On Fri, Apr 09, 2004 at 10:25:45PM -0800, Erik E. Fair wrote:
> At 14:51 +0200 4/9/04, Joachim Kuebart wrote:
> 

<snippy snippy>
 
> As it happens, I have a DigitalServer 3305, which says:
> 
> cia0 at mainbus0: DECchip 2117x Core Logic Chipset (ALCOR/ALCOR2), pass 3
> cia0: extended capabilities: 21<DWEN,BWEN>
> cia0: using BWX for PCI config access
> pci0 at cia0 bus 0
> 
> So I'm definitely interested in getting this fixed. Without knowing 
> the particulars of the intialization process, I'd say #3 is the right 
> thing, given that Jason (who made this change in the first place) was 
> trying to put it in a variable - he just didn't do it soon enough.
> 
> If that can't/doesn't work, I'd say that going back to #1 is best. 
> Really, this amounts to needing a piece of information in order to do 
> an initialization properly; I don't think we should set up an 
> initialization routine to get call more than once as in #2, unless 
> there is some expectation that the system needs that level of 
> dynamism (i.e. it's hot-plug replaceable or something).
> 

This may be a question with an obvious answer, but I thought I'd ask here
(out of laziness, I admit):

Do all 21164s do BWX? I was, according to something I read long ago, under
the impression that only the 21164A had this capability. I own an
AlphaStation 600 5/266, with a 266mhz 21164, and I'm wondering if fixing the
BWX-enabling stuff would help its performance any. Compared to my Ultra 5,
at 270mhz, with the same amount of ram and twice as much L2 cache (but no
L3, the Alpha has 2MB of L3), it runs pretty slowly. I would have expected
the performance gap to be smaller, but the 21164 is (AFAIK) a good deal
older than the UltraSPARC-IIi, so perhaps that's it.

Anyway, I digress. Would BWX being enabled squeeze some extra performance
out of this 60 pound space heater / mail server?

-Sean

--
/~\ The ASCII
\ / Ribbon Campaign                   Sean Davis
 X  Against HTML                       aka dive
/ \ Email!