. > > > > Do you have a forklift? 8) > > I could get one! As long as having the bits of Jordan that didn't stick to the forklift smeared all over the side of the machine doesn't faze you, then I guess it's yours. 8) > > > > -- > > > > I/O APICs: APIC ID Version State Address > > > > 4 0x13 usable 0xfec10000 > > > > ... > > > > INT active-lo level 0 10:A 4 58 > > > > INT active-lo level 0 11:A 4 57 > > > > .. > > > > INT active-lo level 0 12:A 4 48 > > > > INT active-lo level 0 15:D 4 49 > > > > > > one APIC but pin#s higher than 24, some piece of the puzzle is missing. > > > Where can docs on the hardware be found? > > > > I don't know if they can; they're quite possibly still being written. > > I'll ask our source and see what they can come up with. > > > > Is it possible that this might be a new APIC? Any suggestions on part > > numbers to look for on the board? Anything in the SMP kernel output to > > look for that would identify it? > > The IO APIC is traditionally part of the motherboard chipset. So the place > to start would be to get a set of docs on the 450NX chipset. That would explain why I've never seen anything suspiciously APIC-like on any other board. What I get for not reading more I guess. Anyway, the 450NX datasheet is available as: ftp://download.intel.com/design/pcisets/datashts/24377101.pdf and there's a specification update at ftp://download.intel.com/design/pcisets/SPECUPDT/24384803.pdf > > The inference here is of course that if there's more than one APIC, we > > have trouble because we run out of room in the interrupt mask, correct? > > Correct to the extent that we have a completely "plug-n-play" kernel, > but to get things rolling a simple hard-coded hack somewhere in mpapic.c > would probably get this beast to boot. Sounds good to me. What now? -- \\ Sometimes you're ahead, \\ Mike Smith \\ sometimes you're behind. \\ mike@smith.net.au \\ The race is long, and in the \\ msmith@freebsd.org \\ end it's only with yourself. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199809050346.UAA05745>