At 12:13 PM 6/1/00 -0600, Warner Losh wrote:
>In message <[EMAIL PROTECTED]> Dennis writes:
>: Have you done bus performance testing with this card? Given the
>: architechture of the AMCC part, it seems highly improbable that you will be
>: able to get high throughput with such a card. Because the AMCC part
>: requires external logic it is impossible to do pass-through single cycle
>: bursts, which is required for efficient utilization of the PCI bus. Once
>: you begin holding off cycles the PCI bus totally pigs out (which is why
>: virtually all high-speed pci solutions are single-chip type designs).
>
>Yes. I've done drivers for several cards with this design. The AMCC
>part is very fussy and will often lock up the bus unless the card
>designer has put enough extra logic on the card to cope with the
>oddities of the card. Sadly, many don't.
We used it on our first (and now defunct) pci board, and we didnt have
trouble with lockups (there are quite a few errata that have to be
addresses), but the arbitration was pitifully slow. There was no way to get
high throughput across the bus. We completely rejected it for use on
T3...i find it interesting that someone did an OC3/ATM card with it.
Dennis
Emerging Technologies, Inc.
----------------------------------------------------------------------------
---------
http://www.etinc.com
ISA and PCI T1/T3/V35/HSSI Cards for FreeBSD and LINUX
Multiport T1 and HSSI/T3 UNIX-based Routers
Bandwidth Management Standalone Systems
Bandwidth Management software for LINUX and FreeBSD
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
