[comp.dcom.lans] FDDI Cards

fmf@cbnewsl.cb.att.com (frank.fawzi) (05/22/91)

Does anyone know of an FDDI card for the ISA (AT BUS)?  What about
MCA or EISA Buses?  Does it make sense from a through-put stand
point to use an FDDI card in an ISA box with a 386 processor?  


Frank Fawzi
fmf@mtuni.att.com
(908) 957-2724

sblair@upurbmw.dell.com (Steve Blair) (05/22/91)

In article <1991May21.190618.2247@cbnewsl.att.com>, fmf@cbnewsl.cb.att.com (frank.fawzi) writes:
|> 
|> Does anyone know of an FDDI card for the ISA (AT BUS)?  What about
|> MCA or EISA Buses?  Does it make sense from a through-put stand
|> point to use an FDDI card in an ISA box with a 386 processor?  
|> 

Frank --


Get in touch with Network Perepherials Inc., in San Jose Ca(as I
remember). They've got several, and I've used them for some PC based
FDDI demos for Interop '90 while I worked at SynOptics...

Seemed like a nice, reliable product. I was just a happy customer....

-- 
Steve Blair	DELL	UNIX	DIVISION sblair@upurbmw.dell.com
================================================================

*Notice:   "/earth is 98% full, please delete anyone you can...."
					-anonymous @dell.com

vjs@rhyolite.wpd.sgi.com (Vernon Schryver) (05/23/91)

 
>                     Does it make sense from a through-put stand
> point to use an FDDI card in an ISA box with a 386 processor?  

It makes sense only if the 386 system (hardware and software including
operating system) needs more than ethernet speeds.  The bottleneck when
you're actually using FDDI to move data instead of cook numbers with a
bogus, toy benchmark is never the bus.  It's the softwar.  Yeah, "never" is
no doubt too strong; someone probably has a real peach of bus.  While
"real" benchmarks like ttcp are only distantly related to real
applications, the bogus benchmarks I mean are most of those that claim to
show a system can transmit over FDDI at 100Mb/s.  Most of those are blarney
designed to demonstrate that the hardware is not completely misdesigned.
People often write a little code to convince the AMD DPC-RBC chipset to
babble the same frames in a loop, and then claim their system runs at
100Mb/s.  These people try the same frauds with ethernet chips.

High performance workstations can push several MByte/sec thru TCP/FDDI.
They might feel the pinch of a bus as slow as ISA.  However, most 386
systems seem far slower.  They're not likely to notice whether they are
using 20% of the ethernet or 2% of FDDI.


Vernon Schryver,   vjs@sgi.com

brunner@practic.UUCP (Thomas Eric Brunner) (05/24/91)

In article <20227@uudell.dell.com> sblair@upurbmw.dell.com (Steve Blair) writes:
>In article <1991May21.190618.2247@cbnewsl.att.com>, fmf@cbnewsl.cb.att.com (frank.fawzi) writes:
>|> 
>|> Does anyone know of an FDDI card for the ISA (AT BUS)?  What about
>|> MCA or EISA Buses?  Does it make sense from a through-put stand
>|> point to use an FDDI card in an ISA box with a 386 processor?  
>|> 

I'll also add Schneider & Koch, a German firm to Steve's recommendation.
They've an AMD 29000 on the card with tcp/ip already in place. Bandwidth
is a bit better than 3Mb/sec. When I survayed the field last InterOp (in
my copious free time), they appeared the fastest and most versatile, of
course, they may be more expensive due to the bit-slice engine.

Does it make sense? That depends. You can run the card standalone faster
than the rated clock for the cpu board, or you can argure that for some
applications throughput is inherently limited, e.g., attaching a tree of
cheapo boxes to a fddi ring.

In case it isn't obvious, I really wanted to build a TR/FDDI bridge out of
the S&K card. Unfortunately Santa had a surplus of coal.

-- 
#include <std/disclaimer.h>
Eric Brunner 4bsd/RT Project
inet: brunner@monet.berkeley.edu		uucp: uunet!practic!brunner
trying to understand multiprocessing is like having bees live inside your head.

maples@ddtg.com (Greg Maples) (06/27/91)

Since the topic of FDDI has come up...  I'm looking to experiment
with some FDDI interconnects for a new product.  We're thinking of
moving VERY large picture files around a net at high speeds.  Think
on the order of 32bits @ 300-1200 dpi, 11x17 image = lots of megs
PER LAYER!  Therefore, speed and bandwidth are important.

We're interested in a back-end compute engine for image processing
and a friendly front-end for the users...  So, a DEC or HP RISCy
machine with lots of mips and a set of macintoshes on the front end.

Question One:
Can I get a FDDI card for the new 50+ mips HP machines yet?
Question Two:
Ditto for the high end DEC machines?
Question Three ($64,000.00!!)
Is anyone, and I mean ANYONE, even working seriously on a 100MB
FDDI card for the high-end Macs????

If no on question three, we can port a likely card to Apple UNIX,
A/UX for our FDDI support, so how about another nubus machine
like the Next?

Please reply via mail where possible.
Thanks

-- 
Greg Maples                      | These are my opinions, not yours. Keep your
Systems Group Leader             | hands off 'em. They're also not the opinions
DuPont Design Technologies       | of my employer or yours. So there. (c) 1991
maples%ddtisvr@uunet.uu.net      | The preceding is an opinion which is mine.