maximum of CPUs
tlambert2 at mindspring.com
Wed Jul 16 22:59:14 PDT 2003
John Baldwin wrote:
> On 16-Jul-2003 Terry Lambert wrote:
> >> This is from the current code that is trying to renumber the I/O
> >> APIC's since they collide with CPUs. I've completely rewritten
> >> all the mptable code, but I don't support renumbering I/O APICs
> >> yet. I was really hoping that the BIOS would help us out enough
> >> to keep the IDs from overlapping.
> > I thought it had to, to be MP Spec 1.4 compliant?!?
> What had to be what to be compliant?
I thought the BIOS had to "help us out enough" for the motherboard
to be MP Spec 1.4 compliant.
> > This whole "stuff everything into ACPI and to hell with the
> > standards" thing that vendors are doing on Intel these days
> > is really, really annoying.
> No, it's correct. The mptable is quite limited and ACPI's
> configuration mechanism is much cleaner. Complaining about
> ACPI in this matter only serves to display your ignorance of
> what it is and how it works. Please educate yourself on the
> real issues first, thanks.
Please take a look at the picture of Warner's laptop which failed
to turn on the fans or reduce the CPU speed when the temperature
went up, and warped the display and keyboard as it practically
melted them into unrecognizability, thanks to the ACPI not working
like it was supposed to work, even if you turned off autosuspend.
Also, please read the Intel Multiprocessing Specification version
1.4, and note that it says nothing whatsoever about ACPI replacing
the MPTable, and that the MPTable is the only documented standard
mechanism for implementing obtaining MP information in an Intel
Multiprocessing Specification version 1.4 compliant fashion.
ACPI may have a cleaner interface, but standards rule when it comes
to trying to get software running (and I have yet to see APM turn a
laptop into "The Incredible Melting Man": anything that works is
better than anything that doesn't).
More information about the freebsd-smp