On Fri, 2005-02-25 at 10:51 +0100, Geert Uytterhoeven wrote:
> On Thu, 24 Feb 2005, Kars de Jong wrote:
> > I changed the definitions to conform to the above table, and did some
> 
> So you changed GAYLE_DATA from 0x00 to 0x2000?

Yep. But that probably won't work for the A4000, see below.

> > simple timings using hdparm -t:
> > 
> > Old driver: 1.16 MB/s
> > New driver: 1.59 MB/s
> > 
> > So it does make a difference...
> 
> Impressive!

Still awfully slow compared to my SCSI disks :-P

> > Any problems with converting to the above addresses, and can anyone test
> > it on an A4000 (it has different addresses, but I'm assuming the 8/16
> > bit thing holds there too)?
> 
> I'm afraid it won't work, but I (or someone else, my Amiga is still not set up
> since my last move) could give it a try anyway, you wouldn't loose data if it
> doesn't work.

No, it looks like on the A4000 interface it's processor address line A1
which determines 16 or 8 bit transfer, whereas this line does nothing on
the A600/A1200 interface.

It's the only bit that is clear on the data register and set on the
other registers. I guess it looks like this on the A4000:

A12  A1   Chip Select Speed
0    0    _CS1        16 bit
0    1    _CS1         8 bit
1    0    _CS2        16 bit
1    1    _CS2         8 bit

So bit 1 of the address selects the access speed. The other bits are the
same: _CS1 or _CS2 are selected by processor address line A12 and the
disk drive address lines DA0, DA1, and DA2 are connected to processor
address lines A2, A3, and A4 respectively. Which means there's no speed
to be gained there on the A4000, the driver already does the right
thing.

I don't see how the IDE doubler can work on the A4000 though: with the
defines in the driver the data register of the second interface ends up
on the same address as the IRQ register...


Kind regards,

Kars.


-
To unsubscribe from this list: send the line "unsubscribe linux-m68k" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to