--==_Exmh_437718329P
Content-Type: text/plain; charset=us-ascii

In message <000701c35ff3$61ac2870$54a200d3@PAQ2>, you write: 

-> Steven J. Hill sjhilll@realitydiluted.com said;
-> 
-> > that IRIX locked up and had to be rebooted on O2 in certain heavy graphics
-> > load and PCI/DMA. In short, the R10K PCI addressing and coherency sucks
-> > rocks on O2. But don't let that discourage you :).
-> 
-> Does RM7000 O2 reveal the same symptom?  I guess the answer is no as RM7000
-> is the very straight forward descendent of 5000 and 52XX.

My guess would be "no" as well (though were there Rm7k O2s even made?) as
I believe the issues are mostly due to the speculative nature of the R10k
and lack of hardware cohorency.

My $0.02 marked down 50% since this has mostly been said before :-)
--rafal

----
Rafal Boni                                              rafal.boni@eDial.com
 PGP key C7D3024C, print EA49 160D F5E4 C46A 9E91  524E 11E0 7133 C7D3 024C


--==_Exmh_437718329P
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.6 (GNU/Linux)
Comment: Exmh version 2.4 06/23/2000

iD8DBQE/N6Y3EeBxM8fTAkwRAuvwAKCu4thmIabTbGIS7yrbVX/1M6meUgCg0Rjv
Snrmz88vtnbbiECou2hBLjU=
=b8EG
-----END PGP SIGNATURE-----

--==_Exmh_437718329P--