linux-mips-fnet
[Top] [All Lists]

Re: [patch] linux: declance multicast filter fixes

To: Harald Koerfgen <hkoerfg@web.de>
Subject: Re: [patch] linux: declance multicast filter fixes
From: "Maciej W. Rozycki" <macro@ds2.pg.gda.pl>
Date: Tue, 2 Apr 2002 12:32:43 +0200 (MET DST)
Cc: Dave Airlie <airlied@csn.ul.ie>, Ralf Baechle <ralf@uni-koblenz.de>, linux-mips@fnet.fr, linux-mips@oss.sgi.com
In-reply-to: <E16qrGh-0004Vu-00@smtp.web.de>
Organization: Technical University of Gdansk
On Fri, 29 Mar 2002, Harald Koerfgen wrote:

> > Why couldn't it do the same for the LANCE?
> > Host memory addresses are generated on behalf of the LANCE by the I/O ASIC
> > anyway.
> 
> Probably because this would have made the IOASIC 0.0034 cents more expensive?

 I don't think that mattered to DEC that much.  DEC customers were
technically oriented and the design and engineering quality mattered much
to them.  The network performance certainly did.  DECstations were not
PCs.

 The reason might have been the lack of time or appropriate people
available for the task.  Or simply an oversight. 

> > Of course not all designers have a clue, sigh...  A brief study of
> > available documentation suggests no merging mode was implemented for the
> > LANCE and bit 0 of addresses generated is simply hardwired to 0. :-(
> 
> That's my interpretation as well.

 But we do not have a definite and complete I/O ASIC reference specs. 
Also note that the chip consists partly of general-purpose circuits which
operation depends on the actual wiring. 

-- 
+  Maciej W. Rozycki, Technical University of Gdansk, Poland   +
+--------------------------------------------------------------+
+        e-mail: macro@ds2.pg.gda.pl, PGP key available        +

<Prev in Thread] Current Thread [Next in Thread>
  • Re: [patch] linux: declance multicast filter fixes, Maciej W. Rozycki <=