[linux-audio-user] CPU clock - beware

Ryan Underwood nemesis-lists at icequake.net
Sun Jul 25 22:50:40 EDT 2004


On Sun, Jul 25, 2004 at 03:13:37AM +0100, tim hall wrote:
> sure:
> ~$ cat /proc/cpuinfo
> processor       : 0
> vendor_id       : GenuineIntel
> cpu family      : 6
> model           : 8
> model name      : Celeron (Coppermine)
> stepping        : 6
> cpu MHz         : 896.977
> cache size      : 128 KB
> fdiv_bug        : no
> hlt_bug         : yes
> f00f_bug        : no
> coma_bug        : no
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 2
> wp              : yes
> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca 
> cmov pat pse36 mmx fxsr sse
> bogomips        : 1789.13

Yeah, definitely overclocked.  There are no Celerons with 128KB cache
that run with a 100Mhz bus, AFAIK.

> > "cpu MHz" the real current speed
> > "bogomips" issome weird timing value I have no idea what it means exactly
> It's a semi-arbitrary benchmarking value, usually twice the processor speed. 
> AFAIU.

Depends on the chip.  It is used to calculate the amount of time spent
in a particular kernel delay loop.  Some chips run this code faster or
slower than others.  It's not a benchmark as much as a calibration
value.

> This is what I guessed, I'm using the values specified in the manual for a 
> Coppermine FC-PGA 600, so:

Oops.  They could be referring to a PIII Coppermine, you know...

> at 3x clock ratio I get:
> CPU (I assume this is FSB) 100
> PCI 33
> AGP 66
> The display cache runs at 100MHz too, a 1:1 ratio seems logical.

1:1 CPU<->AGP ratio?  That's not going to work well at 100MHZ FSB.

> I think I might read it now. I'm a bit confused as to why my system thinks 
> it's running a 896MHz CPU, But so far there's no overt signs that it isn't 
> happy, so I'll prod it a bit and see ;-)

897MHz is just the FSB * 9.  It doesn't run exactly at 100MHz because it
would be impossible to do so while maintaining synchronicity with a
33MHz PCI bus.  33MHz is actually 33.something, so you end up with
99.something when the FSB is running at 3x the PCI frequency.

-- 
Ryan Underwood, <nemesis at icequake.net>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: Digital signature
Url : http://lists.linuxaudio.org/pipermail/linux-audio-user/attachments/20040725/9e445317/attachment.pgp 


More information about the Linux-audio-user mailing list