More Tyan S2466 Issues

[Robert G. Brown]

On Wed, 1 May 2002, Lambe, Dave wrote:

> UPDATE....
> After fiddling setting the BIOS to defaults, disabling "memory caching", and
> setting the default video to "PCI", I was able to get it to boot a little
> further. 
> Now, it boots to Part 1 (2kernal monte) and begins sending RARP requests.
> The "headnode" sees it and allows it to be "Activated", which assigns it as
> "Node 5"...MAC address...IP Address..."down". The node still says "Sending
> RARP request" to no avail. 
> I'll let it lay for a bit (in hopes it'll eventually come up).

See preceeding discussion about Tyan and slots (over the last week).  Be
sure that you try your cards in different slots.  For us this turned out
to be the "solution" to the 2460 problems we've encountered -- some slot
combinations don't work, others do.  Go figure.

Also be sure to visit www.amdmb.com and join the forum.  They have
many threads on the 2466; perhaps your problem is addressed there.

   rgb

> 
> Dave
> 
> -----Original Message-----
> From: Lambe, Dave [mailto:dave.lambe at targacept.com]
> Sent: Wednesday, May 01, 2002 9:29 AM
> To: Beowulf (E-mail)
> Subject: More Tyan S2466 Issues
> 
> 
> Hello,
> We recently purchased a 2U AMD from Aspen Systems for testing purposes. The
> jest was to run this box head to head with an Intel and buy more of the
> fastest (for our flavor of computing). The Intel booted (via Scyld floppy)
> without issue. The AMD box (using Tyan S2466, dual K7 2gig+ CPUs, & a TNT
> video card...that was added) boots (also via Scyld floppy) until it hits the
> part about "Ramdisk" and suddenly reboots. I have yet to get "jiggy with it"
> as the current workload isn't conducive to spending days figuring out
> hardware glitches.
> 
> My hope in posting here is hopefully grab a response from someone that's
> hashed this out or recieved a response from prior issues from Tyan.
> 
> Thanks,
> 
> Dave
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> 

-- 
Robert G. Brown	                       http://www.phy.duke.edu/~rgb/
Duke University Dept. of Physics, Box 90305
Durham, N.C. 27708-0305
Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu