[NTLUG:Discuss] inconsistent sound (expanded discussion)

[Bryan J. Smith]

On Tue, 2004-10-26 at 22:35, Bryan J. Smith wrote:
> Ironically, nearly all Socket-478 and 462 mainboards don't have any
> better PCI -- maybe 0.25GBps (64-bit slots) if you're lucky.
>  ...
> Yes, I have heard it in games in Windows as well as when doing a lot of
> disk I/O in either, and all you have is a single 0.125GBps PCI channel.
>  ...
> Luckily for consumers, PCI-Express solves it for a lot cheaper than
> PCI-X.  Mainboards are already out for the LGA-775, and ones for
> Socket-939/940 hit next month.

I guess I didn't explain this further.

In the days of P3 and earlier, you had ATA disks that were capable of
_maybe_ 25MBps (0.025GBps) -- not even 1/5th of PCI ideal.  Occasionally
you'd get some interference, but not much.

Nowdays, we have ATA disks bursting 60MBps (0.06GBps) and higher! 
That's quickly starting to saturate the measly, shared 0.125GBps PCI
bus.  The result is contention, resulting in latency, hence the
inconsistent sound.

So the first usage of dedicated 0.125GBps PCI-Express x1 channels is for
ATA.  This keeps disk I/O from saturating the legacy, shared 0.125GBps
PCI bus.  Another is for Gigabit Ethernet (GbE) as well.  These are both
in the "southbridge" of the traditional chipset.

Hence why most PCI-Express chipsets coming out with 20 channels are
implemented in mainboards with (1) PCI-Express x16 slot (graphics), (2)
PCI-Express x1 slots and (4) legacy PCI slots.  Because the two (2)
remaining x1 slots are used internal to the southbridge for ATA and GbE.


-- 
Bryan J. Smith                                  b.j.smith at ieee.org 
------------------------------------------------------------------ 
"Communities don't have rights. Only individuals in the community
 have rights. ... That idea of community rights is firmly rooted
 in the 'Communist Manifesto.'" -- Michael Badnarik