PCI USB controller with a kick needed

[scott-DPNOqEs/LNQ at public.gmane.org (Scott Ehrlich)]

On Wed, 16 May 2007, Martin Owens wrote:

> The goal of all USB 2.0 chipsets is to provide that given the number
> of devices connected. so if you end up buying a card with 6 ports just
> use a single port on each pair although I doubt very much that the
> chip on the card suffers any real performance problems with more than
> one device through the same chip.

Out of curiosity, for my own education, is there documentation stating the 
chipset requirements?   I spent some time at usb.org (per a link from 
intel.com) and couldn't find anything definitive.

Thanks.

Scott

>
> So I guess what your looking for is a PCI Express (not sure what pci-x
> is) card with multiple USB 2.0 chips of which you will use only a
> single port per chip.
>
> Seems reasonable given that each usb pair uses it's own chip.
>
> On 16/05/07, Scott R Ehrlich <scott-3s7WtUTddSA at public.gmane.org> wrote:
>> The goal, be it a PCI, PCI-e, or PCI-x card, is to permit each port to
>> provide dedicated maximum throughput for the device connected to said
>> port.
>> 
>> Scott
>> 
>> Quoting Martin Owens <doctormo-Re5JQEeQqe8AvxtiuMwx3w at public.gmane.org>:
>> 
>> > The problem with your request is that each usb chipset that I know of
>> > supports at least 2 each, they seem to always come in pairs and never
>> > a single usb port.
>> >
>> > I suppose you could have a card that only uses one port of each pair,
>> > but then your udev/HAL would be a mess.
>> >
>> > Best Regards, Martin Owens
>> >
>> > On 16/05/07, Scott R Ehrlich <scott-3s7WtUTddSA at public.gmane.org> wrote:
>> >> I'm looking for a PCI-e or PCI-x USB controller card where each port
>> >> on the card
>> >> has its own separate processor.   Thus, a 4-port USB card would have 4
>> >> processors, 1 each per port.
>> >>
>> >> Does something like that exist?
>> >>
>> >> Thanks!
>> >>
>> >> Scott
>> >>
>> >> --
>> >> This message has been scanned for viruses and
>> >> dangerous content by MailScanner, and is
>> >> believed to be clean.
>> >>
>> >> _______________________________________________
>> >> Discuss mailing list
>> >> Discuss-mNDKBlG2WHs at public.gmane.org
>> >> http://lists.blu.org/mailman/listinfo/discuss
>> >>
>> >
>> 
>> 
>> 
>
> -- 
> This message has been scanned for viruses and
> dangerous content by MailScanner, and is
> believed to be clean.
>
> _______________________________________________
> Discuss mailing list
> Discuss-mNDKBlG2WHs at public.gmane.org
> http://lists.blu.org/mailman/listinfo/discuss
>

-- 
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.